1
|
Zhang Y, Huang Y, Hu K. Multi-scale object equalization learning network for intracerebral hemorrhage region segmentation. Neural Netw 2024; 179:106507. [PMID: 39003984 DOI: 10.1016/j.neunet.2024.106507] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/18/2023] [Revised: 05/31/2024] [Accepted: 07/02/2024] [Indexed: 07/16/2024]
Abstract
Segmentation and the subsequent quantitative assessment of the target object in computed tomography (CT) images provide valuable information for the analysis of intracerebral hemorrhage (ICH) pathology. However, most existing methods lack a reasonable strategy to explore the discriminative semantics of multi-scale ICH regions, making it difficult to address the challenge of complex morphology in clinical data. In this paper, we propose a novel multi-scale object equalization learning network (MOEL-Net) for accurate ICH region segmentation. Specifically, we first introduce a shallow feature extraction module (SFEM) for obtaining shallow semantic representations to maintain sufficient and effective detailed location information. Then, a deep feature extraction module (DFEM) is leveraged to extract the deep semantic information of the ICH region from the combination of SFEM and original image features. To further achieve equalization learning in different scales of ICH regions, we introduce a multi-level semantic feature equalization fusion module (MSFEFM), which explores the equalized fusion features of the described objects with the assistance of shallow and deep semantic information provided by SFEM and DFEM. Driven by the above three designs, MOEL-Net shows a solid capacity to capture more discriminative features in various ICH region segmentation. To promote the research of clinical automatic ICH region segmentation, we collect two datasets, VMICH and FRICH (divided into Test A and Test B) for evaluation. Experimental results show that the proposed model achieves the Dice scores of 88.28%, 90.92%, and 90.95% on the VMICH, FRICH Test A, and Test B, respectively, which outperform fourteen competing methods.
Collapse
Affiliation(s)
- Yuan Zhang
- Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education, Xiangtan University, Xiangtan 411105, China
| | - Yanglin Huang
- Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education, Xiangtan University, Xiangtan 411105, China.
| | - Kai Hu
- Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education, Xiangtan University, Xiangtan 411105, China; Key Laboratory of Medical Imaging and Artificial Intelligence of Hunan Province, Xiangnan University, Chenzhou 423000, China.
| |
Collapse
|
2
|
Fathi M, Eshraghi R, Behzad S, Tavasol A, Bahrami A, Tafazolimoghadam A, Bhatt V, Ghadimi D, Gholamrezanezhad A. Potential strength and weakness of artificial intelligence integration in emergency radiology: a review of diagnostic utilizations and applications in patient care optimization. Emerg Radiol 2024:10.1007/s10140-024-02278-2. [PMID: 39190230 DOI: 10.1007/s10140-024-02278-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/07/2024] [Accepted: 08/08/2024] [Indexed: 08/28/2024]
Abstract
Artificial intelligence (AI) and its recent increasing healthcare integration has created both new opportunities and challenges in the practice of radiology and medical imaging. Recent advancements in AI technology have allowed for more workplace efficiency, higher diagnostic accuracy, and overall improvements in patient care. Limitations of AI such as data imbalances, the unclear nature of AI algorithms, and the challenges in detecting certain diseases make it difficult for its widespread adoption. This review article presents cases involving the use of AI models to diagnose intracranial hemorrhage, spinal fractures, and rib fractures, while discussing how certain factors like, type, location, size, presence of artifacts, calcification, and post-surgical changes, affect AI model performance and accuracy. While the use of artificial intelligence has the potential to improve the practice of emergency radiology, it is important to address its limitations to maximize its advantages while ensuring the safety of patients overall.
Collapse
Affiliation(s)
- Mobina Fathi
- Advanced Diagnostic and Interventional Radiology Research Center (ADIR), Tehran University of Medical Sciences, Tehran, Iran
- School of Medicine, Shahid Beheshti University of Medical Sciences, Tehran, Iran
| | - Reza Eshraghi
- Student Research Committee, Kashan University of Medical Science, Kashan, Iran
| | | | - Arian Tavasol
- School of Medicine, Shahid Beheshti University of Medical Sciences, Tehran, Iran
| | - Ashkan Bahrami
- Student Research Committee, Kashan University of Medical Science, Kashan, Iran
| | | | - Vivek Bhatt
- School of Medicine, University of California, Riverside, CA, USA
| | - Delaram Ghadimi
- School of Medicine, Shahid Beheshti University of Medical Sciences, Tehran, Iran
| | - Ali Gholamrezanezhad
- Keck School of Medicine of University of Southern California, Los Angeles, CA, USA.
- Department of Radiology, Division of Emergency Radiology, Keck School of Medicine, Cedars Sinai Hospital, University of Southern California, 1500 San Pablo Street, Los Angeles, CA, 90033, USA.
| |
Collapse
|
3
|
Yalcinkaya DM, Youssef K, Heydari B, Wei J, Merz NB, Judd R, Dharmakumar R, Simonetti OP, Weinsaft JW, Raman SV, Sharif B. Improved Robustness for Deep Learning-based Segmentation of Multi-Center Myocardial Perfusion MRI Datasets Using Data Adaptive Uncertainty-guided Space-time Analysis. J Cardiovasc Magn Reson 2024:101082. [PMID: 39142567 DOI: 10.1016/j.jocmr.2024.101082] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/09/2023] [Revised: 06/14/2024] [Accepted: 08/07/2024] [Indexed: 08/16/2024] Open
Abstract
BACKGROUND Fully automatic analysis of myocardial perfusion MRI datasets enables rapid and objective reporting of stress/rest studies in patients with suspected ischemic heart disease. Developing deep learning techniques that can analyze multi-center datasets despite limited training data and variations in software (pulse sequence) and hardware (scanner vendor) is an ongoing challenge. METHODS Datasets from 3 medical centers acquired at 3T (n = 150 subjects; 21,150 first-pass images) were included: an internal dataset (inD; n = 95) and two external datasets (exDs; n = 55) used for evaluating the robustness of the trained deep neural network (DNN) models against differences in pulse sequence (exD-1) and scanner vendor (exD-2). A subset of inD (n = 85) was used for training/validation of a pool of DNNs for segmentation, all using the same spatiotemporal U-Net architecture and hyperparameters but with different parameter initializations. We employed a space-time sliding-patch analysis approach that automatically yields a pixel-wise "uncertainty map" as a byproduct of the segmentation process. In our approach, dubbed Data Adaptive Uncertainty-Guided Space-time (DAUGS) analysis, a given test case is segmented by all members of the DNN pool and the resulting uncertainty maps are leveraged to automatically select the "best" one among the pool of solutions. For comparison, we also trained a DNN using the established approach with the same settings (hyperparameters, data augmentation, etc.). RESULTS The proposed DAUGS analysis approach performed similarly to the established approach on the internal dataset (Dice score for the testing subset of inD: 0.896 ± 0.050 vs. 0.890 ± 0.049; p = n.s.) whereas it significantly outperformed on the external datasets (Dice for exD-1: 0.885 ± 0.040 vs. 0.849 ± 0.065, p < 0.005; Dice for exD-2: 0.811 ± 0.070 vs. 0.728 ± 0.149, p < 0.005). Moreover, the number of image series with "failed" segmentation (defined as having myocardial contours that include bloodpool or are noncontiguous in ≥1 segment) was significantly lower for the proposed vs. the established approach (4.3% vs. 17.1%, p < 0.0005). CONCLUSIONS The proposed DAUGS analysis approach has the potential to improve the robustness of deep learning methods for segmentation of multi-center stress perfusion datasets with variations in the choice of pulse sequence, site location or scanner vendor.
Collapse
Affiliation(s)
- Dilek M Yalcinkaya
- Laboratory for Translational Imaging of Microcirculation, Indiana University School of Medicine, Indianapolis, IN, USA; Elmore Family School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA
| | - Khalid Youssef
- Laboratory for Translational Imaging of Microcirculation, Indiana University School of Medicine, Indianapolis, IN, USA; Krannert Cardiovascular Research Center, Dept. of Medicine, Indiana Univ. School of Medicine, Indianapolis, IN, USA
| | - Bobak Heydari
- Stephenson Cardiac Imaging Centre, Department of Cardiac Sciences, University of Calgary, Alberta, Canada
| | - Janet Wei
- Barbra Streisand Women's Heart Center, Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, CA, USA
| | - Noel Bairey Merz
- Barbra Streisand Women's Heart Center, Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, CA, USA
| | - Robert Judd
- Division of Cardiology, Department of Medicine, Duke University, Durham, NC, USA
| | - Rohan Dharmakumar
- Krannert Cardiovascular Research Center, Dept. of Medicine, Indiana Univ. School of Medicine, Indianapolis, IN, USA; OhioHealth, Columbus, OH, USA
| | - Orlando P Simonetti
- Department of Medicine, Davis Heart and Lung Research Institute, The Ohio State University, Columbus, OH, USA
| | - Jonathan W Weinsaft
- Division of Cardiology at NY Presbyterian Hospital, Weill Cornell Medical Center, New York, NY, USA
| | - Subha V Raman
- Krannert Cardiovascular Research Center, Dept. of Medicine, Indiana Univ. School of Medicine, Indianapolis, IN, USA; OhioHealth, Columbus, OH, USA
| | - Behzad Sharif
- Laboratory for Translational Imaging of Microcirculation, Indiana University School of Medicine, Indianapolis, IN, USA; Krannert Cardiovascular Research Center, Dept. of Medicine, Indiana Univ. School of Medicine, Indianapolis, IN, USA; OhioHealth, Columbus, OH, USA.
| |
Collapse
|
4
|
Yalcinkaya DM, Youssef K, Heydari B, Wei J, Merz NB, Judd R, Dharmakumar R, Simonetti OP, Weinsaft JW, Raman SV, Sharif B. Improved Robustness for Deep Learning-based Segmentation of Multi-Center Myocardial Perfusion MRI Datasets Using Data Adaptive Uncertainty-guided Space-time Analysis. ARXIV 2024:arXiv:2408.04805v1. [PMID: 39148930 PMCID: PMC11326424] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Subscribe] [Scholar Register] [Indexed: 08/17/2024]
Abstract
Background Fully automatic analysis of myocardial perfusion MRI datasets enables rapid and objective reporting of stress/rest studies in patients with suspected ischemic heart disease. Developing deep learning techniques that can analyze multi-center datasets despite limited training data and variations in software (pulse sequence) and hardware (scanner vendor) is an ongoing challenge. Methods Datasets from 3 medical centers acquired at 3T (n = 150 subjects; 21,150 first-pass images) were included: an internal dataset (inD; n = 95) and two external datasets (exDs; n = 55) used for evaluating the robustness of the trained deep neural network (DNN) models against differences in pulse sequence (exD-1) and scanner vendor (exD-2). A subset of inD (n = 85) was used for training/validation of a pool of DNNs for segmentation, all using the same spatiotemporal U-Net architecture and hyperparameters but with different parameter initializations. We employed a space-time sliding-patch analysis approach that automatically yields a pixel-wise "uncertainty map" as a byproduct of the segmentation process. In our approach, dubbed Data Adaptive Uncertainty-Guided Space-time (DAUGS) analysis, a given test case is segmented by all members of the DNN pool and the resulting uncertainty maps are leveraged to automatically select the "best" one among the pool of solutions. For comparison, we also trained a DNN using the established approach with the same settings (hyperparameters, data augmentation, etc.). Results The proposed DAUGS analysis approach performed similarly to the established approach on the internal dataset (Dice score for the testing subset of inD: 0.896 ± 0.050 vs. 0.890 ± 0.049; p = n.s.) whereas it significantly outperformed on the external datasets (Dice for exD-1: 0.885 ± 0.040 vs. 0.849 ± 0.065, p < 0.005; Dice for exD-2: 0.811 ± 0.070 vs. 0.728 ± 0.149, p < 0.005). Moreover, the number of image series with "failed" segmentation (defined as having myocardial contours that include bloodpool or are noncontiguous in ≥1 segment) was significantly lower for the proposed vs. the established approach (4.3% vs. 17.1%, p < 0.0005). Conclusions The proposed DAUGS analysis approach has the potential to improve the robustness of deep learning methods for segmentation of multi-center stress perfusion datasets with variations in the choice of pulse sequence, site location or scanner vendor.
Collapse
Affiliation(s)
- Dilek M. Yalcinkaya
- Laboratory for Translational Imaging of Microcirculation, Indiana University School of Medicine, Indianapolis, IN, USA
- Elmore Family School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA
| | - Khalid Youssef
- Laboratory for Translational Imaging of Microcirculation, Indiana University School of Medicine, Indianapolis, IN, USA
- Krannert Cardiovascular Research Center, Dept. of Medicine, Indiana Univ. School of Medicine, Indianapolis, IN, USA
| | - Bobak Heydari
- Stephenson Cardiac Imaging Centre, Department of Cardiac Sciences, University of Calgary, Alberta, Canada
| | - Janet Wei
- Barbra Streisand Women’s Heart Center, Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, CA, USA
| | - Noel Bairey Merz
- Barbra Streisand Women’s Heart Center, Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, CA, USA
| | - Robert Judd
- Division of Cardiology, Department of Medicine, Duke University, Durham, NC, USA
| | - Rohan Dharmakumar
- Krannert Cardiovascular Research Center, Dept. of Medicine, Indiana Univ. School of Medicine, Indianapolis, IN, USA
- Weldon School of Biomedical Engineering, Purdue University, West Lafayette, IN, USA
| | - Orlando P. Simonetti
- Department of Medicine, Davis Heart and Lung Research Institute, The Ohio State University, Columbus, OH, USA
| | - Jonathan W. Weinsaft
- Division of Cardiology at NY Presbyterian Hospital, Weill Cornell Medical Center, New York, NY, USA
| | - Subha V. Raman
- Krannert Cardiovascular Research Center, Dept. of Medicine, Indiana Univ. School of Medicine, Indianapolis, IN, USA
- OhioHealth, Columbus, OH, USA
| | - Behzad Sharif
- Laboratory for Translational Imaging of Microcirculation, Indiana University School of Medicine, Indianapolis, IN, USA
- Elmore Family School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA
- Krannert Cardiovascular Research Center, Dept. of Medicine, Indiana Univ. School of Medicine, Indianapolis, IN, USA
- Weldon School of Biomedical Engineering, Purdue University, West Lafayette, IN, USA
| |
Collapse
|
5
|
García-García S, Cepeda S, Arrese I, Sarabia R. A Fully Automated Pipeline Using Swin Transformers for Deep Learning-Based Blood Segmentation on Head Computed Tomography Scans After Aneurysmal Subarachnoid Hemorrhage. World Neurosurg 2024:S1878-8750(24)01357-3. [PMID: 39111661 DOI: 10.1016/j.wneu.2024.07.216] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/23/2024] [Accepted: 07/31/2024] [Indexed: 09/01/2024]
Abstract
BACKGROUND Accurate volumetric assessment of spontaneous aneurysmal subarachnoid hemorrhage (aSAH) is a labor-intensive task performed with current manual and semiautomatic methods that might be relevant for its clinical and prognostic implications. In the present research, we sought to develop and validate an artificial intelligence-driven, fully automated blood segmentation tool for subarachnoid hemorrhage (SAH) patients via noncontrast computed tomography (NCCT) scans employing a transformer-based Swin-UNETR architecture. METHODS We retrospectively analyzed NCCT scans from patients with confirmed aSAH utilizing the Swin-UNETR for segmentation. The performance of the proposed method was evaluated against manually segmented ground truth data using metrics such as Dice score, intersection over union, volumetric similarity index , symmetric average surface distance , sensitivity, and specificity. A validation cohort from an external institution was included to test the generalizability of the model. RESULTS The model demonstrated high accuracy with robust performance metrics across the internal and external validation cohorts. Notably, it achieved high Dice coefficient (0.873 ± 0.097), intersection over union (0.810 ± 0.092), volumetric similarity index (0.840 ± 0.131), sensitivity (0.821 ± 0.217), and specificity (0.996 ± 0.004) values and a low symmetric average surface distance (1.866 ± 2.910), suggesting proficiency in segmenting blood in SAH patients. The model's efficiency was reflected in its processing speed, indicating potential for real-time applications. CONCLUSIONS Our Swin UNETR-based model offers significant advances in the automated segmentation of blood in SAH patients on NCCT images. Despite the computational demands, the model operates effectively on standard hardware with a user-friendly interface, facilitating broader clinical adoption. Further validation across diverse datasets is warranted to confirm its clinical reliability.
Collapse
Affiliation(s)
- Sergio García-García
- Neurosurgery Department, Hospital Universitario Rio Hortega, Valladolid, Spain; Neurosurgery Department, Helsinki University Hospital, Helsinki, Finland.
| | - Santiago Cepeda
- Neurosurgery Department, Hospital Universitario Rio Hortega, Valladolid, Spain
| | - Ignacio Arrese
- Neurosurgery Department, Hospital Universitario Rio Hortega, Valladolid, Spain
| | - Rosario Sarabia
- Neurosurgery Department, Hospital Universitario Rio Hortega, Valladolid, Spain
| |
Collapse
|
6
|
Bijari S, Sayfollahi S, Mardokh-Rouhani S, Bijari S, Moradian S, Zahiri Z, Rezaeijo SM. Radiomics and Deep Features: Robust Classification of Brain Hemorrhages and Reproducibility Analysis Using a 3D Autoencoder Neural Network. Bioengineering (Basel) 2024; 11:643. [PMID: 39061725 PMCID: PMC11273742 DOI: 10.3390/bioengineering11070643] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/08/2024] [Revised: 06/17/2024] [Accepted: 06/19/2024] [Indexed: 07/28/2024] Open
Abstract
This study evaluates the reproducibility of machine learning models that integrate radiomics and deep features (features extracted from a 3D autoencoder neural network) to classify various brain hemorrhages effectively. Using a dataset of 720 patients, we extracted 215 radiomics features (RFs) and 15,680 deep features (DFs) from CT brain images. With rigorous screening based on Intraclass Correlation Coefficient thresholds (>0.75), we identified 135 RFs and 1054 DFs for analysis. Feature selection techniques such as Boruta, Recursive Feature Elimination (RFE), XGBoost, and ExtraTreesClassifier were utilized alongside 11 classifiers, including AdaBoost, CatBoost, Decision Trees, LightGBM, Logistic Regression, Naive Bayes, Neural Networks, Random Forest, Support Vector Machines (SVM), and k-Nearest Neighbors (k-NN). Evaluation metrics included Area Under the Curve (AUC), Accuracy (ACC), Sensitivity (SEN), and F1-score. The model evaluation involved hyperparameter optimization, a 70:30 train-test split, and bootstrapping, further validated with the Wilcoxon signed-rank test and q-values. Notably, DFs showed higher accuracy. In the case of RFs, the Boruta + SVM combination emerged as the optimal model for AUC, ACC, and SEN, while XGBoost + Random Forest excelled in F1-score. Specifically, RFs achieved AUC, ACC, SEN, and F1-scores of 0.89, 0.85, 0.82, and 0.80, respectively. Among DFs, the ExtraTreesClassifier + Naive Bayes combination demonstrated remarkable performance, attaining an AUC of 0.96, ACC of 0.93, SEN of 0.92, and an F1-score of 0.92. Distinguished models in the RF category included SVM with Boruta, Logistic Regression with XGBoost, SVM with ExtraTreesClassifier, CatBoost with XGBoost, and Random Forest with XGBoost, each yielding significant q-values of 42. In the DFs realm, ExtraTreesClassifier + Naive Bayes, ExtraTreesClassifier + Random Forest, and Boruta + k-NN exhibited robustness, with 43, 43, and 41 significant q-values, respectively. This investigation underscores the potential of synergizing DFs with machine learning models to serve as valuable screening tools, thereby enhancing the interpretation of head CT scans for patients with brain hemorrhages.
Collapse
Affiliation(s)
- Salar Bijari
- Department of Radiology, Faculty of Paramedical, Kurdistan University of Medical Sciences, Sanandaj P.O. Box 66177-13446, Iran;
| | - Sahar Sayfollahi
- Department of Neurosurgery, School of Medicine, Iran University of Medical Sciences, Tehran P.O. Box 14496-14535, Iran;
| | - Shiwa Mardokh-Rouhani
- Mechanical Engineering Group, Faculty of Engineering, University of Kurdistan, Sanandaj P.O. Box 66177-15175, Iran;
| | - Sahar Bijari
- Department of Aging and Health, School of Public Health, Shahid Sadoughi University of Medical Sciences, Yazd P.O. Box 89151-73160, Iran;
| | - Sadegh Moradian
- Department of Radiology, Tehran University of Medical Sciences, Tehran P.O. Box 14197-33151, Iran;
| | - Ziba Zahiri
- Department of Radiation Oncology, Golestan Hospital, Ahvaz Jundishapur University of Medical Sciences, Ahvaz P.O. Box 61357-15794, Iran;
| | - Seyed Masoud Rezaeijo
- Department of Medical Physics, Faculty of Medicine, Ahvaz Jundishapur University of Medical Sciences, Ahvaz P.O. Box 61357-15794, Iran
- Cancer Research Center, Ahvaz Jundishapur University of Medical Sciences, Ahvaz P.O. Box 61357-15794, Iran
| |
Collapse
|
7
|
Carvalho Macruz FBD, Dias ALMP, Andrade CS, Nucci MP, Rimkus CDM, Lucato LT, Rocha AJD, Kitamura FC. The new era of artificial intelligence in neuroradiology: current research and promising tools. ARQUIVOS DE NEURO-PSIQUIATRIA 2024; 82:1-12. [PMID: 38565188 PMCID: PMC10987255 DOI: 10.1055/s-0044-1779486] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 10/18/2023] [Accepted: 12/13/2023] [Indexed: 04/04/2024]
Abstract
Radiology has a number of characteristics that make it an especially suitable medical discipline for early artificial intelligence (AI) adoption. These include having a well-established digital workflow, standardized protocols for image storage, and numerous well-defined interpretive activities. The more than 200 commercial radiologic AI-based products recently approved by the Food and Drug Administration (FDA) to assist radiologists in a number of narrow image-analysis tasks such as image enhancement, workflow triage, and quantification, corroborate this observation. However, in order to leverage AI to boost efficacy and efficiency, and to overcome substantial obstacles to widespread successful clinical use of these products, radiologists should become familiarized with the emerging applications in their particular areas of expertise. In light of this, in this article we survey the existing literature on the application of AI-based techniques in neuroradiology, focusing on conditions such as vascular diseases, epilepsy, and demyelinating and neurodegenerative conditions. We also introduce some of the algorithms behind the applications, briefly discuss a few of the challenges of generalization in the use of AI models in neuroradiology, and skate over the most relevant commercially available solutions adopted in clinical practice. If well designed, AI algorithms have the potential to radically improve radiology, strengthening image analysis, enhancing the value of quantitative imaging techniques, and mitigating diagnostic errors.
Collapse
Affiliation(s)
- Fabíola Bezerra de Carvalho Macruz
- Universidade de São Paulo, Hospital das Clínicas, Departamento de Radiologia e Oncologia, Seção de Neurorradiologia, Faculdade de Medicina, São Paulo SP, Brazil.
- Rede D'Or São Luiz, Departamento de Radiologia e Diagnóstico por Imagem, São Paulo SP, Brazil.
- Universidade de São Paulo, Laboratório de Investigação Médica em Ressonância Magnética (LIM 44), São Paulo SP, Brazil.
- Academia Nacional de Medicina, Rio de Janeiro RJ, Brazil.
| | | | | | - Mariana Penteado Nucci
- Universidade de São Paulo, Laboratório de Investigação Médica em Ressonância Magnética (LIM 44), São Paulo SP, Brazil.
| | - Carolina de Medeiros Rimkus
- Universidade de São Paulo, Hospital das Clínicas, Departamento de Radiologia e Oncologia, Seção de Neurorradiologia, Faculdade de Medicina, São Paulo SP, Brazil.
- Rede D'Or São Luiz, Departamento de Radiologia e Diagnóstico por Imagem, São Paulo SP, Brazil.
- Universidade de São Paulo, Laboratório de Investigação Médica em Ressonância Magnética (LIM 44), São Paulo SP, Brazil.
| | - Leandro Tavares Lucato
- Universidade de São Paulo, Hospital das Clínicas, Departamento de Radiologia e Oncologia, Seção de Neurorradiologia, Faculdade de Medicina, São Paulo SP, Brazil.
- Diagnósticos da América SA, São Paulo SP, Brazil.
| | | | - Felipe Campos Kitamura
- Diagnósticos da América SA, São Paulo SP, Brazil.
- Universidade Federal de São Paulo, São Paulo SP, Brazil.
| |
Collapse
|
8
|
Hu P, Yan T, Xiao B, Shu H, Sheng Y, Wu Y, Shu L, Lv S, Ye M, Gong Y, Wu M, Zhu X. Deep learning-assisted detection and segmentation of intracranial hemorrhage in noncontrast computed tomography scans of acute stroke patients: a systematic review and meta-analysis. Int J Surg 2024; 110:3839-3847. [PMID: 38489547 PMCID: PMC11175741 DOI: 10.1097/js9.0000000000001266] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/19/2023] [Accepted: 02/21/2024] [Indexed: 03/17/2024]
Abstract
BACKGROUND Deep learning (DL)-assisted detection and segmentation of intracranial hemorrhage stroke in noncontrast computed tomography (NCCT) scans are well-established, but evidence on this topic is lacking. MATERIALS AND METHODS PubMed and Embase databases were searched from their inception to November 2023 to identify related studies. The primary outcomes included sensitivity, specificity, and the Dice Similarity Coefficient (DSC); while the secondary outcomes were positive predictive value (PPV), negative predictive value (NPV), precision, area under the receiver operating characteristic curve (AUROC), processing time, and volume of bleeding. Random-effect model and bivariate model were used to pooled independent effect size and diagnostic meta-analysis data, respectively. RESULTS A total of 36 original studies were included in this meta-analysis. Pooled results indicated that DL technologies have a comparable performance in intracranial hemorrhage detection and segmentation with high values of sensitivity (0.89, 95% CI: 0.88-0.90), specificity (0.91, 95% CI: 0.89-0.93), AUROC (0.94, 95% CI: 0.93-0.95), PPV (0.92, 95% CI: 0.91-0.93), NPV (0.94, 95% CI: 0.91-0.96), precision (0.83, 95% CI: 0.77-0.90), DSC (0.84, 95% CI: 0.82-0.87). There is no significant difference between manual labeling and DL technologies in hemorrhage quantification (MD 0.08, 95% CI: -5.45-5.60, P =0.98), but the latter takes less process time than manual labeling (WMD 2.26, 95% CI: 1.96-2.56, P =0.001). CONCLUSION This systematic review has identified a range of DL algorithms that the performance was comparable to experienced clinicians in hemorrhage lesions identification, segmentation, and quantification but with greater efficiency and reduced cost. It is highly emphasized that multicenter randomized controlled clinical trials will be needed to validate the performance of these tools in the future, paving the way for fast and efficient decision-making during clinical procedure in patients with acute hemorrhagic stroke.
Collapse
Affiliation(s)
- Ping Hu
- Department of Neurosurgery, The Second Affiliated Hospital, Jiangxi Medical College, Nanchang University
- Jiangxi Key Laboratory of Neurological Tumors and Cerebrovascular Diseases
- Jiangxi Health Commission Key Laboratory of Neurological Medicine
- Institute of Neuroscience, Nanchang University, Nanchang, Jiangxi, People’s Republic of China
| | - Tengfeng Yan
- Department of Neurosurgery, The Second Affiliated Hospital, Jiangxi Medical College, Nanchang University
- Jiangxi Key Laboratory of Neurological Tumors and Cerebrovascular Diseases
- Jiangxi Health Commission Key Laboratory of Neurological Medicine
- Institute of Neuroscience, Nanchang University, Nanchang, Jiangxi, People’s Republic of China
| | - Bing Xiao
- Department of Neurosurgery, The Second Affiliated Hospital, Jiangxi Medical College, Nanchang University
| | - Hongxin Shu
- Department of Neurosurgery, The Second Affiliated Hospital, Jiangxi Medical College, Nanchang University
- Jiangxi Key Laboratory of Neurological Tumors and Cerebrovascular Diseases
- Jiangxi Health Commission Key Laboratory of Neurological Medicine
- Institute of Neuroscience, Nanchang University, Nanchang, Jiangxi, People’s Republic of China
| | - Yilei Sheng
- Department of Neurosurgery, The Second Affiliated Hospital, Jiangxi Medical College, Nanchang University
- Jiangxi Key Laboratory of Neurological Tumors and Cerebrovascular Diseases
- Jiangxi Health Commission Key Laboratory of Neurological Medicine
- Institute of Neuroscience, Nanchang University, Nanchang, Jiangxi, People’s Republic of China
| | - Yanze Wu
- Department of Neurosurgery, The Second Affiliated Hospital, Jiangxi Medical College, Nanchang University
- Jiangxi Key Laboratory of Neurological Tumors and Cerebrovascular Diseases
- Jiangxi Health Commission Key Laboratory of Neurological Medicine
- Institute of Neuroscience, Nanchang University, Nanchang, Jiangxi, People’s Republic of China
| | - Lei Shu
- Department of Neurosurgery, The Second Affiliated Hospital, Jiangxi Medical College, Nanchang University
- Jiangxi Key Laboratory of Neurological Tumors and Cerebrovascular Diseases
- Jiangxi Health Commission Key Laboratory of Neurological Medicine
- Institute of Neuroscience, Nanchang University, Nanchang, Jiangxi, People’s Republic of China
| | - Shigang Lv
- Department of Neurosurgery, The Second Affiliated Hospital, Jiangxi Medical College, Nanchang University
| | - Minhua Ye
- Department of Neurosurgery, The Second Affiliated Hospital, Jiangxi Medical College, Nanchang University
| | - Yanyan Gong
- Department of Neurosurgery, The Second Affiliated Hospital, Jiangxi Medical College, Nanchang University
| | - Miaojing Wu
- Department of Neurosurgery, The Second Affiliated Hospital, Jiangxi Medical College, Nanchang University
| | - Xingen Zhu
- Department of Neurosurgery, The Second Affiliated Hospital, Jiangxi Medical College, Nanchang University
- Jiangxi Key Laboratory of Neurological Tumors and Cerebrovascular Diseases
- Jiangxi Health Commission Key Laboratory of Neurological Medicine
- Institute of Neuroscience, Nanchang University, Nanchang, Jiangxi, People’s Republic of China
| |
Collapse
|
9
|
Wu D, Smith D, VanBerlo B, Roshankar A, Lee H, Li B, Ali F, Rahman M, Basmaji J, Tschirhart J, Ford A, VanBerlo B, Durvasula A, Vannelli C, Dave C, Deglint J, Ho J, Chaudhary R, Clausdorff H, Prager R, Millington S, Shah S, Buchanan B, Arntfield R. Improving the Generalizability and Performance of an Ultrasound Deep Learning Model Using Limited Multicenter Data for Lung Sliding Artifact Identification. Diagnostics (Basel) 2024; 14:1081. [PMID: 38893608 PMCID: PMC11172006 DOI: 10.3390/diagnostics14111081] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/06/2024] [Revised: 05/18/2024] [Accepted: 05/20/2024] [Indexed: 06/21/2024] Open
Abstract
Deep learning (DL) models for medical image classification frequently struggle to generalize to data from outside institutions. Additional clinical data are also rarely collected to comprehensively assess and understand model performance amongst subgroups. Following the development of a single-center model to identify the lung sliding artifact on lung ultrasound (LUS), we pursued a validation strategy using external LUS data. As annotated LUS data are relatively scarce-compared to other medical imaging data-we adopted a novel technique to optimize the use of limited external data to improve model generalizability. Externally acquired LUS data from three tertiary care centers, totaling 641 clips from 238 patients, were used to assess the baseline generalizability of our lung sliding model. We then employed our novel Threshold-Aware Accumulative Fine-Tuning (TAAFT) method to fine-tune the baseline model and determine the minimum amount of data required to achieve predefined performance goals. A subgroup analysis was also performed and Grad-CAM++ explanations were examined. The final model was fine-tuned on one-third of the external dataset to achieve 0.917 sensitivity, 0.817 specificity, and 0.920 area under the receiver operator characteristic curve (AUC) on the external validation dataset, exceeding our predefined performance goals. Subgroup analyses identified LUS characteristics that most greatly challenged the model's performance. Grad-CAM++ saliency maps highlighted clinically relevant regions on M-mode images. We report a multicenter study that exploits limited available external data to improve the generalizability and performance of our lung sliding model while identifying poorly performing subgroups to inform future iterative improvements. This approach may contribute to efficiencies for DL researchers working with smaller quantities of external validation data.
Collapse
Affiliation(s)
- Derek Wu
- Department of Medicine, Western University, London, ON N6A 5C1, Canada;
| | - Delaney Smith
- Faculty of Mathematics, University of Waterloo, Waterloo, ON N2L 3G1, Canada; (D.S.); (H.L.)
| | - Blake VanBerlo
- Faculty of Mathematics, University of Waterloo, Waterloo, ON N2L 3G1, Canada; (D.S.); (H.L.)
| | - Amir Roshankar
- Faculty of Engineering, University of Waterloo, Waterloo, ON N2L 3G1, Canada; (A.R.); (B.L.); (F.A.); (M.R.)
| | - Hoseok Lee
- Faculty of Mathematics, University of Waterloo, Waterloo, ON N2L 3G1, Canada; (D.S.); (H.L.)
| | - Brian Li
- Faculty of Engineering, University of Waterloo, Waterloo, ON N2L 3G1, Canada; (A.R.); (B.L.); (F.A.); (M.R.)
| | - Faraz Ali
- Faculty of Engineering, University of Waterloo, Waterloo, ON N2L 3G1, Canada; (A.R.); (B.L.); (F.A.); (M.R.)
| | - Marwan Rahman
- Faculty of Engineering, University of Waterloo, Waterloo, ON N2L 3G1, Canada; (A.R.); (B.L.); (F.A.); (M.R.)
| | - John Basmaji
- Division of Critical Care Medicine, Western University, London, ON N6A 5C1, Canada; (J.B.); (C.D.); (R.P.); (R.A.)
| | - Jared Tschirhart
- Schulich School of Medicine and Dentistry, Western University, London, ON N6A 5C1, Canada; (J.T.); (A.D.); (C.V.)
| | - Alex Ford
- Independent Researcher, London, ON N6A 1L8, Canada;
| | - Bennett VanBerlo
- Faculty of Engineering, Western University, London, ON N6A 5C1, Canada;
| | - Ashritha Durvasula
- Schulich School of Medicine and Dentistry, Western University, London, ON N6A 5C1, Canada; (J.T.); (A.D.); (C.V.)
| | - Claire Vannelli
- Schulich School of Medicine and Dentistry, Western University, London, ON N6A 5C1, Canada; (J.T.); (A.D.); (C.V.)
| | - Chintan Dave
- Division of Critical Care Medicine, Western University, London, ON N6A 5C1, Canada; (J.B.); (C.D.); (R.P.); (R.A.)
| | - Jason Deglint
- Faculty of Engineering, University of Waterloo, Waterloo, ON N2L 3G1, Canada; (A.R.); (B.L.); (F.A.); (M.R.)
| | - Jordan Ho
- Department of Family Medicine, Western University, London, ON N6A 5C1, Canada;
| | - Rushil Chaudhary
- Department of Medicine, Western University, London, ON N6A 5C1, Canada;
| | - Hans Clausdorff
- Departamento de Medicina de Urgencia, Pontificia Universidad Católica de Chile, Santiago 8331150, Chile;
| | - Ross Prager
- Division of Critical Care Medicine, Western University, London, ON N6A 5C1, Canada; (J.B.); (C.D.); (R.P.); (R.A.)
| | - Scott Millington
- Department of Critical Care Medicine, University of Ottawa, Ottawa, ON K1N 6N5, Canada;
| | - Samveg Shah
- Department of Medicine, University of Alberta, Edmonton, AB T6G 2R3, Canada;
| | - Brian Buchanan
- Department of Critical Care, University of Alberta, Edmonton, AB T6G 2R3, Canada;
| | - Robert Arntfield
- Division of Critical Care Medicine, Western University, London, ON N6A 5C1, Canada; (J.B.); (C.D.); (R.P.); (R.A.)
| |
Collapse
|
10
|
Lin E, Yuh EL. Semi-supervised Learning for Generalizable Intracranial Hemorrhage Detection and Segmentation. Radiol Artif Intell 2024; 6:e230077. [PMID: 38446043 PMCID: PMC11140498 DOI: 10.1148/ryai.230077] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/17/2023] [Revised: 02/01/2024] [Accepted: 02/16/2024] [Indexed: 03/07/2024]
Abstract
Purpose To develop and evaluate a semi-supervised learning model for intracranial hemorrhage detection and segmentation on an out-of-distribution head CT evaluation set. Materials and Methods This retrospective study used semi-supervised learning to bootstrap performance. An initial "teacher" deep learning model was trained on 457 pixel-labeled head CT scans collected from one U.S. institution from 2010 to 2017 and used to generate pseudo labels on a separate unlabeled corpus of 25 000 examinations from the Radiological Society of North America and American Society of Neuroradiology. A second "student" model was trained on this combined pixel- and pseudo-labeled dataset. Hyperparameter tuning was performed on a validation set of 93 scans. Testing for both classification (n = 481 examinations) and segmentation (n = 23 examinations, or 529 images) was performed on CQ500, a dataset of 481 scans performed in India, to evaluate out-of-distribution generalizability. The semi-supervised model was compared with a baseline model trained on only labeled data using area under the receiver operating characteristic curve, Dice similarity coefficient, and average precision metrics. Results The semi-supervised model achieved a statistically significant higher examination area under the receiver operating characteristic curve on CQ500 compared with the baseline (0.939 [95% CI: 0.938, 0.940] vs 0.907 [95% CI: 0.906, 0.908]; P = .009). It also achieved a higher Dice similarity coefficient (0.829 [95% CI: 0.825, 0.833] vs 0.809 [95% CI: 0.803, 0.812]; P = .012) and pixel average precision (0.848 [95% CI: 0.843, 0.853]) vs 0.828 [95% CI: 0.817, 0.828]) compared with the baseline. Conclusion The addition of unlabeled data in a semi-supervised learning framework demonstrates stronger generalizability potential for intracranial hemorrhage detection and segmentation compared with a supervised baseline. Keywords: Semi-supervised Learning, Traumatic Brain Injury, CT, Machine Learning Supplemental material is available for this article. Published under a CC BY 4.0 license. See also the commentary by Swimburne in this issue.
Collapse
Affiliation(s)
- Emily Lin
- From the Department of Radiology & Biomedical Imaging, University of California San Francisco, 185 Berry St, San Francisco CA 94107
| | - Esther L Yuh
- From the Department of Radiology & Biomedical Imaging, University of California San Francisco, 185 Berry St, San Francisco CA 94107
| |
Collapse
|
11
|
Vande Vyvere T, Pisică D, Wilms G, Claes L, Van Dyck P, Snoeckx A, van den Hauwe L, Pullens P, Verheyden J, Wintermark M, Dekeyzer S, Mac Donald CL, Maas AIR, Parizel PM. Imaging Findings in Acute Traumatic Brain Injury: a National Institute of Neurological Disorders and Stroke Common Data Element-Based Pictorial Review and Analysis of Over 4000 Admission Brain Computed Tomography Scans from the Collaborative European NeuroTrauma Effectiveness Research in Traumatic Brain Injury (CENTER-TBI) Study. J Neurotrauma 2024. [PMID: 38482818 DOI: 10.1089/neu.2023.0553] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 04/20/2024] Open
Abstract
In 2010, the National Institute of Neurological Disorders and Stroke (NINDS) created a set of common data elements (CDEs) to help standardize the assessment and reporting of imaging findings in traumatic brain injury (TBI). However, as opposed to other standardized radiology reporting systems, a visual overview and data to support the proposed standardized lexicon are lacking. We used over 4000 admission computed tomography (CT) scans of patients with TBI from the Collaborative European NeuroTrauma Effectiveness Research in Traumatic Brain Injury (CENTER-TBI) study to develop an extensive pictorial overview of the NINDS TBI CDEs, with visual examples and background information on individual pathoanatomical lesion types, up to the level of supplemental and emerging information (e.g., location and estimated volumes). We documented the frequency of lesion occurrence, aiming to quantify the relative importance of different CDEs for characterizing TBI, and performed a critical appraisal of our experience with the intent to inform updating of the CDEs. In addition, we investigated the co-occurrence and clustering of lesion types and the distribution of six CT classification systems. The median age of the 4087 patients in our dataset was 50 years (interquartile range, 29-66; range, 0-96), including 238 patients under 18 years old (5.8%). Traumatic subarachnoid hemorrhage (45.3%), skull fractures (37.4%), contusions (31.3%), and acute subdural hematoma (28.9%) were the most frequently occurring CT findings in acute TBI. The ranking of these lesions was the same in patients with mild TBI (baseline Glasgow Coma Scale [GCS] score 13-15) compared with those with moderate-severe TBI (baseline GCS score 3-12), but the frequency of occurrence was up to three times higher in moderate-severe TBI. In most TBI patients with CT abnormalities, there was co-occurrence and clustering of different lesion types, with significant differences between mild and moderate-severe TBI patients. More specifically, lesion patterns were more complex in moderate-severe TBI patients, with more co-existing lesions and more frequent signs of mass effect. These patients also had higher and more heterogeneous CT score distributions, associated with worse predicted outcomes. The critical appraisal of the NINDS CDEs was highly positive, but revealed that full assessment can be time consuming, that some CDEs had very low frequencies, and identified a few redundancies and ambiguity in some definitions. Whilst primarily developed for research, implementation of CDE templates for use in clinical practice is advocated, but this will require development of an abbreviated version. In conclusion, with this study, we provide an educational resource for clinicians and researchers to help assess, characterize, and report the vast and complex spectrum of imaging findings in patients with TBI. Our data provides a comprehensive overview of the contemporary landscape of TBI imaging pathology in Europe, and the findings can serve as empirical evidence for updating the current NINDS radiologic CDEs to version 3.0.
Collapse
Affiliation(s)
- Thijs Vande Vyvere
- Department of Radiology, Antwerp University Hospital, Antwerp, Belgium
- Department of Molecular Imaging and Radiology (MIRA), Faculty of Medicine and Health Science, University of Antwerp, Antwerp, Belgium
| | - Dana Pisică
- Department of Neurosurgery, Erasmus MC - University Medical Center Rotterdam, Rotterdam, the Netherlands
- Department of Public Health, Erasmus MC - University Medical Center Rotterdam, Rotterdam, the Netherlands
| | - Guido Wilms
- Department of Radiology, University Hospitals Leuven, Leuven, Belgium
| | - Lene Claes
- icometrix, Research and Development, Leuven, Belgium
| | - Pieter Van Dyck
- Department of Radiology, Antwerp University Hospital, Antwerp, Belgium
- Department of Molecular Imaging and Radiology (MIRA), Faculty of Medicine and Health Science, University of Antwerp, Antwerp, Belgium
| | - Annemiek Snoeckx
- Department of Radiology, Antwerp University Hospital, Antwerp, Belgium
- Department of Molecular Imaging and Radiology (MIRA), Faculty of Medicine and Health Science, University of Antwerp, Antwerp, Belgium
| | - Luc van den Hauwe
- Department of Radiology, Antwerp University Hospital, Antwerp, Belgium
| | - Pim Pullens
- Department of Imaging, University Hospital Ghent; IBITech/MEDISIP, Engineering and Architecture, Ghent University; Ghent Institute for Functional and Metabolic Imaging, Ghent University, Belgium
| | - Jan Verheyden
- icometrix, Research and Development, Leuven, Belgium
| | - Max Wintermark
- Department of Neuroradiology, University of Texas MD Anderson Center, Houston, Texas, USA
| | - Sven Dekeyzer
- Department of Radiology, Antwerp University Hospital, Antwerp, Belgium
- Department of Radiology, University Hospital Ghent, Belgium
| | - Christine L Mac Donald
- Department of Neurological Surgery, School of Medicine, Harborview Medical Center, Seattle, Washington, USA
- Department of Neurological Surgery, School of Medicine, University of Washington, Seattle, Washington, USA
| | - Andrew I R Maas
- Department of Neurosurgery, Antwerp University Hospital, Antwerp, Belgium
- Department of Translational Neuroscience, Faculty of Medicine and Health Science, University of Antwerp, Antwerp, Belgium
| | - Paul M Parizel
- Department of Radiology, Royal Perth Hospital (RPH) and University of Western Australia (UWA), Perth, Australia; Western Australia National Imaging Facility (WA NIF) node, Australia
| |
Collapse
|
12
|
Qu M, Xu Y, Lu L. Global research evolution and frontier analysis of artificial intelligence in brain injury: A bibliometric analysis. Brain Res Bull 2024; 209:110920. [PMID: 38453035 DOI: 10.1016/j.brainresbull.2024.110920] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/02/2023] [Revised: 12/18/2023] [Accepted: 03/03/2024] [Indexed: 03/09/2024]
Abstract
Research on artificial intelligence for brain injury is currently a prominent area of scientific research. A significant amount of related literature has been accumulated in this field. This study aims to identify hotspots and clarify research resources by conducting literature metrology visualization analysis, providing valuable ideas and references for related fields. The research object of this paper consists of 3000 articles cited in the core database of Web of Science from 1998 to 2023. These articles are visualized and analyzed using VOSviewer and CiteSpace. The bibliometric analysis reveals a continuous increase in the number of articles published on this topic, particularly since 2016, indicating significant growth. The United States stands out as the leading country in artificial intelligence for brain injury, followed by China, which tends to catch up. The core research institutions are primarily universities in developed countries, but there is a lack of cooperation and communication between research groups. With the development of computer technology, the research in this field has shown strong wave characteristics, experiencing the early stage of applied research based on expert systems, the middle stage of prediction research based on machine learning, and the current phase of diversified research focused on deep learning. Artificial intelligence has innovative development prospects in brain injury, providing a new orientation for the treatment and auxiliary diagnosis in this field.
Collapse
Affiliation(s)
- Mengqi Qu
- Institute of Disaster and Emergency Medicine, Tianjin University, Tianjin 300072, China.
| | - Yang Xu
- Institute of Disaster and Emergency Medicine, Tianjin University, Tianjin 300072, China.
| | - Lu Lu
- Institute of Disaster and Emergency Medicine, Tianjin University, Tianjin 300072, China.
| |
Collapse
|
13
|
Lee H, Lee J, Jang J, Hwang I, Choi KS, Park JH, Chung JW, Choi SH. Predicting hematoma expansion in acute spontaneous intracerebral hemorrhage: integrating clinical factors with a multitask deep learning model for non-contrast head CT. Neuroradiology 2024; 66:577-587. [PMID: 38337016 PMCID: PMC10937749 DOI: 10.1007/s00234-024-03298-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/06/2023] [Accepted: 01/25/2024] [Indexed: 02/12/2024]
Abstract
PURPOSE To predict hematoma growth in intracerebral hemorrhage patients by combining clinical findings with non-contrast CT imaging features analyzed through deep learning. METHODS Three models were developed to predict hematoma expansion (HE) in 572 patients. We utilized multi-task learning for both hematoma segmentation and prediction of expansion: the Image-to-HE model processed hematoma slices, extracting features and computing a normalized DL score for HE prediction. The Clinical-to-HE model utilized multivariate logistic regression on clinical variables. The Integrated-to-HE model combined image-derived and clinical data. Significant clinical variables were selected using forward selection in logistic regression. The two models incorporating clinical variables were statistically validated. RESULTS For hematoma detection, the diagnostic performance of the developed multi-task model was excellent (AUC, 0.99). For expansion prediction, three models were evaluated for predicting HE. The Image-to-HE model achieved an accuracy of 67.3%, sensitivity of 81.0%, specificity of 64.0%, and an AUC of 0.76. The Clinical-to-HE model registered an accuracy of 74.8%, sensitivity of 81.0%, specificity of 73.3%, and an AUC of 0.81. The Integrated-to-HE model, merging both image and clinical data, excelled with an accuracy of 81.3%, sensitivity of 76.2%, specificity of 82.6%, and an AUC of 0.83. The Integrated-to-HE model, aligning closest to the diagonal line and indicating the highest level of calibration, showcases superior performance in predicting HE outcomes among the three models. CONCLUSION The integration of clinical findings with non-contrast CT imaging features analyzed through deep learning showed the potential for improving the prediction of HE in acute spontaneous intracerebral hemorrhage patients.
Collapse
Affiliation(s)
- Hyochul Lee
- Interdisciplinary Program in Cancer Biology, Seoul National University College of Medicine, Seoul, 03080, Republic of Korea
- Department of Radiology, Seoul National University Hospital, 101 Daehak-Ro, Jongno-Gu, Seoul, 03080, Republic of Korea
| | - Junhyeok Lee
- Interdisciplinary Program in Cancer Biology, Seoul National University College of Medicine, Seoul, 03080, Republic of Korea
- Department of Radiology, Seoul National University Hospital, 101 Daehak-Ro, Jongno-Gu, Seoul, 03080, Republic of Korea
| | - Joon Jang
- Department of Biomedical Sciences, Seoul National University, Seoul, 03080, Korea
| | - Inpyeong Hwang
- Department of Radiology, Seoul National University Hospital, 101 Daehak-Ro, Jongno-Gu, Seoul, 03080, Republic of Korea.
- Department of Radiology, Seoul National University College of Medicine, 101 Daehak-Ro, Jongno-Gu, Seoul, 03080, Republic of Korea.
- Artificial Intelligence Collaborative Network, Department of Radiology, Seoul National University Hospital, Seoul, 03080, Republic of Korea.
| | - Kyu Sung Choi
- Department of Radiology, Seoul National University Hospital, 101 Daehak-Ro, Jongno-Gu, Seoul, 03080, Republic of Korea.
- Artificial Intelligence Collaborative Network, Department of Radiology, Seoul National University Hospital, Seoul, 03080, Republic of Korea.
| | - Jung Hyun Park
- Department of Radiology, Seoul Metropolitan Government Seoul National University Boramae Medical Center, Seoul, 07061, South Korea
| | - Jin Wook Chung
- Department of Radiology, Seoul National University Hospital, 101 Daehak-Ro, Jongno-Gu, Seoul, 03080, Republic of Korea
- Department of Radiology, Seoul National University College of Medicine, 101 Daehak-Ro, Jongno-Gu, Seoul, 03080, Republic of Korea
- Artificial Intelligence Collaborative Network, Department of Radiology, Seoul National University Hospital, Seoul, 03080, Republic of Korea
| | - Seung Hong Choi
- Interdisciplinary Program in Cancer Biology, Seoul National University College of Medicine, Seoul, 03080, Republic of Korea
- Department of Radiology, Seoul National University Hospital, 101 Daehak-Ro, Jongno-Gu, Seoul, 03080, Republic of Korea
- Department of Radiology, Seoul National University College of Medicine, 101 Daehak-Ro, Jongno-Gu, Seoul, 03080, Republic of Korea
- Artificial Intelligence Collaborative Network, Department of Radiology, Seoul National University Hospital, Seoul, 03080, Republic of Korea
- Center for Nanoparticle Research, Institute for Basic Science (IBS), Seoul, 08826, Republic of Korea
| |
Collapse
|
14
|
Hoang QT, Pham XH, Trinh XT, Le AV, Bui MV, Bui TT. An Efficient CNN-Based Method for Intracranial Hemorrhage Segmentation from Computerized Tomography Imaging. J Imaging 2024; 10:77. [PMID: 38667975 PMCID: PMC11051045 DOI: 10.3390/jimaging10040077] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/22/2024] [Revised: 03/21/2024] [Accepted: 03/22/2024] [Indexed: 04/28/2024] Open
Abstract
Intracranial hemorrhage (ICH) resulting from traumatic brain injury is a serious issue, often leading to death or long-term disability if not promptly diagnosed. Currently, doctors primarily use Computerized Tomography (CT) scans to detect and precisely locate a hemorrhage, typically interpreted by radiologists. However, this diagnostic process heavily relies on the expertise of medical professionals. To address potential errors, computer-aided diagnosis systems have been developed. In this study, we propose a new method that enhances the localization and segmentation of ICH lesions in CT scans by using multiple images created through different data augmentation techniques. We integrate residual connections into a U-Net-based segmentation network to improve the training efficiency. Our experiments, based on 82 CT scans from traumatic brain injury patients, validate the effectiveness of our approach, achieving an IOU score of 0.807 ± 0.03 for ICH segmentation using 10-fold cross-validation.
Collapse
Affiliation(s)
- Quoc Tuan Hoang
- Faculty of Mechanical Engineering, Hung Yen University of Technology and Education, 39Rd., Hung Yen 160000, Vietnam; (Q.T.H.); (X.T.T.)
| | - Xuan Hien Pham
- Faculty of Mechanical Engineering, University of Transport and Communications, Hanoi 100000, Vietnam;
| | - Xuan Thang Trinh
- Faculty of Mechanical Engineering, Hung Yen University of Technology and Education, 39Rd., Hung Yen 160000, Vietnam; (Q.T.H.); (X.T.T.)
| | - Anh Vu Le
- Communication and Signal Processing Research Group, Faculty of Electrical and Electronics Engineering, Ton Duc Thang University, Ho Chi Minh City 700000, Vietnam
| | - Minh V. Bui
- Faculty of Engineering and Technology, Nguyen Tat Thanh University, 300A, Nguyen Tat Thanh, Ward 13, District 4, Ho Chi Minh City 700000, Vietnam;
| | - Trung Thanh Bui
- Faculty of Mechanical Engineering, Hung Yen University of Technology and Education, 39Rd., Hung Yen 160000, Vietnam; (Q.T.H.); (X.T.T.)
| |
Collapse
|
15
|
Westwood M, Ramaekers B, Grimm S, Armstrong N, Wijnen B, Ahmadu C, de Kock S, Noake C, Joore M. Software with artificial intelligence-derived algorithms for analysing CT brain scans in people with a suspected acute stroke: a systematic review and cost-effectiveness analysis. Health Technol Assess 2024; 28:1-204. [PMID: 38512017 PMCID: PMC11017149 DOI: 10.3310/rdpa1487] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 03/22/2024] Open
Abstract
Background Artificial intelligence-derived software technologies have been developed that are intended to facilitate the review of computed tomography brain scans in patients with suspected stroke. Objectives To evaluate the clinical and cost-effectiveness of using artificial intelligence-derived software to support review of computed tomography brain scans in acute stroke in the National Health Service setting. Methods Twenty-five databases were searched to July 2021. The review process included measures to minimise error and bias. Results were summarised by research question, artificial intelligence-derived software technology and study type. The health economic analysis focused on the addition of artificial intelligence-derived software-assisted review of computed tomography angiography brain scans for guiding mechanical thrombectomy treatment decisions for people with an ischaemic stroke. The de novo model (developed in R Shiny, R Foundation for Statistical Computing, Vienna, Austria) consisted of a decision tree (short-term) and a state transition model (long-term) to calculate the mean expected costs and quality-adjusted life-years for people with ischaemic stroke and suspected large-vessel occlusion comparing artificial intelligence-derived software-assisted review to usual care. Results A total of 22 studies (30 publications) were included in the review; 18/22 studies concerned artificial intelligence-derived software for the interpretation of computed tomography angiography to detect large-vessel occlusion. No study evaluated an artificial intelligence-derived software technology used as specified in the inclusion criteria for this assessment. For artificial intelligence-derived software technology alone, sensitivity and specificity estimates for proximal anterior circulation large-vessel occlusion were 95.4% (95% confidence interval 92.7% to 97.1%) and 79.4% (95% confidence interval 75.8% to 82.6%) for Rapid (iSchemaView, Menlo Park, CA, USA) computed tomography angiography, 91.2% (95% confidence interval 77.0% to 97.0%) and 85.0 (95% confidence interval 64.0% to 94.8%) for Viz LVO (Viz.ai, Inc., San Fransisco, VA, USA) large-vessel occlusion, 83.8% (95% confidence interval 77.3% to 88.7%) and 95.7% (95% confidence interval 91.0% to 98.0%) for Brainomix (Brainomix Ltd, Oxford, UK) e-computed tomography angiography and 98.1% (95% confidence interval 94.5% to 99.3%) and 98.2% (95% confidence interval 95.5% to 99.3%) for Avicenna CINA (Avicenna AI, La Ciotat, France) large-vessel occlusion, based on one study each. These studies were not considered appropriate to inform cost-effectiveness modelling but formed the basis by which the accuracy of artificial intelligence plus human reader could be elicited by expert opinion. Probabilistic analyses based on the expert elicitation to inform the sensitivity of the diagnostic pathway indicated that the addition of artificial intelligence to detect large-vessel occlusion is potentially more effective (quality-adjusted life-year gain of 0.003), more costly (increased costs of £8.61) and cost-effective for willingness-to-pay thresholds of £3380 per quality-adjusted life-year and higher. Limitations and conclusions The available evidence is not suitable to determine the clinical effectiveness of using artificial intelligence-derived software to support the review of computed tomography brain scans in acute stroke. The economic analyses did not provide evidence to prefer the artificial intelligence-derived software strategy over current clinical practice. However, results indicated that if the addition of artificial intelligence-derived software-assisted review for guiding mechanical thrombectomy treatment decisions increased the sensitivity of the diagnostic pathway (i.e. reduced the proportion of undetected large-vessel occlusions), this may be considered cost-effective. Future work Large, preferably multicentre, studies are needed (for all artificial intelligence-derived software technologies) that evaluate these technologies as they would be implemented in clinical practice. Study registration This study is registered as PROSPERO CRD42021269609. Funding This award was funded by the National Institute for Health and Care Research (NIHR) Evidence Synthesis programme (NIHR award ref: NIHR133836) and is published in full in Health Technology Assessment; Vol. 28, No. 11. See the NIHR Funding and Awards website for further award information.
Collapse
Affiliation(s)
| | - Bram Ramaekers
- Department of Clinical Epidemiology and Medical Technology Assessment, Maastricht University Medical Centre (MUMC), Maastricht, Netherlands
| | | | | | - Ben Wijnen
- Kleijnen Systematic Reviews (KSR) Ltd, York, UK
| | | | | | - Caro Noake
- Kleijnen Systematic Reviews (KSR) Ltd, York, UK
| | - Manuela Joore
- Department of Clinical Epidemiology and Medical Technology Assessment, Maastricht University Medical Centre (MUMC), Maastricht, Netherlands
| |
Collapse
|
16
|
Kazimierczak N, Kazimierczak W, Serafin Z, Nowicki P, Nożewski J, Janiszewska-Olszowska J. AI in Orthodontics: Revolutionizing Diagnostics and Treatment Planning-A Comprehensive Review. J Clin Med 2024; 13:344. [PMID: 38256478 PMCID: PMC10816993 DOI: 10.3390/jcm13020344] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/19/2023] [Revised: 12/29/2023] [Accepted: 01/05/2024] [Indexed: 01/24/2024] Open
Abstract
The advent of artificial intelligence (AI) in medicine has transformed various medical specialties, including orthodontics. AI has shown promising results in enhancing the accuracy of diagnoses, treatment planning, and predicting treatment outcomes. Its usage in orthodontic practices worldwide has increased with the availability of various AI applications and tools. This review explores the principles of AI, its applications in orthodontics, and its implementation in clinical practice. A comprehensive literature review was conducted, focusing on AI applications in dental diagnostics, cephalometric evaluation, skeletal age determination, temporomandibular joint (TMJ) evaluation, decision making, and patient telemonitoring. Due to study heterogeneity, no meta-analysis was possible. AI has demonstrated high efficacy in all these areas, but variations in performance and the need for manual supervision suggest caution in clinical settings. The complexity and unpredictability of AI algorithms call for cautious implementation and regular manual validation. Continuous AI learning, proper governance, and addressing privacy and ethical concerns are crucial for successful integration into orthodontic practice.
Collapse
Affiliation(s)
- Natalia Kazimierczak
- Kazimierczak Private Medical Practice, Dworcowa 13/u6a, 85-009 Bydgoszcz, Poland
| | - Wojciech Kazimierczak
- Kazimierczak Private Medical Practice, Dworcowa 13/u6a, 85-009 Bydgoszcz, Poland
- Department of Radiology and Diagnostic Imaging, Collegium Medicum, Nicolaus Copernicus University in Torun, Jagiellońska 13-15, 85-067 Bydgoszcz, Poland
| | - Zbigniew Serafin
- Department of Radiology and Diagnostic Imaging, Collegium Medicum, Nicolaus Copernicus University in Torun, Jagiellońska 13-15, 85-067 Bydgoszcz, Poland
| | - Paweł Nowicki
- Kazimierczak Private Medical Practice, Dworcowa 13/u6a, 85-009 Bydgoszcz, Poland
| | - Jakub Nożewski
- Department of Emeregncy Medicine, University Hospital No 2 in Bydgoszcz, Ujejskiego 75, 85-168 Bydgoszcz, Poland
| | | |
Collapse
|
17
|
Kang DW, Park GH, Ryu WS, Schellingerhout D, Kim M, Kim YS, Park CY, Lee KJ, Han MK, Jeong HG, Kim DE. Strengthening deep-learning models for intracranial hemorrhage detection: strongly annotated computed tomography images and model ensembles. Front Neurol 2023; 14:1321964. [PMID: 38221995 PMCID: PMC10784380 DOI: 10.3389/fneur.2023.1321964] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/15/2023] [Accepted: 12/11/2023] [Indexed: 01/16/2024] Open
Abstract
Background and purpose Multiple attempts at intracranial hemorrhage (ICH) detection using deep-learning techniques have been plagued by clinical failures. We aimed to compare the performance of a deep-learning algorithm for ICH detection trained on strongly and weakly annotated datasets, and to assess whether a weighted ensemble model that integrates separate models trained using datasets with different ICH improves performance. Methods We used brain CT scans from the Radiological Society of North America (27,861 CT scans, 3,528 ICHs) and AI-Hub (53,045 CT scans, 7,013 ICHs) for training. DenseNet121, InceptionResNetV2, MobileNetV2, and VGG19 were trained on strongly and weakly annotated datasets and compared using independent external test datasets. We then developed a weighted ensemble model combining separate models trained on all ICH, subdural hemorrhage (SDH), subarachnoid hemorrhage (SAH), and small-lesion ICH cases. The final weighted ensemble model was compared to four well-known deep-learning models. After external testing, six neurologists reviewed 91 ICH cases difficult for AI and humans. Results InceptionResNetV2, MobileNetV2, and VGG19 models outperformed when trained on strongly annotated datasets. A weighted ensemble model combining models trained on SDH, SAH, and small-lesion ICH had a higher AUC, compared with a model trained on all ICH cases only. This model outperformed four deep-learning models (AUC [95% C.I.]: Ensemble model, 0.953[0.938-0.965]; InceptionResNetV2, 0.852[0.828-0.873]; DenseNet121, 0.875[0.852-0.895]; VGG19, 0.796[0.770-0.821]; MobileNetV2, 0.650[0.620-0.680]; p < 0.0001). In addition, the case review showed that a better understanding and management of difficult cases may facilitate clinical use of ICH detection algorithms. Conclusion We propose a weighted ensemble model for ICH detection, trained on large-scale, strongly annotated CT scans, as no model can capture all aspects of complex tasks.
Collapse
Affiliation(s)
- Dong-Wan Kang
- Department of Public Health, Seoul National University Bundang Hospital, Seongnam, Republic of Korea
- Department of Neurology, Gyeonggi Provincial Medical Center, Icheon Hospital, Icheon, Republic of Korea
- Department of Neurology, Seoul National University Bundang Hospital, Seoul National University College of Medicine, Seongnam, Republic of Korea
| | - Gi-Hun Park
- JLK Inc., Artificial Intelligence Research Center, Seoul, Republic of Korea
| | - Wi-Sun Ryu
- JLK Inc., Artificial Intelligence Research Center, Seoul, Republic of Korea
| | - Dawid Schellingerhout
- Department of Neuroradiology and Imaging Physics, The University of Texas M.D. Anderson Cancer Center, Houston, TX, United States
| | - Museong Kim
- Department of Neurosurgery, Seoul National University Bundang Hospital, Seoul National University College of Medicine, Seongnam, Republic of Korea
- Hospital Medicine Center, Seoul National University Bundang Hospital, Seoul National University College of Medicine, Seongnam, Republic of Korea
| | - Yong Soo Kim
- Department of Neurology, Nowon Eulji Medical Center, Eulji University School of Medicine, Seoul, Republic of Korea
| | - Chan-Young Park
- Department of Neurology, Chung-Ang University Hospital, Seoul, Republic of Korea
| | - Keon-Joo Lee
- Department of Neurology, Korea University Guro Hospital, Seoul, Republic of Korea
| | - Moon-Ku Han
- Department of Neurology, Seoul National University Bundang Hospital, Seoul National University College of Medicine, Seongnam, Republic of Korea
| | - Han-Gil Jeong
- Department of Neurology, Seoul National University Bundang Hospital, Seoul National University College of Medicine, Seongnam, Republic of Korea
- Department of Neurosurgery, Seoul National University Bundang Hospital, Seoul National University College of Medicine, Seongnam, Republic of Korea
| | - Dong-Eog Kim
- Department of Neurology, Dongguk University Ilsan Hospital, Goyang, Republic of Korea
- National Priority Research Center for Stroke, Goyang, Republic of Korea
| |
Collapse
|
18
|
Maghami M, Sattari SA, Tahmasbi M, Panahi P, Mozafari J, Shirbandi K. Diagnostic test accuracy of machine learning algorithms for the detection intracranial hemorrhage: a systematic review and meta-analysis study. Biomed Eng Online 2023; 22:114. [PMID: 38049809 PMCID: PMC10694901 DOI: 10.1186/s12938-023-01172-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/20/2023] [Accepted: 11/17/2023] [Indexed: 12/06/2023] Open
Abstract
BACKGROUND This systematic review and meta-analysis were conducted to objectively evaluate the evidence of machine learning (ML) in the patient diagnosis of Intracranial Hemorrhage (ICH) on computed tomography (CT) scans. METHODS Until May 2023, systematic searches were conducted in ISI Web of Science, PubMed, Scopus, Cochrane Library, IEEE Xplore Digital Library, CINAHL, Science Direct, PROSPERO, and EMBASE for studies that evaluated the diagnostic precision of ML model-assisted ICH detection. Patients with and without ICH as the target condition who were receiving CT-Scan were eligible for the research, which used ML algorithms based on radiologists' reports as the gold reference standard. For meta-analysis, pooled sensitivities, specificities, and a summary receiver operating characteristics curve (SROC) were used. RESULTS At last, after screening the title, abstract, and full paper, twenty-six retrospective and three prospective, and two retrospective/prospective studies were included. The overall (Diagnostic Test Accuracy) DTA of retrospective studies with a pooled sensitivity was 0.917 (95% CI 0.88-0.943, I2 = 99%). The pooled specificity was 0.945 (95% CI 0.918-0.964, I2 = 100%). The pooled diagnostic odds ratio (DOR) was 219.47 (95% CI 104.78-459.66, I2 = 100%). These results were significant for the specificity of the different network architecture models (p-value = 0.0289). However, the results for sensitivity (p-value = 0.6417) and DOR (p-value = 0.2187) were not significant. The ResNet algorithm has higher pooled specificity than other algorithms with 0.935 (95% CI 0.854-0.973, I2 = 93%). CONCLUSION This meta-analysis on DTA of ML algorithms for detecting ICH by assessing non-contrast CT-Scans shows the ML has an acceptable performance in diagnosing ICH. Using ResNet in ICH detection remains promising prediction was improved via training in an Architecture Learning Network (ALN).
Collapse
Affiliation(s)
- Masoud Maghami
- Medical Doctor (MD), School of Medicine, Ahvaz Jundishapur University of Medical Sciences, Ahvaz, Iran
| | - Shahab Aldin Sattari
- Department of Neurosurgery, Johns Hopkins University School of Medicine, Baltimore, MD, USA
| | - Marziyeh Tahmasbi
- Department of Medical Imaging and Radiation Sciences, School of Allied Medical Sciences, Ahvaz Jundishapur University of Medical Sciences, Ahvaz, Iran
| | - Pegah Panahi
- Medical Doctor (MD), School of Medicine, Ahvaz Jundishapur University of Medical Sciences, Ahvaz, Iran
| | - Javad Mozafari
- Department of Emergency Medicine, School of Medicine, Ahvaz Jundishapur University of Medical Sciences, Ahvaz, Iran
- Department of Radiology, Resident (MD), EUREGIO-KLINIK Albert-Schweitzer-Straße GmbH, Nordhorn, Germany
| | | |
Collapse
|
19
|
Lima WDS, Soares MHP, Paschoal EHA, Paschoal JKSF, Paschoal FM, Bor-Seng-Shu E. Intracranial hemorrhages in patients with COVID-19: a systematic review of the literature, regarding six cases in an Amazonian population. ARQUIVOS DE NEURO-PSIQUIATRIA 2023; 81:989-999. [PMID: 38035584 PMCID: PMC10689113 DOI: 10.1055/s-0043-1772834] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 10/15/2022] [Accepted: 05/01/2023] [Indexed: 12/02/2023]
Abstract
BACKGROUND Coronavirus disease 2019 (COVID-19) has emerged as a public health emergency worldwide, predominantly affecting the respiratory tract. However, evidence supports the involvement of extrapulmonary sites, including reports of intracranial hemorrhages. OBJECTIVE To describe six original cases and review the literature on intracranial hemorrhages in patients diagnosed with COVID-19 by molecular methods. METHODS A systematic literature review was performed on MEDLINE, PubMed, and NCBI electronic databases to identify eligible studies. Of the total 1,624 articles retrieved, only 53 articles met the inclusion criteria. RESULTS The overall incidence of intracranial hemorrhage in patients hospitalized for COVID-19 was 0.26%. In this patient group, the mean age was 60 years, and the majority were male (68%) with initial respiratory symptoms (73%) and some comorbidity. Before the diagnosis of hemorrhage, 43% of patients were using anticoagulants, 47.3% at therapeutic doses. The intraparenchymal (50%) was the most affected compartment, followed by the subarachnoid (34%), intraventricular (11%), and subdural (7%). There was a predominance of lobar over non-lobar topographies. Multifocal or multicompartmental hemorrhages were described in 25% of cases. Overall mortality in the cohort studies was 44%, while around 55% of patients were discharged from hospital. CONCLUSION Despite the unusual association, the combination of these two diseases is associated with high rates of mortality and morbidity, as well as more severe clinicoradiological presentations. Further studies are needed to provide robust evidence on the exact pathophysiology behind the occurrence of intracranial hemorrhages after COVID-19 infection.
Collapse
Affiliation(s)
- William de Sousa Lima
- Universidade Federal do Pará, Faculdade de Medicina, Departamento de Neurologia do Hospital Universitário João de Barros Barreto, Belém PA, Brazil.
| | - Marcelo Henrique Pereira Soares
- Universidade Federal do Pará, Faculdade de Medicina, Departamento de Neurologia do Hospital Universitário João de Barros Barreto, Belém PA, Brazil.
| | - Eric Homero Albuquerque Paschoal
- Universidade Federal do Pará, Faculdade de Medicina, Departamento de Neurologia do Hospital Universitário João de Barros Barreto, Belém PA, Brazil.
| | | | - Fernando Mendes Paschoal
- Universidade Federal do Pará, Faculdade de Medicina, Departamento de Neurologia do Hospital Universitário João de Barros Barreto, Belém PA, Brazil.
| | - Edson Bor-Seng-Shu
- Universidade de São Paulo, Faculdade de Medicina, Departamento de Neurologia do Hospital das Clínicas, São Paulo SP, Brazil.
| |
Collapse
|
20
|
Yalcinkaya DM, Youssef K, Heydari B, Simonetti O, Dharmakumar R, Raman S, Sharif B. Temporal Uncertainty Localization to Enable Human-in-the-Loop Analysis of Dynamic Contrast-Enhanced Cardiac MRI Datasets. MEDICAL IMAGE COMPUTING AND COMPUTER-ASSISTED INTERVENTION : MICCAI ... INTERNATIONAL CONFERENCE ON MEDICAL IMAGE COMPUTING AND COMPUTER-ASSISTED INTERVENTION 2023; 14222:453-462. [PMID: 38204763 PMCID: PMC10775176 DOI: 10.1007/978-3-031-43898-1_44] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 01/12/2024]
Abstract
Dynamic contrast-enhanced (DCE) cardiac magnetic resonance imaging (CMRI) is a widely used modality for diagnosing myocardial blood flow (perfusion) abnormalities. During a typical free-breathing DCE-CMRI scan, close to 300 time-resolved images of myocardial perfusion are acquired at various contrast "wash in/out" phases. Manual segmentation of myocardial contours in each time-frame of a DCE image series can be tedious and time-consuming, particularly when non-rigid motion correction has failed or is unavailable. While deep neural networks (DNNs) have shown promise for analyzing DCE-CMRI datasets, a "dynamic quality control" (dQC) technique for reliably detecting failed segmentations is lacking. Here we propose a new space-time uncertainty metric as a dQC tool for DNN-based segmentation of free-breathing DCE-CMRI datasets by validating the proposed metric on an external dataset and establishing a human-in-the-loop framework to improve the segmentation results. In the proposed approach, we referred the top 10% most uncertain segmentations as detected by our dQC tool to the human expert for refinement. This approach resulted in a significant increase in the Dice score (p < 0.001) and a notable decrease in the number of images with failed segmentation (16.2% to 11.3%) whereas the alternative approach of randomly selecting the same number of segmentations for human referral did not achieve any significant improvement. Our results suggest that the proposed dQC framework has the potential to accurately identify poor-quality segmentations and may enable efficient DNN-based analysis of DCE-CMRI in a human-in-the-loop pipeline for clinical interpretation and reporting of dynamic CMRI datasets.
Collapse
Affiliation(s)
- Dilek M Yalcinkaya
- Laboratory for Translational Imaging of Microcirculation, Indiana University School of Medicine (IUSM), Indianapolis, IN, USA
- Elmore Family School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA
| | - Khalid Youssef
- Laboratory for Translational Imaging of Microcirculation, Indiana University School of Medicine (IUSM), Indianapolis, IN, USA
- Krannert Cardiovascular Research Center, IUSM/IU Health Cardiovascular Institute, Indianapolis, IN, USA
| | - Bobak Heydari
- Stephenson Cardiac Imaging Centre, University of Calgary, Alberta, Canada
| | - Orlando Simonetti
- Department of Internal Medicine, Division of Cardiovascular Medicine, Davis Heart and Lung Research Institute, The Ohio State University, Columbus, OH, USA
| | - Rohan Dharmakumar
- Krannert Cardiovascular Research Center, IUSM/IU Health Cardiovascular Institute, Indianapolis, IN, USA
- Weldon School of Biomedical Engineering, Purdue University, West Lafayette, IN, USA
| | - Subha Raman
- Krannert Cardiovascular Research Center, IUSM/IU Health Cardiovascular Institute, Indianapolis, IN, USA
- Weldon School of Biomedical Engineering, Purdue University, West Lafayette, IN, USA
| | - Behzad Sharif
- Laboratory for Translational Imaging of Microcirculation, Indiana University School of Medicine (IUSM), Indianapolis, IN, USA
- Krannert Cardiovascular Research Center, IUSM/IU Health Cardiovascular Institute, Indianapolis, IN, USA
- Weldon School of Biomedical Engineering, Purdue University, West Lafayette, IN, USA
| |
Collapse
|
21
|
Agrawal D, Poonamallee L, Joshi S, Bahel V. Automated intracranial hemorrhage detection in traumatic brain injury using 3D CNN. J Neurosci Rural Pract 2023; 14:615-621. [PMID: 38059235 PMCID: PMC10696364 DOI: 10.25259/jnrp_172_2023] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/27/2023] [Accepted: 08/25/2023] [Indexed: 12/08/2023] Open
Abstract
Objectives Intracranial hemorrhage (ICH) is a prevalent and potentially fatal consequence of traumatic brain injury (TBI). Timely identification of ICH is crucial to ensure timely intervention and to optimize better patient outcomes. However, the current methods for diagnosing ICH from head computed tomography (CT) scans require skilled personnel (Radiologists and/or Neurosurgeons) who may be unavailable in all centers, especially in rural areas. The aim of this study is to develop a neurotrauma screening tool for identifying ICH from head CT scans of TBI patients. Materials and Methods We prospectively collected head CT scans from the Department of Neurosurgery, All India Institute of Medical Sciences, New Delhi. Approximately 738 consecutive head CT scans from patients enrolled in the department were collected for this study spanning a duration of 9 months, that is, January 2020 to September 2020. The metadata collected along with the head CT scans consisted of demographic and clinical details and the radiologist's report which was used as the gold standard. A deep learning-based 3D convolutional neural network (CNN) model was trained on the dataset. The pre-processing, hyperparameters, and augmentation were common for training the 3D CNN model whereas the training modules were set differently. The model was trained along with the save best model option and was monitored by validation metrics. The Institute Ethics Committee permission was taken before starting the study. Results We developed a 3D CNN model for automatically detecting the ICH from head CT scans. The screening tool was tested in 20 cases and trained on 200 head CT scans, with 99 normal head CT and 101 CT scans with some type of ICH. The final model performed with 90% sensitivity, 70% specificity, and 80% accuracy. Conclusion Our study reveals that the automated screening tool exhibits a commendable level of accuracy and sensitivity in detecting ICH from the head CT scans. The results indicate that the 3D CNN approach has a potential for further exploring the TBI-related pathologies.
Collapse
Affiliation(s)
- Deepak Agrawal
- Department of Neurosurgery, All India Institute of Medical Sciences, New Delhi, India
| | - Latha Poonamallee
- Department of Research, In-Med Prognostics Inc., San Diego, California, United States
| | - Sharwari Joshi
- Department of Research, In-Med Prognostics Inc., Pune, Maharashtra, India
| | - Vaibhav Bahel
- Department of Development, In-Med Prognostics Inc., Pune, Maharashtra, India
| |
Collapse
|
22
|
Abdollahifard S, Farrokhi A, Mowla A. Application of deep learning models for detection of subdural hematoma: a systematic review and meta-analysis. J Neurointerv Surg 2023; 15:995-1000. [PMID: 36418163 DOI: 10.1136/jnis-2022-019627] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/13/2022] [Accepted: 11/09/2022] [Indexed: 11/24/2022]
Abstract
BACKGROUND This study aimed to investigate the application of deep learning (DL) models for the detection of subdural hematoma (SDH). METHODS We conducted a comprehensive search using relevant keywords. Articles extracted were original studies in which sensitivity and/or specificity were reported. Two different approaches of frequentist and Bayesian inference were applied. For quality and risk of bias assessment we used Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2). RESULTS We analyzed 22 articles that included 1,997,749 patients. In the first step, the frequentist method showed a pooled sensitivity of 88.8% (95% confidence interval (CI): 83.9% to 92.4%) and a specificity of 97.2% (95% CI 94.6% to 98.6%). In the second step, using Bayesian methods including 11 studies that reported sensitivity and specificity, a sensitivity rate of 86.8% (95% CI: 77.6% to 92.9%) at a specificity level of 86.9% (95% CI: 60.9% to 97.2%) was achieved. The risk of bias assessment was not remarkable using QUADAS-2. CONCLUSION DL models might be an appropriate tool for detecting SDHs with a reasonably high sensitivity and specificity.
Collapse
Affiliation(s)
- Saeed Abdollahifard
- Medical School, Shiraz University of Medical Sciences, Shiraz, Iran
- Center for Neuromodulation and Pain, Shiraz University of Medical Sciences, Shiraz, Iran
| | - Amirmohammad Farrokhi
- Medical School, Shiraz University of Medical Sciences, Shiraz, Iran
- Center for Neuromodulation and Pain, Shiraz University of Medical Sciences, Shiraz, Iran
| | - Ashkan Mowla
- Neurological Surgery, University of Southern California, Los Angeles, California, USA
| |
Collapse
|
23
|
Hu P, Zhou H, Yan T, Miu H, Xiao F, Zhu X, Shu L, Yang S, Jin R, Dou W, Ren B, Zhu L, Liu W, Zhang Y, Zeng K, Ye M, Lv S, Wu M, Deng G, Hu R, Zhan R, Chen Q, Zhang D, Zhu X. Deep learning-assisted identification and quantification of aneurysmal subarachnoid hemorrhage in non-contrast CT scans: Development and external validation of Hybrid 2D/3D UNet. Neuroimage 2023; 279:120321. [PMID: 37574119 DOI: 10.1016/j.neuroimage.2023.120321] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/27/2023] [Revised: 08/01/2023] [Accepted: 08/10/2023] [Indexed: 08/15/2023] Open
Abstract
Accurate stroke assessment and consequent favorable clinical outcomes rely on the early identification and quantification of aneurysmal subarachnoid hemorrhage (aSAH) in non-contrast computed tomography (NCCT) images. However, hemorrhagic lesions can be complex and difficult to distinguish manually. To solve these problems, here we propose a novel Hybrid 2D/3D UNet deep-learning framework for automatic aSAH identification and quantification in NCCT images. We evaluated 1824 consecutive patients admitted with aSAH to four hospitals in China between June 2018 and May 2022. Accuracy and precision, Dice scores and intersection over union (IoU), and interclass correlation coefficients (ICC) were calculated to assess model performance, segmentation performance, and correlations between automatic and manual segmentation, respectively. A total of 1355 patients with aSAH were enrolled: 931, 101, 179, and 144 in four datasets, of whom 326 were scanned with Siemens, 640 with Philips, and 389 with GE Medical Systems scanners. Our proposed deep-learning method accurately identified (accuracies 0.993-0.999) and segmented (Dice scores 0.550-0.897) hemorrhage in both the internal and external datasets, even combinations of hemorrhage subtypes. We further developed a convenient AI-assisted platform based on our algorithm to assist clinical workflows, whose performance was comparable to manual measurements by experienced neurosurgeons (ICCs 0.815-0.957) but with greater efficiency and reduced cost. While this tool has not yet been prospectively tested in clinical practice, our innovative hybrid network algorithm and platform can accurately identify and quantify aSAH, paving the way for fast and cheap NCCT interpretation and a reliable AI-based approach to expedite clinical decision-making for aSAH patients.
Collapse
Affiliation(s)
- Ping Hu
- Department of Neurosurgery, The Second Affiliated Hospital of Nanchang University, Nanchang, Jiangxi 330006, China; Jiangxi Key Laboratory of Neurological Tumors and Cerebrovascular Diseases, Nanchang, Jiangxi 330006, China; Jiangxi Health Commission Key Laboratory of Neurological Medicine, Nanchang, Jiangxi 330006, China; Institute of Neuroscience, Nanchang University, Nanchang, Jiangxi 330006, China
| | - Haizhu Zhou
- School of Physics and Technology, Wuhan University, Wuhan, Hubei 430060, China
| | - Tengfeng Yan
- Department of Neurosurgery, The Second Affiliated Hospital of Nanchang University, Nanchang, Jiangxi 330006, China; Jiangxi Key Laboratory of Neurological Tumors and Cerebrovascular Diseases, Nanchang, Jiangxi 330006, China; Jiangxi Health Commission Key Laboratory of Neurological Medicine, Nanchang, Jiangxi 330006, China; Institute of Neuroscience, Nanchang University, Nanchang, Jiangxi 330006, China
| | - Hongping Miu
- Department of Neurosurgery, Southwest Hospital, Third Military Medical University (Army Medical University), Chongqing 400038, China
| | - Feng Xiao
- Department of Neurosurgery, First Affiliated Hospital, School of Medicine, Zhejiang University, Hangzhou, Zhejiang 310003, China
| | - Xinyi Zhu
- Department of Neurosurgery, Renmin Hospital of Wuhan University, Wuhan, Hubei 430060, China
| | - Lei Shu
- Department of Neurosurgery, The Second Affiliated Hospital of Nanchang University, Nanchang, Jiangxi 330006, China; Jiangxi Key Laboratory of Neurological Tumors and Cerebrovascular Diseases, Nanchang, Jiangxi 330006, China; Jiangxi Health Commission Key Laboratory of Neurological Medicine, Nanchang, Jiangxi 330006, China; Institute of Neuroscience, Nanchang University, Nanchang, Jiangxi 330006, China
| | - Shuang Yang
- School of Physics and Technology, Wuhan University, Wuhan, Hubei 430060, China
| | - Ruiyun Jin
- Department of Neurosurgery, The Second Affiliated Hospital of Nanchang University, Nanchang, Jiangxi 330006, China
| | - Wenlei Dou
- Department of Neurosurgery, The Second Affiliated Hospital of Nanchang University, Nanchang, Jiangxi 330006, China
| | - Baoyu Ren
- Department of Neurosurgery, The Second Affiliated Hospital of Nanchang University, Nanchang, Jiangxi 330006, China
| | - Lizhen Zhu
- Department of Neurosurgery, The Second Affiliated Hospital of Nanchang University, Nanchang, Jiangxi 330006, China
| | - Wanrong Liu
- Department of Neurosurgery, The Second Affiliated Hospital of Nanchang University, Nanchang, Jiangxi 330006, China
| | - Yihan Zhang
- Department of Neurosurgery, The Second Affiliated Hospital of Nanchang University, Nanchang, Jiangxi 330006, China
| | - Kaisheng Zeng
- Department of Neurosurgery, The Second Affiliated Hospital of Nanchang University, Nanchang, Jiangxi 330006, China
| | - Minhua Ye
- Department of Neurosurgery, The Second Affiliated Hospital of Nanchang University, Nanchang, Jiangxi 330006, China
| | - Shigang Lv
- Department of Neurosurgery, The Second Affiliated Hospital of Nanchang University, Nanchang, Jiangxi 330006, China
| | - Miaojing Wu
- Department of Neurosurgery, The Second Affiliated Hospital of Nanchang University, Nanchang, Jiangxi 330006, China
| | - Gang Deng
- Department of Neurosurgery, Renmin Hospital of Wuhan University, Wuhan, Hubei 430060, China
| | - Rong Hu
- Department of Neurosurgery, Southwest Hospital, Third Military Medical University (Army Medical University), Chongqing 400038, China
| | - Renya Zhan
- Department of Neurosurgery, First Affiliated Hospital, School of Medicine, Zhejiang University, Hangzhou, Zhejiang 310003, China
| | - Qianxue Chen
- Department of Neurosurgery, Renmin Hospital of Wuhan University, Wuhan, Hubei 430060, China
| | - Dong Zhang
- School of Physics and Technology, Wuhan University, Wuhan, Hubei 430060, China
| | - Xingen Zhu
- Department of Neurosurgery, The Second Affiliated Hospital of Nanchang University, Nanchang, Jiangxi 330006, China; Jiangxi Key Laboratory of Neurological Tumors and Cerebrovascular Diseases, Nanchang, Jiangxi 330006, China; Jiangxi Health Commission Key Laboratory of Neurological Medicine, Nanchang, Jiangxi 330006, China; Institute of Neuroscience, Nanchang University, Nanchang, Jiangxi 330006, China.
| |
Collapse
|
24
|
Nafees Ahmed S, Prakasam P. A systematic review on intracranial aneurysm and hemorrhage detection using machine learning and deep learning techniques. PROGRESS IN BIOPHYSICS AND MOLECULAR BIOLOGY 2023; 183:1-16. [PMID: 37499766 DOI: 10.1016/j.pbiomolbio.2023.07.001] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 03/21/2023] [Revised: 07/05/2023] [Accepted: 07/15/2023] [Indexed: 07/29/2023]
Abstract
The risk of discovering an intracranial aneurysm during the initial screening and follow-up screening are reported as around 11%, and 7% respectively (Zuurbie et al., 2023) to these mass effects, unruptured aneurysms frequently generate symptoms, however, the real hazard occurs when an aneurysm ruptures and results in a cerebral hemorrhage known as a subarachnoid hemorrhage. The objective is to study the multiple kinds of hemorrhage and aneurysm detection problems and develop machine and deep learning models to recognise them. Due to its early stage, subarachnoid hemorrhage, the most typical symptom after aneurysm rupture, is an important medical condition. It frequently results in severe neurological emergencies or even death. Although most aneurysms are asymptomatic and won't burst, because of their unpredictable growth, even small aneurysms are susceptible. A timely diagnosis is essential to prevent early mortality because a large percentage of hemorrhage cases present can be fatal. Physiological/imaging markers and the degree of the subarachnoid hemorrhage can be used as indicators for potential early treatments in hemorrhage. The hemodynamic pathomechanisms and microcellular environment should remain a priority for academics and medical professionals. There is still disagreement about how and when to care for aneurysms that have not ruptured despite studies reporting on the risk of rupture and outcomes. We are optimistic that with the progress in our understanding of the pathophysiology of hemorrhages and aneurysms and the advancement of artificial intelligence has made it feasible to conduct analyses with a high degree of precision, effectiveness and reliability.
Collapse
Affiliation(s)
- S Nafees Ahmed
- School of Electronics Engineering, Vellore Institute of Technology, Vellore, India.
| | - P Prakasam
- School of Electronics Engineering, Vellore Institute of Technology, Vellore, India.
| |
Collapse
|
25
|
Gilotra K, Swarna S, Mani R, Basem J, Dashti R. Role of artificial intelligence and machine learning in the diagnosis of cerebrovascular disease. Front Hum Neurosci 2023; 17:1254417. [PMID: 37746051 PMCID: PMC10516608 DOI: 10.3389/fnhum.2023.1254417] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/07/2023] [Accepted: 08/23/2023] [Indexed: 09/26/2023] Open
Abstract
Introduction Cerebrovascular diseases are known to cause significant morbidity and mortality to the general population. In patients with cerebrovascular disease, prompt clinical evaluation and radiographic interpretation are both essential in optimizing clinical management and in triaging patients for critical and potentially life-saving neurosurgical interventions. With recent advancements in the domains of artificial intelligence (AI) and machine learning (ML), many AI and ML algorithms have been developed to further optimize the diagnosis and subsequent management of cerebrovascular disease. Despite such advances, further studies are needed to substantively evaluate both the diagnostic accuracy and feasibility of these techniques for their application in clinical practice. This review aims to analyze the current use of AI and MI algorithms in the diagnosis of, and clinical decision making for cerebrovascular disease, and to discuss both the feasibility and future applications of utilizing such algorithms. Methods We review the use of AI and ML algorithms to assist clinicians in the diagnosis and management of ischemic stroke, hemorrhagic stroke, intracranial aneurysms, and arteriovenous malformations (AVMs). After identifying the most widely used algorithms, we provide a detailed analysis of the accuracy and effectiveness of these algorithms in practice. Results The incorporation of AI and ML algorithms for cerebrovascular patients has demonstrated improvements in time to detection of intracranial pathologies such as intracerebral hemorrhage (ICH) and infarcts. For ischemic and hemorrhagic strokes, commercial AI software platforms such as RapidAI and Viz.AI have bene implemented into routine clinical practice at many stroke centers to expedite the detection of infarcts and ICH, respectively. Such algorithms and neural networks have also been analyzed for use in prognostication for such cerebrovascular pathologies. These include predicting outcomes for ischemic stroke patients, hematoma expansion, risk of aneurysm rupture, bleeding of AVMs, and in predicting outcomes following interventions such as risk of occlusion for various endovascular devices. Preliminary analyses have yielded promising sensitivities when AI and ML are used in concert with imaging modalities and a multidisciplinary team of health care providers. Conclusion The implementation of AI and ML algorithms to supplement clinical practice has conferred a high degree of accuracy, efficiency, and expedited detection in the clinical and radiographic evaluation and management of ischemic and hemorrhagic strokes, AVMs, and aneurysms. Such algorithms have been explored for further purposes of prognostication for these conditions, with promising preliminary results. Further studies should evaluate the longitudinal implementation of such techniques into hospital networks and residency programs to supplement clinical practice, and the extent to which these techniques improve patient care and clinical outcomes in the long-term.
Collapse
Affiliation(s)
| | | | | | | | - Reza Dashti
- Dashti Lab, Department of Neurological Surgery, Stony Brook University Hospital, Stony Brook, NY, United States
| |
Collapse
|
26
|
Wang D, Jin R, Shieh CC, Ng AY, Pham H, Dugal T, Barnett M, Winoto L, Wang C, Barnett Y. Real world validation of an AI-based CT hemorrhage detection tool. Front Neurol 2023; 14:1177723. [PMID: 37602253 PMCID: PMC10435741 DOI: 10.3389/fneur.2023.1177723] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/01/2023] [Accepted: 07/12/2023] [Indexed: 08/22/2023] Open
Abstract
Introduction Intracranial hemorrhage (ICH) is a potentially life-threatening medical event that requires expedited diagnosis with computed tomography (CT). Automated medical imaging triaging tools can rapidly bring scans containing critical abnormalities, such as ICH, to the attention of radiologists and clinicians. Here, we retrospectively investigated the real-world performance of VeriScout™, an artificial intelligence-based CT hemorrhage detection and triage tool. Methods Ground truth for the presence or absence of ICH was iteratively determined by expert consensus in an unselected dataset of 527 consecutively acquired non-contrast head CT scans, which were sub-grouped according to the presence of artefact, post-operative features and referral source. The performance of VeriScout™ was compared with the ground truths for all groups. Results VeriScout™ detected hemorrhage with a sensitivity of 0.92 (CI 0.84-0.96) and a specificity of 0.96 (CI 0.94-0.98) in the global dataset, exceeding the sensitivity of general radiologists (0.88) with only a minor relative decrement in specificity (0.98). Crucially, the AI tool detected 13/14 cases of subarachnoid hemorrhage, a potentially fatal condition that is often missed in emergency department settings. There was no decrement in the performance of VeriScout™ in scans containing artefact or postoperative change. Using an integrated informatics platform, VeriScout™ was deployed into the existing radiology workflow. Detected hemorrhage cases were flagged in the hospital radiology information system (RIS) and relevant, annotated, preview images made available in the picture archiving and communications system (PACS) within 10 min. Conclusion AI-based radiology worklist prioritization for critical abnormalities, such as ICH, may enhance patient care without adding to radiologist or clinician burden.
Collapse
Affiliation(s)
- Dongang Wang
- Sydney Neuroimaging Analysis Centre, Camperdown, NSW, Australia
- Brain and Mind Centre, University of Sydney, Sydney, NSW, Australia
| | - Ruilin Jin
- Department of Medical Imaging, St. Vincent’s Hospital, Sydney, NSW, Australia
| | | | - Adrian Y. Ng
- Emergency Department, St. Vincent’s Hospital, Sydney, NSW, Australia
| | - Hiep Pham
- Department of Medical Imaging, St. Vincent’s Hospital, Sydney, NSW, Australia
| | - Tej Dugal
- Sydney Neuroimaging Analysis Centre, Camperdown, NSW, Australia
| | - Michael Barnett
- Sydney Neuroimaging Analysis Centre, Camperdown, NSW, Australia
- Brain and Mind Centre, University of Sydney, Sydney, NSW, Australia
| | - Luis Winoto
- Emergency Department, St. Vincent’s Hospital, Sydney, NSW, Australia
| | - Chenyu Wang
- Sydney Neuroimaging Analysis Centre, Camperdown, NSW, Australia
- Brain and Mind Centre, University of Sydney, Sydney, NSW, Australia
| | - Yael Barnett
- Sydney Neuroimaging Analysis Centre, Camperdown, NSW, Australia
- Department of Medical Imaging, St. Vincent’s Hospital, Sydney, NSW, Australia
| |
Collapse
|
27
|
Gramer R, Shlobin NA, Yang Z, Niedzwiecki D, Haglund MM, Fuller AT. Clinical Utility of Near-Infrared Device in Detecting Traumatic Intracranial Hemorrhage: A Pilot Study Toward Application as an Emergent Diagnostic Modality in a Low-Resource Setting. J Neurotrauma 2023; 40:1596-1602. [PMID: 35856820 DOI: 10.1089/neu.2021.0342] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/13/2022] Open
Abstract
Limited computed tomography (CT) availability in low- and middle-income countries frequently impedes life-saving neurosurgical decompression for traumatic brain injury. A reliable, accessible, cost-effective solution is necessary to detect and localize bleeds. We report the largest study to date using a near-infrared device (NIRD) to detect traumatic intracranial bleeds. Patients with confirmed or suspected head trauma who received a head CT scan were included. Within 30 min of the initial head CT scan, a blinded examiner scanned each patient's cranium with a NIRD, interrogating bilaterally the frontal, parietal, temporal, and occipital quadrants Sensitivity, specificity, accuracy, and precision were investigated. We recruited 500 consecutive patients; 104 patients had intracranial bleeding. For all patients with CT-proven bleeds, irrespective of size, initial NIRD scans localized the bleed to the appropriate quadrant with a sensitivity of 86% and specificity of 96% compared with CT. For extra-axial bleeds >3.5mL, sensitivity and specificity were 94% and 96%, respectively. For longitudinal serial rescans with the NIRD, sensitivity was 89% (< 4 days from injury: sensitivity: 99%), and specificity was 96%. For all patients who required craniectomy or craniotomy, the device demonstrated 100% sensitivity. NIRD is highly sensitive, specific, and reproducible over time in diagnosing intracranial bleeds. NIRD may inform neurosurgical decision making in settings where CT scanning is unavailable or impractical.
Collapse
Affiliation(s)
- Robert Gramer
- Department of Neurological Surgery, Massachusetts General Hospital, Boston, Massachusetts, USA
- Duke Global Neurosurgery and Neurology, Duke University, Durham, North Carolina, USA
| | - Nathan A Shlobin
- Duke Global Neurosurgery and Neurology, Duke University, Durham, North Carolina, USA
- Department of Neurological Surgery, Northwestern University Feinberg School of Medicine, Chicago, Illinois, USA
| | - Zidanyue Yang
- Department of Biostatistics and Bioinformatics, Duke University, Durham, North Carolina, USA
| | - Donna Niedzwiecki
- Department of Biostatistics and Bioinformatics, Duke University, Durham, North Carolina, USA
| | - Michael M Haglund
- Duke Global Neurosurgery and Neurology, Duke University, Durham, North Carolina, USA
| | - Anthony T Fuller
- Duke Global Neurosurgery and Neurology, Duke University, Durham, North Carolina, USA
| |
Collapse
|
28
|
Spahr A, Ståhle J, Wang C, Kaijser M. Label-efficient deep semantic segmentation of intracranial hemorrhages in CT-scans. FRONTIERS IN NEUROIMAGING 2023; 2:1157565. [PMID: 37554648 PMCID: PMC10406224 DOI: 10.3389/fnimg.2023.1157565] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 02/02/2023] [Accepted: 06/22/2023] [Indexed: 08/10/2023]
Abstract
Intracranial hemorrhage (ICH) is a common finding in traumatic brain injury (TBI) and computed tomography (CT) is considered the gold standard for diagnosis. Automated detection of ICH provides clinical value in diagnostics and in the ability to feed robust quantification measures into future prediction models. Several studies have explored ICH detection and segmentation but the research process is somewhat hindered due to a lack of open large and labeled datasets, making validation and comparison almost impossible. The complexity of the task is further challenged by the heterogeneity of ICH patterns, requiring a large number of labeled data to train robust and reliable models. Consequently, due to the labeling cost, there is a need for label-efficient algorithms that can exploit easily available unlabeled or weakly-labeled data. Our aims for this study were to evaluate whether transfer learning can improve ICH segmentation performance and to compare a variety of transfer learning approaches that harness unlabeled and weakly-labeled data. Three self-supervised and three weakly-supervised transfer learning approaches were explored. To be used in our comparisons, we also manually labeled a dataset of 51 CT scans. We demonstrate that transfer learning improves ICH segmentation performance on both datasets. Unlike most studies on ICH segmentation our work relies exclusively on publicly available datasets, allowing for easy comparison of performances in future studies. To further promote comparison between studies, we also present a new public dataset of ICH-labeled CT scans, Seq-CQ500.
Collapse
Affiliation(s)
- Antoine Spahr
- Department of Biomedical Engineering and Health Systems, KTH Royal Institute of Technology, Stockholm, Sweden
- Signal Processing Laboratory (LTS5), École Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland
- CHUV—Lausanne University Hospital, Lausanne, Switzerland
| | - Jennifer Ståhle
- Department of Clinical Neuroscience, Karolinska Institutet, Solna, Stockholm, Sweden
- Department of Neuroradiology, Karolinska University Hospital, Stockholm, Sweden
| | - Chunliang Wang
- Department of Biomedical Engineering and Health Systems, KTH Royal Institute of Technology, Stockholm, Sweden
| | - Magnus Kaijser
- Department of Neuroradiology, Karolinska University Hospital, Stockholm, Sweden
- Institute of Environmental Medicine, Karolinska Institutet, Stockholm, Sweden
| |
Collapse
|
29
|
Sengupta J, Alzbutas R, Falkowski-Gilski P, Falkowska-Gilska B. Intracranial hemorrhage detection in 3D computed tomography images using a bi-directional long short-term memory network-based modified genetic algorithm. Front Neurosci 2023; 17:1200630. [PMID: 37469843 PMCID: PMC10352619 DOI: 10.3389/fnins.2023.1200630] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/12/2023] [Accepted: 06/12/2023] [Indexed: 07/21/2023] Open
Abstract
Introduction Intracranial hemorrhage detection in 3D Computed Tomography (CT) brain images has gained more attention in the research community. The major issue to deal with the 3D CT brain images is scarce and hard to obtain the labelled data with better recognition results. Methods To overcome the aforementioned problem, a new model has been implemented in this research manuscript. After acquiring the images from the Radiological Society of North America (RSNA) 2019 database, the region of interest (RoI) was segmented by employing Otsu's thresholding method. Then, feature extraction was performed utilizing Tamura features: directionality, contrast, coarseness, and Gradient Local Ternary Pattern (GLTP) descriptors to extract vectors from the segmented RoI regions. The extracted vectors were dimensionally reduced by proposing a modified genetic algorithm, where the infinite feature selection technique was incorporated with the conventional genetic algorithm to further reduce the redundancy within the regularized vectors. The selected optimal vectors were finally fed to the Bi-directional Long Short Term Memory (Bi-LSTM) network to classify intracranial hemorrhage sub-types, such as subdural, intraparenchymal, subarachnoid, epidural, and intraventricular. Results The experimental investigation demonstrated that the Bi-LSTM based modified genetic algorithm obtained 99.40% sensitivity, 99.80% accuracy, and 99.48% specificity, which are higher compared to the existing machine learning models: Naïve Bayes, Random Forest, Support Vector Machine (SVM), Recurrent Neural Network (RNN), and Long Short-Term Memory (LSTM) network.
Collapse
|
30
|
AlRyalat SA, Singh P, Kalpathy-Cramer J, Kahook MY. Artificial Intelligence and Glaucoma: Going Back to Basics. Clin Ophthalmol 2023; 17:1525-1530. [PMID: 37284059 PMCID: PMC10239633 DOI: 10.2147/opth.s410905] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/22/2023] [Accepted: 05/24/2023] [Indexed: 06/08/2023] Open
Abstract
There has been a recent surge in the number of publications centered on the use of artificial intelligence (AI) to diagnose various systemic diseases. The Food and Drug Administration has approved several algorithms for use in clinical practice. In ophthalmology, most advances in AI relate to diabetic retinopathy, which is a disease process with agreed upon diagnostic and classification criteria. However, this is not the case for glaucoma, which is a relatively complex disease without agreed-upon diagnostic criteria. Moreover, currently available public datasets that focus on glaucoma have inconstant label quality, further complicating attempts at training AI algorithms efficiently. In this perspective paper, we discuss specific details related to developing AI models for glaucoma and suggest potential steps to overcome current limitations.
Collapse
Affiliation(s)
| | - Praveer Singh
- Department of Ophthalmology, University of Colorado School of Medicine, Sue Anschutz-Rodgers Eye Center, Aurora, CO, USA
| | - Jayashree Kalpathy-Cramer
- Department of Ophthalmology, University of Colorado School of Medicine, Sue Anschutz-Rodgers Eye Center, Aurora, CO, USA
| | - Malik Y Kahook
- Department of Ophthalmology, University of Colorado School of Medicine, Sue Anschutz-Rodgers Eye Center, Aurora, CO, USA
| |
Collapse
|
31
|
Chandrabhatla AS, Kuo EA, Sokolowski JD, Kellogg RT, Park M, Mastorakos P. Artificial Intelligence and Machine Learning in the Diagnosis and Management of Stroke: A Narrative Review of United States Food and Drug Administration-Approved Technologies. J Clin Med 2023; 12:jcm12113755. [PMID: 37297949 DOI: 10.3390/jcm12113755] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/30/2023] [Revised: 05/22/2023] [Accepted: 05/26/2023] [Indexed: 06/12/2023] Open
Abstract
Stroke is an emergency in which delays in treatment can lead to significant loss of neurological function and be fatal. Technologies that increase the speed and accuracy of stroke diagnosis or assist in post-stroke rehabilitation can improve patient outcomes. No resource exists that comprehensively assesses artificial intelligence/machine learning (AI/ML)-enabled technologies indicated for the management of ischemic and hemorrhagic stroke. We queried a United States Food and Drug Administration (FDA) database, along with PubMed and private company websites, to identify the recent literature assessing the clinical performance of FDA-approved AI/ML-enabled technologies. The FDA has approved 22 AI/ML-enabled technologies that triage brain imaging for more immediate diagnosis or promote post-stroke neurological/functional recovery. Technologies that assist with diagnosis predominantly use convolutional neural networks to identify abnormal brain images (e.g., CT perfusion). These technologies perform comparably to neuroradiologists, improve clinical workflows (e.g., time from scan acquisition to reading), and improve patient outcomes (e.g., days spent in the neurological ICU). Two devices are indicated for post-stroke rehabilitation by leveraging neuromodulation techniques. Multiple FDA-approved technologies exist that can help clinicians better diagnose and manage stroke. This review summarizes the most up-to-date literature regarding the functionality, performance, and utility of these technologies so clinicians can make informed decisions when using them in practice.
Collapse
Affiliation(s)
- Anirudha S Chandrabhatla
- School of Medicine, University of Virginia Health Sciences Center, 1215 Lee Street, Charlottesville, VA 22903, USA
- Department of Neurological Surgery, University of Virginia Health Sciences Center, 1215 Lee Street, Charlottesville, VA 22903, USA
| | - Elyse A Kuo
- School of Medicine, University of Virginia Health Sciences Center, 1215 Lee Street, Charlottesville, VA 22903, USA
- Department of Neurological Surgery, University of Virginia Health Sciences Center, 1215 Lee Street, Charlottesville, VA 22903, USA
| | - Jennifer D Sokolowski
- Department of Neurological Surgery, University of Virginia Health Sciences Center, 1215 Lee Street, Charlottesville, VA 22903, USA
| | - Ryan T Kellogg
- Department of Neurological Surgery, University of Virginia Health Sciences Center, 1215 Lee Street, Charlottesville, VA 22903, USA
| | - Min Park
- Department of Neurological Surgery, University of Virginia Health Sciences Center, 1215 Lee Street, Charlottesville, VA 22903, USA
| | - Panagiotis Mastorakos
- Department of Neurological Surgery, University of Virginia Health Sciences Center, 1215 Lee Street, Charlottesville, VA 22903, USA
- Department of Neurological Surgery, Thomas Jefferson University Hospital, 111 S 11th Street, Philadelphia, PA 19107, USA
| |
Collapse
|
32
|
Neves G, Warman PI, Warman A, Warman R, Bueso T, Vadhan JD, Windisch T. External Validation of an Artificial Intelligence Device for Intracranial Hemorrhage Detection. World Neurosurg 2023; 173:e800-e807. [PMID: 36906085 DOI: 10.1016/j.wneu.2023.03.019] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/18/2022] [Revised: 03/03/2023] [Accepted: 03/04/2023] [Indexed: 03/12/2023]
Abstract
BACKGROUND Artificial intelligence applications have gained traction in the field of cerebrovascular disease by assisting in the triage, classification, and prognostication of both ischemic and hemorrhagic stroke. The Caire ICH system aims to be the first device to move into the realm of assisted diagnosis for intracranial hemorrhage (ICH) and its subtypes. METHODS A single-center retrospective dataset of 402 head noncontrast CT scans (NCCT) with an intracranial hemorrhage were retrospectively collected from January 2012 to July 2020; an additional 108 NCCT scans with no intracranial hemorrhage findings were also included. The presence of an ICH and its subtype were determined from the International Classification of Diseases-10 code associated with the scan and validated by an expert panel. We used the Caire ICH vR1 to analyze these scans, and we evaluated its performance in terms of accuracy, sensitivity, and specificity. RESULTS We found the Caire ICH system to have an accuracy of 98.05% (95% confidence interval [CI]: 96.44%-99.06%), a sensitivity of 97.52% (95% CI: 95.50%-98.81%), and a specificity of 100% (95% CI: 96.67%-100.00%) in the detection of ICH. Experts reviewed the 10 incorrectly classified scans. CONCLUSIONS The Caire ICH vR1 algorithm was highly accurate, sensitive, and specific in detecting the presence or absence of an ICH and its subtypes in NCCTs. This work suggests that the Caire ICH device has potential to minimize clinical errors in ICH diagnosis that could improve patient outcomes and current workflows as both a point-of-care tool for diagnostics and as a safety net for radiologists.
Collapse
Affiliation(s)
- Gabriel Neves
- Department of Neurology, Texas Tech University Medical Sciences Center, Lubbock, Texas, USA.
| | | | | | | | - Tulio Bueso
- Department of Neurology, Texas Tech University Medical Sciences Center, Lubbock, Texas, USA
| | - Jason D Vadhan
- Department of Emergency Medicine, UT Southwestern Medical Center, Dallas, Texas, USA
| | - Thomas Windisch
- Department of Neurology, Texas Tech University Medical Sciences Center, Lubbock, Texas, USA; Covenant Health, Lubbock, Texas, USA
| |
Collapse
|
33
|
Huang YW, Huang HL, Li ZP, Yin XS. Research advances in imaging markers for predicting hematoma expansion in intracerebral hemorrhage: a narrative review. Front Neurol 2023; 14:1176390. [PMID: 37181553 PMCID: PMC10166819 DOI: 10.3389/fneur.2023.1176390] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/28/2023] [Accepted: 04/03/2023] [Indexed: 05/16/2023] Open
Abstract
Introduction Stroke is a major global health concern and is ranked as the second leading cause of death worldwide, with the third highest incidence of disability. Intracerebral hemorrhage (ICH) is a devastating form of stroke that is responsible for a significant proportion of stroke-related morbidity and mortality worldwide. Hematoma expansion (HE), which occurs in up to one-third of ICH patients, is a strong predictor of poor prognosis and can be potentially preventable if high-risk patients are identified early. In this review, we provide a comprehensive summary of previous research in this area and highlight the potential use of imaging markers for future research studies. Recent advances Imaging markers have been developed in recent years to aid in the early detection of HE and guide clinical decision-making. These markers have been found to be effective in predicting HE in ICH patients and include specific manifestations on Computed Tomography (CT) and CT Angiography (CTA), such as the spot sign, leakage sign, spot-tail sign, island sign, satellite sign, iodine sign, blend sign, swirl sign, black hole sign, and hypodensities. The use of imaging markers holds great promise for improving the management and outcomes of ICH patients. Conclusion The management of ICH presents a significant challenge, and identifying high-risk patients for HE is crucial to improving outcomes. The use of imaging markers for HE prediction can aid in the rapid identification of such patients and may serve as potential targets for anti-HE therapies in the acute phase of ICH. Therefore, further research is needed to establish the reliability and validity of these markers in identifying high-risk patients and guiding appropriate treatment decisions.
Collapse
Affiliation(s)
- Yong-Wei Huang
- Department of Neurosurgery, Mianyang Central Hospital, School of Medicine, University of Electronic Science and Technology of China, Mianyang, Sichuan, China
| | - Hai-Lin Huang
- Department of Neurosurgery, Mianyang Central Hospital, School of Medicine, University of Electronic Science and Technology of China, Mianyang, Sichuan, China
| | - Zong-Ping Li
- Department of Neurosurgery, Mianyang Central Hospital, School of Medicine, University of Electronic Science and Technology of China, Mianyang, Sichuan, China
| | - Xiao-Shuang Yin
- Department of Immunology, Mianyang Central Hospital, School of Medicine, University of Electronic Science and Technology of China, Mianyang, Sichuan, China
| |
Collapse
|
34
|
Yeo M, Tahayori B, Kok HK, Maingard J, Kutaiba N, Russell J, Thijs V, Jhamb A, Chandra RV, Brooks M, Barras CD, Asadi H. Evaluation of techniques to improve a deep learning algorithm for the automatic detection of intracranial haemorrhage on CT head imaging. Eur Radiol Exp 2023; 7:17. [PMID: 37032417 PMCID: PMC10083149 DOI: 10.1186/s41747-023-00330-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/09/2022] [Accepted: 02/07/2023] [Indexed: 04/11/2023] Open
Abstract
BACKGROUND Deep learning (DL) algorithms are playing an increasing role in automatic medical image analysis. PURPOSE To evaluate the performance of a DL model for the automatic detection of intracranial haemorrhage and its subtypes on non-contrast CT (NCCT) head studies and to compare the effects of various preprocessing and model design implementations. METHODS The DL algorithm was trained and externally validated on open-source, multi-centre retrospective data containing radiologist-annotated NCCT head studies. The training dataset was sourced from four research institutions across Canada, the USA and Brazil. The test dataset was sourced from a research centre in India. A convolutional neural network (CNN) was used, with its performance compared against similar models with additional implementations: (1) a recurrent neural network (RNN) attached to the CNN, (2) preprocessed CT image-windowed inputs and (3) preprocessed CT image-concatenated inputs. The area under the receiver operating characteristic curve (AUC-ROC) and microaveraged precision (mAP) score were used to evaluate and compare model performances. RESULTS The training and test datasets contained 21,744 and 491 NCCT head studies, respectively, with 8,882 (40.8%) and 205 (41.8%) positive for intracranial haemorrhage. Implementation of preprocessing techniques and the CNN-RNN framework increased mAP from 0.77 to 0.93 and increased AUC-ROC [95% confidence intervals] from 0.854 [0.816-0.889] to 0.966 [0.951-0.980] (p-value = 3.91 × 10-12). CONCLUSIONS The deep learning model accurately detected intracranial haemorrhage and improved in performance following specific implementation techniques, demonstrating clinical potential as a decision support tool and an automated system to improve radiologist workflow efficiency. KEY POINTS • The deep learning model detected intracranial haemorrhages on computed tomography with high accuracy. • Image preprocessing, such as windowing, plays a large role in improving deep learning model performance. • Implementations which enable an analysis of interslice dependencies can improve deep learning model performance. • Visual saliency maps can facilitate explainable artificial intelligence systems. • Deep learning within a triage system may expedite earlier intracranial haemorrhage detection.
Collapse
Affiliation(s)
- Melissa Yeo
- Melbourne Medical School, The University of Melbourne, Melbourne, VIC, Australia.
| | - Bahman Tahayori
- Department of Biomedical Engineering, The University of Melbourne, Melbourne, VIC, Australia
- IBM Research Australia, Melbourne, VIC, Australia
| | - Hong Kuan Kok
- Interventional Radiology Service, Department of Radiology, Northern Health, Epping, VIC, Australia
- School of Medicine, Faculty of Health, Deakin University, Burwood, VIC, Australia
| | - Julian Maingard
- School of Medicine, Faculty of Health, Deakin University, Burwood, VIC, Australia
- Interventional Neuroradiology Unit, Monash Health, Clayton, VIC, Australia
- Faculty of Medicine Nursing and Health Sciences, Monash University, Clayton, VIC, Australia
- Department of Radiology, St Vincent's Hospital, Melbourne, VIC, Australia
| | - Numan Kutaiba
- Department of Radiology, Austin Hospital, Melbourne, VIC, Australia
| | - Jeremy Russell
- Department of Neurosurgery, Austin Hospital, Melbourne, VIC, Australia
| | - Vincent Thijs
- Stroke Theme, Florey Institute of Neuroscience and Mental Health, Melbourne, VIC, Australia
- Department of Neurology, Austin Health, Melbourne, VIC, Australia
| | - Ashu Jhamb
- Department of Radiology, St Vincent's Hospital, Melbourne, VIC, Australia
| | - Ronil V Chandra
- Interventional Neuroradiology Unit, Monash Health, Clayton, VIC, Australia
- Faculty of Medicine Nursing and Health Sciences, Monash University, Clayton, VIC, Australia
| | - Mark Brooks
- Melbourne Medical School, The University of Melbourne, Melbourne, VIC, Australia
- School of Medicine, Faculty of Health, Deakin University, Burwood, VIC, Australia
- Stroke Theme, Florey Institute of Neuroscience and Mental Health, Melbourne, VIC, Australia
- Interventional Neuroradiology Service, Department of Radiology, Austin Hospital, Melbourne, VIC, Australia
| | - Christen D Barras
- South Australian Institute of Health and Medical Research, Adelaide, South Australia, Australia
- School of Medicine, The University of Adelaide, Adelaide, South Australia, Australia
| | - Hamed Asadi
- Melbourne Medical School, The University of Melbourne, Melbourne, VIC, Australia
- School of Medicine, Faculty of Health, Deakin University, Burwood, VIC, Australia
- Interventional Neuroradiology Unit, Monash Health, Clayton, VIC, Australia
- Department of Radiology, St Vincent's Hospital, Melbourne, VIC, Australia
- Stroke Theme, Florey Institute of Neuroscience and Mental Health, Melbourne, VIC, Australia
- Interventional Neuroradiology Service, Department of Radiology, Austin Hospital, Melbourne, VIC, Australia
| |
Collapse
|
35
|
Yun TJ, Choi JW, Han M, Jung WS, Choi SH, Yoo RE, Hwang IP. Deep learning based automatic detection algorithm for acute intracranial haemorrhage: a pivotal randomized clinical trial. NPJ Digit Med 2023; 6:61. [PMID: 37029272 PMCID: PMC10082037 DOI: 10.1038/s41746-023-00798-8] [Citation(s) in RCA: 6] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/10/2022] [Accepted: 03/10/2023] [Indexed: 04/09/2023] Open
Abstract
Acute intracranial haemorrhage (AIH) is a potentially life-threatening emergency that requires prompt and accurate assessment and management. This study aims to develop and validate an artificial intelligence (AI) algorithm for diagnosing AIH using brain-computed tomography (CT) images. A retrospective, multi-reader, pivotal, crossover, randomised study was performed to validate the performance of an AI algorithm was trained using 104,666 slices from 3010 patients. Brain CT images (12,663 slices from 296 patients) were evaluated by nine reviewers belonging to one of the three subgroups (non-radiologist physicians, n = 3; board-certified radiologists, n = 3; and neuroradiologists, n = 3) with and without the aid of our AI algorithm. Sensitivity, specificity, and accuracy were compared between AI-unassisted and AI-assisted interpretations using the chi-square test. Brain CT interpretation with AI assistance results in significantly higher diagnostic accuracy than that without AI assistance (0.9703 vs. 0.9471, p < 0.0001, patient-wise). Among the three subgroups of reviewers, non-radiologist physicians demonstrate the greatest improvement in diagnostic accuracy for brain CT interpretation with AI assistance compared to that without AI assistance. For board-certified radiologists, the diagnostic accuracy for brain CT interpretation is significantly higher with AI assistance than without AI assistance. For neuroradiologists, although brain CT interpretation with AI assistance results in a trend for higher diagnostic accuracy compared to that without AI assistance, the difference does not reach statistical significance. For the detection of AIH, brain CT interpretation with AI assistance results in better diagnostic performance than that without AI assistance, with the most significant improvement observed for non-radiologist physicians.
Collapse
Affiliation(s)
- Tae Jin Yun
- Institute of Radiation Medicine, Seoul National University Medical Research Center, Seoul, Republic of Korea
- Department of Radiology, Seoul National University Hospital, Seoul, Republic of Korea
| | - Jin Wook Choi
- Department of Radiology, Ajou University School of Medicine, Suwon, Republic of Korea.
| | - Miran Han
- Department of Radiology, Ajou University School of Medicine, Suwon, Republic of Korea
| | - Woo Sang Jung
- Department of Radiology, Ajou University School of Medicine, Suwon, Republic of Korea
| | - Seung Hong Choi
- Institute of Radiation Medicine, Seoul National University Medical Research Center, Seoul, Republic of Korea
- Department of Radiology, Seoul National University Hospital, Seoul, Republic of Korea
| | - Roh-Eul Yoo
- Institute of Radiation Medicine, Seoul National University Medical Research Center, Seoul, Republic of Korea
- Department of Radiology, Seoul National University Hospital, Seoul, Republic of Korea
| | - In Pyeong Hwang
- Institute of Radiation Medicine, Seoul National University Medical Research Center, Seoul, Republic of Korea
- Department of Radiology, Seoul National University Hospital, Seoul, Republic of Korea
| |
Collapse
|
36
|
Lee SB, Hong Y, Cho YJ, Jeong D, Lee J, Yoon SH, Lee S, Choi YH, Cheon JE. Deep Learning-Based Computed Tomography Image Standardization to Improve Generalizability of Deep Learning-Based Hepatic Segmentation. Korean J Radiol 2023; 24:294-304. [PMID: 36907592 PMCID: PMC10067697 DOI: 10.3348/kjr.2022.0588] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/17/2022] [Revised: 12/19/2022] [Accepted: 01/24/2023] [Indexed: 03/14/2023] Open
Abstract
OBJECTIVE We aimed to investigate whether image standardization using deep learning-based computed tomography (CT) image conversion would improve the performance of deep learning-based automated hepatic segmentation across various reconstruction methods. MATERIALS AND METHODS We collected contrast-enhanced dual-energy CT of the abdomen that was obtained using various reconstruction methods, including filtered back projection, iterative reconstruction, optimum contrast, and monoenergetic images with 40, 60, and 80 keV. A deep learning based image conversion algorithm was developed to standardize the CT images using 142 CT examinations (128 for training and 14 for tuning). A separate set of 43 CT examinations from 42 patients (mean age, 10.1 years) was used as the test data. A commercial software program (MEDIP PRO v2.0.0.0, MEDICALIP Co. Ltd.) based on 2D U-NET was used to create liver segmentation masks with liver volume. The original 80 keV images were used as the ground truth. We used the paired t-test to compare the segmentation performance in the Dice similarity coefficient (DSC) and difference ratio of the liver volume relative to the ground truth volume before and after image standardization. The concordance correlation coefficient (CCC) was used to assess the agreement between the segmented liver volume and ground-truth volume. RESULTS The original CT images showed variable and poor segmentation performances. The standardized images achieved significantly higher DSCs for liver segmentation than the original images (DSC [original, 5.40%-91.27%] vs. [standardized, 93.16%-96.74%], all P < 0.001). The difference ratio of liver volume also decreased significantly after image conversion (original, 9.84%-91.37% vs. standardized, 1.99%-4.41%). In all protocols, CCCs improved after image conversion (original, -0.006-0.964 vs. standardized, 0.990-0.998). CONCLUSION Deep learning-based CT image standardization can improve the performance of automated hepatic segmentation using CT images reconstructed using various methods. Deep learning-based CT image conversion may have the potential to improve the generalizability of the segmentation network.
Collapse
Affiliation(s)
- Seul Bi Lee
- Department of Radiology, Seoul National University Hospital, Seoul, Korea.,Department of Radiology, Seoul National University College of Medicine, Seoul, Korea
| | - Youngtaek Hong
- CONNECT-AI R&D Center, Yonsei University College of Medicine, Seoul, Korea
| | - Yeon Jin Cho
- Department of Radiology, Seoul National University Hospital, Seoul, Korea.,Department of Radiology, Seoul National University College of Medicine, Seoul, Korea.
| | - Dawun Jeong
- CONNECT-AI R&D Center, Yonsei University College of Medicine, Seoul, Korea.,Brain Korea, 21 PLUS Project for Medical Science, Yonsei University, Seoul, Korea
| | - Jina Lee
- CONNECT-AI R&D Center, Yonsei University College of Medicine, Seoul, Korea.,Brain Korea, 21 PLUS Project for Medical Science, Yonsei University, Seoul, Korea
| | - Soon Ho Yoon
- Department of Radiology, Seoul National University Hospital, Seoul, Korea.,Department of Radiology, Seoul National University College of Medicine, Seoul, Korea.,MEDICALIP Co. Ltd., Seoul, Korea
| | - Seunghyun Lee
- Department of Radiology, Seoul National University Hospital, Seoul, Korea.,Department of Radiology, Seoul National University College of Medicine, Seoul, Korea
| | - Young Hun Choi
- Department of Radiology, Seoul National University Hospital, Seoul, Korea.,Department of Radiology, Seoul National University College of Medicine, Seoul, Korea
| | - Jung-Eun Cheon
- Department of Radiology, Seoul National University Hospital, Seoul, Korea.,Department of Radiology, Seoul National University College of Medicine, Seoul, Korea.,Institute of Radiation Medicine, Seoul National University Medical Research Center, Seoul, Korea
| |
Collapse
|
37
|
Wang C, Yu J, Zhong J, Han S, Qi Y, Fang B, Li X. Prior knowledge-based precise diagnosis of blend sign from head computed tomography. Front Neurosci 2023; 17:1112355. [PMID: 36845414 PMCID: PMC9950259 DOI: 10.3389/fnins.2023.1112355] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/30/2022] [Accepted: 01/17/2023] [Indexed: 02/12/2023] Open
Abstract
Introduction Automated diagnosis of intracranial hemorrhage on head computed tomography (CT) plays a decisive role in clinical management. This paper presents a prior knowledge-based precise diagnosis of blend sign network from head CT scans. Method We employ the object detection task as an auxiliary task in addition to the classification task, which could incorporate the hemorrhage location as prior knowledge into the detection framework. The auxiliary task could help the model pay more attention to the regions with hemorrhage, which is beneficial for distinguishing the blend sign. Furthermore, we propose a self-knowledge distillation strategy to deal with inaccuracy annotations. Results In the experiment, we retrospectively collected 1749 anonymous non-contrast head CT scans from the First Affiliated Hospital of China Medical University. The dataset contains three categories: no intracranial hemorrhage (non-ICH), normal intracranial hemorrhage (normal ICH), and blend sign. The experimental results demonstrate that our method performs better than other methods. Discussion Our method has the potential to assist less-experienced head CT interpreters, reduce radiologists' workload, and improve efficiency in natural clinical settings.
Collapse
Affiliation(s)
- Chen Wang
- College of Computer Science, Chongqing University, Chongqing, China
| | - Jiefu Yu
- Department of Neurosurgery, The First Hospital of China Medical University, Shenyang, China
| | - Jiang Zhong
- College of Computer Science, Chongqing University, Chongqing, China,*Correspondence: Jiang Zhong ✉
| | - Shuai Han
- Department of Neurosurgery, Shengjing Hospital of China Medical University, Shenyang, China,Shuai Han ✉
| | - Yafei Qi
- College of Computer Science and Engineering, Central South University, Changsha, China
| | - Bin Fang
- College of Computer Science, Chongqing University, Chongqing, China
| | - Xue Li
- School of Information Technology and Electrical Engineering, The University of Queensland, Brisbane, QLD, Australia
| |
Collapse
|
38
|
Intracranial Hemorrhage Detection Using Parallel Deep Convolutional Models and Boosting Mechanism. Diagnostics (Basel) 2023; 13:diagnostics13040652. [PMID: 36832137 PMCID: PMC9955715 DOI: 10.3390/diagnostics13040652] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/21/2022] [Revised: 01/31/2023] [Accepted: 02/02/2023] [Indexed: 02/12/2023] Open
Abstract
Intracranial hemorrhage (ICH) can lead to death or disability, which requires immediate action from radiologists. Due to the heavy workload, less experienced staff, and the complexity of subtle hemorrhages, a more intelligent and automated system is necessary to detect ICH. In literature, many artificial-intelligence-based methods are proposed. However, they are less accurate for ICH detection and subtype classification. Therefore, in this paper, we present a new methodology to improve the detection and subtype classification of ICH based on two parallel paths and a boosting technique. The first path employs the architecture of ResNet101-V2 to extract potential features from windowed slices, whereas Inception-V4 captures significant spatial information in the second path. Afterwards, the detection and subtype classification of ICH is performed by the light gradient boosting machine (LGBM) using the outputs of ResNet101-V2 and Inception-V4. Thus, the combined solution, known as ResNet101-V2, Inception-V4, and LGBM (Res-Inc-LGBM), is trained and tested over the brain computed tomography (CT) scans of CQ500 and Radiological Society of North America (RSNA) datasets. The experimental results state that the proposed solution efficiently obtains 97.7% accuracy, 96.5% sensitivity, and 97.4% F1 score using the RSNA dataset. Moreover, the proposed Res-Inc-LGBM outperforms the standard benchmarks for the detection and subtype classification of ICH regarding the accuracy, sensitivity, and F1 score. The results prove the significance of the proposed solution for its real-time application.
Collapse
|
39
|
Deep Learning Applied to Intracranial Hemorrhage Detection. J Imaging 2023; 9:jimaging9020037. [PMID: 36826956 PMCID: PMC9963867 DOI: 10.3390/jimaging9020037] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/17/2022] [Revised: 01/22/2023] [Accepted: 01/26/2023] [Indexed: 02/10/2023] Open
Abstract
Intracranial hemorrhage is a serious medical problem that requires rapid and often intensive medical care. Identifying the location and type of any hemorrhage present is a critical step in the treatment of the patient. Detection of, and diagnosis of, a hemorrhage that requires an urgent procedure is a difficult and time-consuming process for human experts. In this paper, we propose methods based on EfficientDet's deep-learning technology that can be applied to the diagnosis of hemorrhages at a patient level and which could, thus, become a decision-support system. Our proposal is two-fold. On the one hand, the proposed technique classifies slices of computed tomography scans for the presence of hemorrhage or its lack of, and evaluates whether the patient is positive in terms of hemorrhage, and achieving, in this regard, 92.7% accuracy and 0.978 ROC AUC. On the other hand, our methodology provides visual explanations of the chosen classification using the Grad-CAM methodology.
Collapse
|
40
|
Detection of Critical Spinal Epidural Lesions on CT Using Machine Learning. Spine (Phila Pa 1976) 2023; 48:1-7. [PMID: 35905328 DOI: 10.1097/brs.0000000000004438] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 05/27/2022] [Accepted: 07/12/2022] [Indexed: 02/01/2023]
Abstract
BACKGROUND Critical spinal epidural pathologies can cause paralysis or death if untreated. Although magnetic resonance imaging is the preferred modality for visualizing these pathologies, computed tomography (CT) occurs far more commonly than magnetic resonance imaging in the clinical setting. OBJECTIVE A machine learning model was developed to screen for critical epidural lesions on CT images at a large-scale teleradiology practice. This model has utility for both worklist prioritization of emergent studies and identifying missed findings. MATERIALS AND METHODS There were 153 studies with epidural lesions available for training. These lesions were segmented and used to train a machine learning model. A test data set was also created using previously missed epidural lesions. The trained model was then integrated into a teleradiology workflow for 90 days. Studies were sent to secondary manual review if the model detected an epidural lesion but none was mentioned in the clinical report. RESULTS The model correctly identified 50.0% of epidural lesions in the test data set with 99.0% specificity. For prospective data, the model correctly prioritized 66.7% of the 18 epidural lesions diagnosed on the initial read with 98.9% specificity. There were 2.0 studies flagged for potential missed findings per day, and 17 missed epidural lesions were found during a 90-day time period. These results suggest almost half of critical spinal epidural lesions visible on CT imaging are being missed on initial diagnosis. CONCLUSION A machine learning model for identifying spinal epidural hematomas and abscesses on CT can be implemented in a clinical workflow.
Collapse
|
41
|
Smorchkova AK, Khoruzhaya AN, Kremneva EI, Petryaikin AV. [Machine learning technologies in CT-based diagnostics and classification of intracranial hemorrhages]. ZHURNAL VOPROSY NEIROKHIRURGII IMENI N. N. BURDENKO 2023; 87:85-91. [PMID: 37011333 DOI: 10.17116/neiro20238702185] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 04/05/2023]
Abstract
This review discusses pooled experience of creation, implementation and effectiveness of machine learning technologies in CT-based diagnosis of intracranial hemorrhages. The authors analyzed 21 original articles between 2015 and 2022 using the following keywords: «intracranial hemorrhage», «machine learning», «deep learning», «artificial intelligence». The review contains general data on basic concepts of machine learning and also considers in more detail such aspects as technical characteristics of data sets used for creation of AI algorithms for certain type of clinical task, their possible impact on effectiveness and clinical experience.
Collapse
Affiliation(s)
- A K Smorchkova
- Moscow Research Practical Clinical Center for Diagnostics and Telemedicine Technologies, Moscow, Russia
| | - A N Khoruzhaya
- Moscow Research Practical Clinical Center for Diagnostics and Telemedicine Technologies, Moscow, Russia
| | - E I Kremneva
- Moscow Research Practical Clinical Center for Diagnostics and Telemedicine Technologies, Moscow, Russia
- Neurology Research Center, Moscow, Russia
| | - A V Petryaikin
- Moscow Research Practical Clinical Center for Diagnostics and Telemedicine Technologies, Moscow, Russia
| |
Collapse
|
42
|
Wang S, Chen F, Zhang M, Zhao X, Wen L, Wu W, Wu S, Li Z, Tian J, Liu T. Predicting prognosis of primary pontine hemorrhage using CT image and deep learning. Neuroimage Clin 2022; 36:103257. [PMID: 36510407 PMCID: PMC9668666 DOI: 10.1016/j.nicl.2022.103257] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/30/2022] [Revised: 10/22/2022] [Accepted: 11/01/2022] [Indexed: 11/06/2022]
Abstract
Prognosis of primary pontine hemorrhage (PPH) is important for treatment planning and patient management. However, only few clinical factors were reported to have prognostic value to PPH. Here, we propose a deep learning (DL) model that mines high-dimensional prognostic information from computed tomography (CT) images and combines clinical factors for predicting individualized prognosis of PPH. We proposed a multi-task DL model to learn high-dimensional CT features of hematoma and perihematomal areas for predicting the risk of 30-day mortality, 90-day mortality and 90-day functional outcome of PPH simultaneously. We further explored the combination of the DL model and clinical factors by building a combined model. All the models were trained in a training cohort (n = 219) and tested in an independent testing cohort (n = 35). The DL model achieved area under the curve (AUC) of 0.886, 0.886, and 0.759 in predicting 30-day mortality, 90-day mortality and 90-day functional outcome of PPH in the independent testing cohort, which improved over the previously reported new PPH score and the clinical model. When combining the DL model and clinical factors, the combined model achieved improved performance (AUC = 0.920, 0.941, and 0.894), indicating that DL model mines CT information that complements clinical factors. Through DL visualization technique, we found that the internal structure of hematoma and its expansion to perihematomal regions are important for predicting the prognosis of PPH. This DL model provides an easy-to-use way for predicting individualized prognosis of PPH by mining high-dimensional information from CT images, and showed improvement over clinical factors and present methods.
Collapse
Affiliation(s)
- Shuo Wang
- Beijing Advanced Innovation Center for Big Data-Based Precision Medicine, School of Engineering Medicine, Beihang University, Beijing, China,Key Laboratory of Big Data-Based Precision Medicine, Ministry of Industry and Information Technology, People’s Republic of China, Beijing, China
| | - Feng Chen
- Department of Radiology, Hainan General Hospital (Hainan Affiliated Hospital of Hainan Medical University), Haikou, China,Corresponding authors at: Beijing Advanced Innovation Center for Big Data-Based Precision Medicine, School of Engineering Medicine, Beihang University (J. Tian); Department of Neurology, Hainan General Hospital (Hannan Affiliated Hospital of Hainan Medical University) (T. Liu); and Department of Radiology, Hainan General Hospital (Hannan Affiliated Hospital of Hainan Medical University) (F. Chen).
| | - Mingyu Zhang
- Beijing Advanced Innovation Center for Big Data-Based Precision Medicine, School of Engineering Medicine, Beihang University, Beijing, China,Key Laboratory of Big Data-Based Precision Medicine, Ministry of Industry and Information Technology, People’s Republic of China, Beijing, China
| | - Xiaolin Zhao
- Department of Neurology, Nanfang Hospital, Southern Medical University, Guangzhou, China
| | - Linghua Wen
- Department of Radiology, Hainan General Hospital (Hainan Affiliated Hospital of Hainan Medical University), Haikou, China,Department of Radiology, Yueyang Central Hospital, Yueyang, China
| | - Wenyuan Wu
- Department of Radiology, Hainan General Hospital (Hainan Affiliated Hospital of Hainan Medical University), Haikou, China
| | - Shina Wu
- Department of Neurology, Hainan General Hospital (Hainan Affiliated Hospital of Hainan Medical University), Haikou, China
| | - Zhe Li
- School of Cyberspace Science and Technology, University of Science and Technology of China, Hefei, China
| | - Jie Tian
- Beijing Advanced Innovation Center for Big Data-Based Precision Medicine, School of Engineering Medicine, Beihang University, Beijing, China,Key Laboratory of Big Data-Based Precision Medicine, Ministry of Industry and Information Technology, People’s Republic of China, Beijing, China,Corresponding authors at: Beijing Advanced Innovation Center for Big Data-Based Precision Medicine, School of Engineering Medicine, Beihang University (J. Tian); Department of Neurology, Hainan General Hospital (Hannan Affiliated Hospital of Hainan Medical University) (T. Liu); and Department of Radiology, Hainan General Hospital (Hannan Affiliated Hospital of Hainan Medical University) (F. Chen).
| | - Tao Liu
- Department of Neurology, Hainan General Hospital (Hainan Affiliated Hospital of Hainan Medical University), Haikou, China,Corresponding authors at: Beijing Advanced Innovation Center for Big Data-Based Precision Medicine, School of Engineering Medicine, Beihang University (J. Tian); Department of Neurology, Hainan General Hospital (Hannan Affiliated Hospital of Hainan Medical University) (T. Liu); and Department of Radiology, Hainan General Hospital (Hannan Affiliated Hospital of Hainan Medical University) (F. Chen).
| |
Collapse
|
43
|
Ghesu FC, Georgescu B, Mansoor A, Yoo Y, Neumann D, Patel P, Vishwanath RS, Balter JM, Cao Y, Grbic S, Comaniciu D. Contrastive self-supervised learning from 100 million medical images with optional supervision. J Med Imaging (Bellingham) 2022; 9:064503. [PMID: 36466078 PMCID: PMC9710476 DOI: 10.1117/1.jmi.9.6.064503] [Citation(s) in RCA: 12] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/25/2022] [Accepted: 11/14/2022] [Indexed: 12/05/2022] Open
Abstract
Purpose Building accurate and robust artificial intelligence systems for medical image assessment requires the creation of large sets of annotated training examples. However, constructing such datasets is very costly due to the complex nature of annotation tasks, which often require expert knowledge (e.g., a radiologist). To counter this limitation, we propose a method to learn from medical images at scale in a self-supervised way. Approach Our approach, based on contrastive learning and online feature clustering, leverages training datasets of over 100,000,000 medical images of various modalities, including radiography, computed tomography (CT), magnetic resonance (MR) imaging, and ultrasonography (US). We propose to use the learned features to guide model training in supervised and hybrid self-supervised/supervised regime on various downstream tasks. Results We highlight a number of advantages of this strategy on challenging image assessment problems in radiography, CT, and MR: (1) significant increase in accuracy compared to the state-of-the-art (e.g., area under the curve boost of 3% to 7% for detection of abnormalities from chest radiography scans and hemorrhage detection on brain CT); (2) acceleration of model convergence during training by up to 85% compared with using no pretraining (e.g., 83% when training a model for detection of brain metastases in MR scans); and (3) increase in robustness to various image augmentations, such as intensity variations, rotations or scaling reflective of data variation seen in the field. Conclusions The proposed approach enables large gains in accuracy and robustness on challenging image assessment problems. The improvement is significant compared with other state-of-the-art approaches trained on medical or vision images (e.g., ImageNet).
Collapse
Affiliation(s)
- Florin C. Ghesu
- Siemens Healthineers, Digital Technology and Innovation, Princeton, New Jersey, United States
| | - Bogdan Georgescu
- Siemens Healthineers, Digital Technology and Innovation, Princeton, New Jersey, United States
| | - Awais Mansoor
- Siemens Healthineers, Digital Technology and Innovation, Princeton, New Jersey, United States
| | - Youngjin Yoo
- Siemens Healthineers, Digital Technology and Innovation, Princeton, New Jersey, United States
| | - Dominik Neumann
- Siemens Healthineers, Digital Technology and Innovation, Erlangen, Germany
| | - Pragneshkumar Patel
- Siemens Healthineers, Digital Technology and Innovation, Princeton, New Jersey, United States
| | | | - James M. Balter
- University of Michigan, Department of Radiation Oncology, Ann Arbor, Michigan, United States
| | - Yue Cao
- University of Michigan, Department of Radiation Oncology, Ann Arbor, Michigan, United States
| | - Sasa Grbic
- Siemens Healthineers, Digital Technology and Innovation, Princeton, New Jersey, United States
| | - Dorin Comaniciu
- Siemens Healthineers, Digital Technology and Innovation, Princeton, New Jersey, United States
| |
Collapse
|
44
|
Maas AIR, Menon DK, Manley GT, Abrams M, Åkerlund C, Andelic N, Aries M, Bashford T, Bell MJ, Bodien YG, Brett BL, Büki A, Chesnut RM, Citerio G, Clark D, Clasby B, Cooper DJ, Czeiter E, Czosnyka M, Dams-O’Connor K, De Keyser V, Diaz-Arrastia R, Ercole A, van Essen TA, Falvey É, Ferguson AR, Figaji A, Fitzgerald M, Foreman B, Gantner D, Gao G, Giacino J, Gravesteijn B, Guiza F, Gupta D, Gurnell M, Haagsma JA, Hammond FM, Hawryluk G, Hutchinson P, van der Jagt M, Jain S, Jain S, Jiang JY, Kent H, Kolias A, Kompanje EJO, Lecky F, Lingsma HF, Maegele M, Majdan M, Markowitz A, McCrea M, Meyfroidt G, Mikolić A, Mondello S, Mukherjee P, Nelson D, Nelson LD, Newcombe V, Okonkwo D, Orešič M, Peul W, Pisică D, Polinder S, Ponsford J, Puybasset L, Raj R, Robba C, Røe C, Rosand J, Schueler P, Sharp DJ, Smielewski P, Stein MB, von Steinbüchel N, Stewart W, Steyerberg EW, Stocchetti N, Temkin N, Tenovuo O, Theadom A, Thomas I, Espin AT, Turgeon AF, Unterberg A, Van Praag D, van Veen E, Verheyden J, Vyvere TV, Wang KKW, Wiegers EJA, Williams WH, Wilson L, Wisniewski SR, Younsi A, Yue JK, Yuh EL, Zeiler FA, Zeldovich M, Zemek R. Traumatic brain injury: progress and challenges in prevention, clinical care, and research. Lancet Neurol 2022; 21:1004-1060. [PMID: 36183712 PMCID: PMC10427240 DOI: 10.1016/s1474-4422(22)00309-x] [Citation(s) in RCA: 255] [Impact Index Per Article: 127.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/28/2022] [Accepted: 07/22/2022] [Indexed: 02/06/2023]
Abstract
Traumatic brain injury (TBI) has the highest incidence of all common neurological disorders, and poses a substantial public health burden. TBI is increasingly documented not only as an acute condition but also as a chronic disease with long-term consequences, including an increased risk of late-onset neurodegeneration. The first Lancet Neurology Commission on TBI, published in 2017, called for a concerted effort to tackle the global health problem posed by TBI. Since then, funding agencies have supported research both in high-income countries (HICs) and in low-income and middle-income countries (LMICs). In November 2020, the World Health Assembly, the decision-making body of WHO, passed resolution WHA73.10 for global actions on epilepsy and other neurological disorders, and WHO launched the Decade for Action on Road Safety plan in 2021. New knowledge has been generated by large observational studies, including those conducted under the umbrella of the International Traumatic Brain Injury Research (InTBIR) initiative, established as a collaboration of funding agencies in 2011. InTBIR has also provided a huge stimulus to collaborative research in TBI and has facilitated participation of global partners. The return on investment has been high, but many needs of patients with TBI remain unaddressed. This update to the 2017 Commission presents advances and discusses persisting and new challenges in prevention, clinical care, and research. In LMICs, the occurrence of TBI is driven by road traffic incidents, often involving vulnerable road users such as motorcyclists and pedestrians. In HICs, most TBI is caused by falls, particularly in older people (aged ≥65 years), who often have comorbidities. Risk factors such as frailty and alcohol misuse provide opportunities for targeted prevention actions. Little evidence exists to inform treatment of older patients, who have been commonly excluded from past clinical trials—consequently, appropriate evidence is urgently required. Although increasing age is associated with worse outcomes from TBI, age should not dictate limitations in therapy. However, patients injured by low-energy falls (who are mostly older people) are about 50% less likely to receive critical care or emergency interventions, compared with those injured by high-energy mechanisms, such as road traffic incidents. Mild TBI, defined as a Glasgow Coma sum score of 13–15, comprises most of the TBI cases (over 90%) presenting to hospital. Around 50% of adult patients with mild TBI presenting to hospital do not recover to pre-TBI levels of health by 6 months after their injury. Fewer than 10% of patients discharged after presenting to an emergency department for TBI in Europe currently receive follow-up. Structured follow-up after mild TBI should be considered good practice, and urgent research is needed to identify which patients with mild TBI are at risk for incomplete recovery. The selection of patients for CT is an important triage decision in mild TBI since it allows early identification of lesions that can trigger hospital admission or life-saving surgery. Current decision making for deciding on CT is inefficient, with 90–95% of scanned patients showing no intracranial injury but being subjected to radiation risks. InTBIR studies have shown that measurement of blood-based biomarkers adds value to previously proposed clinical decision rules, holding the potential to improve efficiency while reducing radiation exposure. Increased concentrations of biomarkers in the blood of patients with a normal presentation CT scan suggest structural brain damage, which is seen on MR scanning in up to 30% of patients with mild TBI. Advanced MRI, including diffusion tensor imaging and volumetric analyses, can identify additional injuries not detectable by visual inspection of standard clinical MR images. Thus, the absence of CT abnormalities does not exclude structural damage—an observation relevant to litigation procedures, to management of mild TBI, and when CT scans are insufficient to explain the severity of the clinical condition. Although blood-based protein biomarkers have been shown to have important roles in the evaluation of TBI, most available assays are for research use only. To date, there is only one vendor of such assays with regulatory clearance in Europe and the USA with an indication to rule out the need for CT imaging for patients with suspected TBI. Regulatory clearance is provided for a combination of biomarkers, although evidence is accumulating that a single biomarker can perform as well as a combination. Additional biomarkers and more clinical-use platforms are on the horizon, but cross-platform harmonisation of results is needed. Health-care efficiency would benefit from diversity in providers. In the intensive care setting, automated analysis of blood pressure and intracranial pressure with calculation of derived parameters can help individualise management of TBI. Interest in the identification of subgroups of patients who might benefit more from some specific therapeutic approaches than others represents a welcome shift towards precision medicine. Comparative-effectiveness research to identify best practice has delivered on expectations for providing evidence in support of best practices, both in adult and paediatric patients with TBI. Progress has also been made in improving outcome assessment after TBI. Key instruments have been translated into up to 20 languages and linguistically validated, and are now internationally available for clinical and research use. TBI affects multiple domains of functioning, and outcomes are affected by personal characteristics and life-course events, consistent with a multifactorial bio-psycho-socio-ecological model of TBI, as presented in the US National Academies of Sciences, Engineering, and Medicine (NASEM) 2022 report. Multidimensional assessment is desirable and might be best based on measurement of global functional impairment. More work is required to develop and implement recommendations for multidimensional assessment. Prediction of outcome is relevant to patients and their families, and can facilitate the benchmarking of quality of care. InTBIR studies have identified new building blocks (eg, blood biomarkers and quantitative CT analysis) to refine existing prognostic models. Further improvement in prognostication could come from MRI, genetics, and the integration of dynamic changes in patient status after presentation. Neurotrauma researchers traditionally seek translation of their research findings through publications, clinical guidelines, and industry collaborations. However, to effectively impact clinical care and outcome, interactions are also needed with research funders, regulators, and policy makers, and partnership with patient organisations. Such interactions are increasingly taking place, with exemplars including interactions with the All Party Parliamentary Group on Acquired Brain Injury in the UK, the production of the NASEM report in the USA, and interactions with the US Food and Drug Administration. More interactions should be encouraged, and future discussions with regulators should include debates around consent from patients with acute mental incapacity and data sharing. Data sharing is strongly advocated by funding agencies. From January 2023, the US National Institutes of Health will require upload of research data into public repositories, but the EU requires data controllers to safeguard data security and privacy regulation. The tension between open data-sharing and adherence to privacy regulation could be resolved by cross-dataset analyses on federated platforms, with the data remaining at their original safe location. Tools already exist for conventional statistical analyses on federated platforms, however federated machine learning requires further development. Support for further development of federated platforms, and neuroinformatics more generally, should be a priority. This update to the 2017 Commission presents new insights and challenges across a range of topics around TBI: epidemiology and prevention (section 1 ); system of care (section 2 ); clinical management (section 3 ); characterisation of TBI (section 4 ); outcome assessment (section 5 ); prognosis (Section 6 ); and new directions for acquiring and implementing evidence (section 7 ). Table 1 summarises key messages from this Commission and proposes recommendations for the way forward to advance research and clinical management of TBI.
Collapse
Affiliation(s)
- Andrew I R Maas
- Department of Neurosurgery, Antwerp University Hospital and University of Antwerp, Edegem, Belgium
| | - David K Menon
- Division of Anaesthesia, University of Cambridge, Addenbrooke’s Hospital, Cambridge, UK
| | - Geoffrey T Manley
- Department of Neurological Surgery, University of California, San Francisco, CA, USA
| | - Mathew Abrams
- International Neuroinformatics Coordinating Facility, Karolinska Institutet, Stockholm, Sweden
| | - Cecilia Åkerlund
- Department of Physiology and Pharmacology, Section of Perioperative Medicine and Intensive Care, Karolinska Institutet, Stockholm, Sweden
| | - Nada Andelic
- Division of Clinical Neuroscience, Department of Physical Medicine and Rehabilitation, Oslo University Hospital and University of Oslo, Oslo, Norway
| | - Marcel Aries
- Department of Intensive Care, Maastricht UMC, Maastricht, Netherlands
| | - Tom Bashford
- Division of Anaesthesia, University of Cambridge, Addenbrooke’s Hospital, Cambridge, UK
| | - Michael J Bell
- Critical Care Medicine, Neurological Surgery and Pediatrics, University of Pittsburgh School of Medicine, Pittsburgh, PA, USA
| | - Yelena G Bodien
- Department of Neurology and Department of Physical Medicine and Rehabilitation, Harvard Medical School, Boston, MA, USA
| | - Benjamin L Brett
- Department of Neurosurgery, Medical College of Wisconsin, Milwaukee, WI, USA
| | - András Büki
- Department of Neurosurgery, Faculty of Medicine and Health Örebro University, Örebro, Sweden
- Department of Neurosurgery, Medical School; ELKH-PTE Clinical Neuroscience MR Research Group; and Neurotrauma Research Group, Janos Szentagothai Research Centre, University of Pecs, Pecs, Hungary
| | - Randall M Chesnut
- Department of Neurological Surgery and Department of Orthopaedics and Sports Medicine, University of Washington, Harborview Medical Center, Seattle, WA, USA
| | - Giuseppe Citerio
- School of Medicine and Surgery, Universita Milano Bicocca, Milan, Italy
- NeuroIntensive Care, San Gerardo Hospital, Azienda Socio Sanitaria Territoriale (ASST) Monza, Monza, Italy
| | - David Clark
- Brain Physics Lab, Division of Neurosurgery, Department of Clinical Neurosciences, University of Cambridge, Addenbrooke’s Hospital, Cambridge, UK
| | - Betony Clasby
- Department of Sociological Studies, University of Sheffield, Sheffield, UK
| | - D Jamie Cooper
- School of Public Health and Preventive Medicine, Monash University and The Alfred Hospital, Melbourne, VIC, Australia
| | - Endre Czeiter
- Department of Neurosurgery, Medical School; ELKH-PTE Clinical Neuroscience MR Research Group; and Neurotrauma Research Group, Janos Szentagothai Research Centre, University of Pecs, Pecs, Hungary
| | - Marek Czosnyka
- Brain Physics Lab, Division of Neurosurgery, Department of Clinical Neurosciences, University of Cambridge, Addenbrooke’s Hospital, Cambridge, UK
| | - Kristen Dams-O’Connor
- Department of Rehabilitation and Human Performance and Department of Neurology, Brain Injury Research Center, Icahn School of Medicine at Mount Sinai, New York, NY, USA
| | - Véronique De Keyser
- Department of Neurosurgery, Antwerp University Hospital and University of Antwerp, Edegem, Belgium
| | - Ramon Diaz-Arrastia
- Department of Neurology and Center for Brain Injury and Repair, University of Pennsylvania Perelman School of Medicine, Philadelphia, PA, USA
| | - Ari Ercole
- Division of Anaesthesia, University of Cambridge, Addenbrooke’s Hospital, Cambridge, UK
| | - Thomas A van Essen
- Department of Neurosurgery, Leiden University Medical Center, Leiden, Netherlands
- Department of Neurosurgery, Medical Center Haaglanden, The Hague, Netherlands
| | - Éanna Falvey
- College of Medicine and Health, University College Cork, Cork, Ireland
| | - Adam R Ferguson
- Brain and Spinal Injury Center, Department of Neurological Surgery, Weill Institute for Neurosciences, University of California San Francisco and San Francisco Veterans Affairs Healthcare System, San Francisco, CA, USA
| | - Anthony Figaji
- Division of Neurosurgery and Neuroscience Institute, University of Cape Town, Cape Town, South Africa
| | - Melinda Fitzgerald
- Curtin Health Innovation Research Institute, Curtin University, Bentley, WA, Australia
- Perron Institute for Neurological and Translational Sciences, Nedlands, WA, Australia
| | - Brandon Foreman
- Department of Neurology and Rehabilitation Medicine, University of Cincinnati Gardner Neuroscience Institute, University of Cincinnati, Cincinnati, OH, USA
| | - Dashiell Gantner
- School of Public Health and Preventive Medicine, Monash University and The Alfred Hospital, Melbourne, VIC, Australia
| | - Guoyi Gao
- Department of Neurosurgery, Shanghai General Hospital, Shanghai Jiaotong University School of Medicine
| | - Joseph Giacino
- Department of Physical Medicine and Rehabilitation, Harvard Medical School and Spaulding Rehabilitation Hospital, Charlestown, MA, USA
| | - Benjamin Gravesteijn
- Department of Public Health, Erasmus MC University Medical Center Rotterdam, Rotterdam, Netherlands
| | - Fabian Guiza
- Department and Laboratory of Intensive Care Medicine, University Hospitals Leuven and KU Leuven, Leuven, Belgium
| | - Deepak Gupta
- Department of Neurosurgery, Neurosciences Centre and JPN Apex Trauma Centre, All India Institute of Medical Sciences, New Delhi, India
| | - Mark Gurnell
- Metabolic Research Laboratories, Institute of Metabolic Science, University of Cambridge, Cambridge, UK
| | - Juanita A Haagsma
- Department of Public Health, Erasmus MC University Medical Center Rotterdam, Rotterdam, Netherlands
| | - Flora M Hammond
- Department of Physical Medicine and Rehabilitation, Indiana University School of Medicine, Rehabilitation Hospital of Indiana, Indianapolis, IN, USA
| | - Gregory Hawryluk
- Section of Neurosurgery, GB1, Health Sciences Centre, University of Manitoba, Winnipeg, MB, Canada
| | - Peter Hutchinson
- Brain Physics Lab, Division of Neurosurgery, Department of Clinical Neurosciences, University of Cambridge, Addenbrooke’s Hospital, Cambridge, UK
| | - Mathieu van der Jagt
- Department of Intensive Care, Erasmus MC University Medical Center Rotterdam, Rotterdam, Netherlands
| | - Sonia Jain
- Biostatistics Research Center, Herbert Wertheim School of Public Health, University of California, San Diego, CA, USA
| | - Swati Jain
- Brain Physics Lab, Division of Neurosurgery, Department of Clinical Neurosciences, University of Cambridge, Addenbrooke’s Hospital, Cambridge, UK
| | - Ji-yao Jiang
- Department of Neurosurgery, Shanghai Renji Hospital, Shanghai Jiaotong University School of Medicine, Shanghai, China
| | - Hope Kent
- Department of Psychology, University of Exeter, Exeter, UK
| | - Angelos Kolias
- Brain Physics Lab, Division of Neurosurgery, Department of Clinical Neurosciences, University of Cambridge, Addenbrooke’s Hospital, Cambridge, UK
| | - Erwin J O Kompanje
- Department of Intensive Care, Erasmus MC University Medical Center Rotterdam, Rotterdam, Netherlands
| | - Fiona Lecky
- Centre for Urgent and Emergency Care Research, Health Services Research Section, School of Health and Related Research, University of Sheffield, Sheffield, UK
| | - Hester F Lingsma
- Department of Public Health, Erasmus MC University Medical Center Rotterdam, Rotterdam, Netherlands
| | - Marc Maegele
- Cologne-Merheim Medical Center, Department of Trauma and Orthopedic Surgery, Witten/Herdecke University, Cologne, Germany
| | - Marek Majdan
- Institute for Global Health and Epidemiology, Department of Public Health, Faculty of Health Sciences and Social Work, Trnava University, Trnava, Slovakia
| | - Amy Markowitz
- Department of Neurological Surgery, University of California, San Francisco, CA, USA
| | - Michael McCrea
- Department of Neurosurgery and Neurology, Medical College of Wisconsin, Milwaukee, WI, USA
| | - Geert Meyfroidt
- Department and Laboratory of Intensive Care Medicine, University Hospitals Leuven and KU Leuven, Leuven, Belgium
| | - Ana Mikolić
- Department of Public Health, Erasmus MC University Medical Center Rotterdam, Rotterdam, Netherlands
| | - Stefania Mondello
- Department of Biomedical and Dental Sciences and Morphofunctional Imaging, University of Messina, Messina, Italy
| | - Pratik Mukherjee
- Department of Radiology and Biomedical Imaging, University of California San Francisco, San Francisco, CA, USA
| | - David Nelson
- Section for Anesthesiology and Intensive Care, Department of Physiology and Pharmacology, Karolinska Institutet, Stockholm, Sweden
| | - Lindsay D Nelson
- Department of Neurosurgery and Neurology, Medical College of Wisconsin, Milwaukee, WI, USA
| | - Virginia Newcombe
- Division of Anaesthesia, University of Cambridge, Addenbrooke’s Hospital, Cambridge, UK
| | - David Okonkwo
- Department of Neurological Surgery, University of Pittsburgh, Pittsburgh, PA, USA
| | - Matej Orešič
- School of Medical Sciences, Örebro University, Örebro, Sweden
| | - Wilco Peul
- Department of Neurosurgery, Leiden University Medical Center, Leiden, Netherlands
| | - Dana Pisică
- Department of Public Health, Erasmus MC University Medical Center Rotterdam, Rotterdam, Netherlands
- Department of Neurosurgery, Erasmus MC University Medical Center Rotterdam, Rotterdam, Netherlands
| | - Suzanne Polinder
- Department of Public Health, Erasmus MC University Medical Center Rotterdam, Rotterdam, Netherlands
| | - Jennie Ponsford
- Monash-Epworth Rehabilitation Research Centre, Turner Institute for Brain and Mental Health, School of Psychological Sciences, Monash University, Melbourne, VIC, Australia
| | - Louis Puybasset
- Department of Anesthesiology and Intensive Care, APHP, Sorbonne Université, Hôpital Pitié-Salpêtrière, Paris, France
| | - Rahul Raj
- Department of Neurosurgery, Helsinki University Hospital and University of Helsinki, Helsinki, Finland
| | - Chiara Robba
- Department of Anaesthesia and Intensive Care, Policlinico San Martino IRCCS for Oncology and Neuroscience, Genova, Italy, and Dipartimento di Scienze Chirurgiche e Diagnostiche, University of Genoa, Italy
| | - Cecilie Røe
- Division of Clinical Neuroscience, Department of Physical Medicine and Rehabilitation, Oslo University Hospital and University of Oslo, Oslo, Norway
| | - Jonathan Rosand
- Center for Genomic Medicine, Massachusetts General Hospital, Boston, MA, USA
| | | | - David J Sharp
- Department of Brain Sciences, Imperial College London, London, UK
| | - Peter Smielewski
- Brain Physics Lab, Division of Neurosurgery, Department of Clinical Neurosciences, University of Cambridge, Addenbrooke’s Hospital, Cambridge, UK
| | - Murray B Stein
- Department of Psychiatry and Department of Family Medicine and Public Health, UCSD School of Medicine, La Jolla, CA, USA
| | - Nicole von Steinbüchel
- Institute of Medical Psychology and Medical Sociology, University Medical Center Goettingen, Goettingen, Germany
| | - William Stewart
- Department of Neuropathology, Queen Elizabeth University Hospital and University of Glasgow, Glasgow, UK
| | - Ewout W Steyerberg
- Department of Biomedical Data Sciences Leiden University Medical Center, Leiden, Netherlands
| | - Nino Stocchetti
- Department of Pathophysiology and Transplantation, Milan University, and Neuroscience ICU, Fondazione IRCCS Ca Granda Ospedale Maggiore Policlinico, Milan, Italy
| | - Nancy Temkin
- Departments of Neurological Surgery, and Biostatistics, University of Washington, Seattle, WA, USA
| | - Olli Tenovuo
- Department of Rehabilitation and Brain Trauma, Turku University Hospital, and Department of Neurology, University of Turku, Turku, Finland
| | - Alice Theadom
- National Institute for Stroke and Applied Neurosciences, Faculty of Health and Environmental Studies, Auckland University of Technology, Auckland, New Zealand
| | - Ilias Thomas
- School of Medical Sciences, Örebro University, Örebro, Sweden
| | - Abel Torres Espin
- Department of Neurological Surgery, University of California, San Francisco, CA, USA
| | - Alexis F Turgeon
- Department of Anesthesiology and Critical Care Medicine, Division of Critical Care Medicine, Université Laval, CHU de Québec-Université Laval Research Center, Québec City, QC, Canada
| | - Andreas Unterberg
- Department of Neurosurgery, Heidelberg University Hospital, Heidelberg, Germany
| | - Dominique Van Praag
- Departments of Clinical Psychology and Neurosurgery, Antwerp University Hospital, and University of Antwerp, Edegem, Belgium
| | - Ernest van Veen
- Department of Public Health, Erasmus MC University Medical Center Rotterdam, Rotterdam, Netherlands
| | | | - Thijs Vande Vyvere
- Department of Radiology, Faculty of Medicine and Health Sciences, Department of Rehabilitation Sciences (MOVANT), Antwerp University Hospital, and University of Antwerp, Edegem, Belgium
| | - Kevin K W Wang
- Department of Psychiatry, University of Florida, Gainesville, FL, USA
| | - Eveline J A Wiegers
- Department of Public Health, Erasmus MC University Medical Center Rotterdam, Rotterdam, Netherlands
| | - W Huw Williams
- Centre for Clinical Neuropsychology Research, Department of Psychology, University of Exeter, Exeter, UK
| | - Lindsay Wilson
- Division of Psychology, University of Stirling, Stirling, UK
| | - Stephen R Wisniewski
- University of Pittsburgh Graduate School of Public Health, Pittsburgh, Pennsylvania, USA
| | - Alexander Younsi
- Department of Neurosurgery, Heidelberg University Hospital, Heidelberg, Germany
| | - John K Yue
- Department of Neurological Surgery, University of California, San Francisco, CA, USA
| | - Esther L Yuh
- Department of Radiology and Biomedical Imaging, University of California San Francisco, San Francisco, CA, USA
| | - Frederick A Zeiler
- Departments of Surgery, Human Anatomy and Cell Science, and Biomedical Engineering, Rady Faculty of Health Sciences and Price Faculty of Engineering, University of Manitoba, Winnipeg, MB, Canada
| | - Marina Zeldovich
- Institute of Medical Psychology and Medical Sociology, University Medical Center Goettingen, Goettingen, Germany
| | - Roger Zemek
- Departments of Pediatrics and Emergency Medicine, University of Ottawa, Children’s Hospital of Eastern Ontario, ON, Canada
| | | |
Collapse
|
45
|
Zhao G, Feng Q, Chen C, Zhou Z, Yu Y. Diagnose Like a Radiologist: Hybrid Neuro-Probabilistic Reasoning for Attribute-Based Medical Image Diagnosis. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2022; 44:7400-7416. [PMID: 34822325 DOI: 10.1109/tpami.2021.3130759] [Citation(s) in RCA: 7] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/13/2023]
Abstract
During clinical practice, radiologists often use attributes, e.g., morphological and appearance characteristics of a lesion, to aid disease diagnosis. Effectively modeling attributes as well as all relationships involving attributes could boost the generalization ability and verifiability of medical image diagnosis algorithms. In this paper, we introduce a hybrid neuro-probabilistic reasoning algorithm for verifiable attribute-based medical image diagnosis. There are two parallel branches in our hybrid algorithm, a Bayesian network branch performing probabilistic causal relationship reasoning and a graph convolutional network branch performing more generic relational modeling and reasoning using a feature representation. Tight coupling between these two branches is achieved via a cross-network attention mechanism and the fusion of their classification results. We have successfully applied our hybrid reasoning algorithm to two challenging medical image diagnosis tasks. On the LIDC-IDRI benchmark dataset for benign-malignant classification of pulmonary nodules in CT images, our method achieves a new state-of-the-art accuracy of 95.36% and an AUC of 96.54%. Our method also achieves a 3.24% accuracy improvement on an in-house chest X-ray image dataset for tuberculosis diagnosis. Our ablation study indicates that our hybrid algorithm achieves a much better generalization performance than a pure neural network architecture under very limited training data.
Collapse
|
46
|
Chen S, Duan J, Wang H, Wang R, Li J, Qi M, Duan Y, Qi S. Automatic detection of stroke lesion from diffusion-weighted imaging via the improved YOLOv5. Comput Biol Med 2022; 150:106120. [PMID: 36179511 DOI: 10.1016/j.compbiomed.2022.106120] [Citation(s) in RCA: 9] [Impact Index Per Article: 4.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/05/2022] [Revised: 08/31/2022] [Accepted: 09/17/2022] [Indexed: 11/30/2022]
Abstract
BACKGROUND AND OBJECTIVE Stroke is the second most deadly disease globally and seriously endangers people's lives and health. The automatic detection of stroke lesions from diffusion-weighted imaging (DWI) can improve the diagnosis. Recently, automatic detection methods based on YOLOv5 have been utilized in medical images. However, most of them barely capture the stroke lesions because of their small size and fuzzy boundaries. METHODS To address this problem, a novel method for tracing the edge of the stroke lesion based on YOLOv5 (TE-YOLOv5) is proposed. Specifically, we constantly update the high-level features of the lesion using an aggregate pool (AP) module. Conversely, we feed the extracted feature into the reverse attention (RA) module to trace the edge relationship promptly. Overall, 1681 DWI images of 319 stroke patients have been collected, and experienced radiologists have marked the lesions. DWI images were randomly split into the training and test set at a ratio of 8:2. TE-YOLOv5 has been compared with the related models, and a detailed ablation analysis has been conducted to clarify the role of the RA and AP modules. RESULTS TE-YOLOv5 outperforms its counterparts and achieves competitive performance with a precision of 81.5%, a recall of 75.8%, and a mAP@0.5 of 80.7% (mean average precision while the intersection over union is 0.5) under the same backbone. At the patient level, the positive finding rate can reach 98.51%, while the confidence is set at 80.0%. After ablating RA, the mAP@0.5 decreases to 79.6%; after ablating RA and AP, the mAP@0.5 decreases to 78.1%. CONCLUSIONS The proposed TE-YOLOv5 can automatically and effectively detect stroke lesions from DWI images, especially for those with an extremely small size and blurred boundaries. AP and RA modules can aggregate multi-layer high-level features and concurrently track the edge relationship of stroke lesions. These detection methods might help radiologists improve stroke diagnosis and have great application potential in clinical practice.
Collapse
Affiliation(s)
- Shannan Chen
- College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, China; Key Lab of Advanced Design and Intelligent Computing, Ministry of Education, Dalian University, Dalian, China.
| | - Jinfeng Duan
- Department of General Surgery, General Hospital of Northern Theater Command, Shenyang, China.
| | - Hong Wang
- Department of Radiology, General Hospital of Northern Theater Command, Shenyang, China.
| | - Rongqiang Wang
- Department of Radiology, General Hospital of Northern Theater Command, Shenyang, China.
| | - Jinze Li
- Department of Radiology, General Hospital of Northern Theater Command, Shenyang, China.
| | - Miao Qi
- Department of Radiology, General Hospital of Northern Theater Command, Shenyang, China.
| | - Yang Duan
- Department of Radiology, General Hospital of Northern Theater Command, Shenyang, China.
| | - Shouliang Qi
- College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, China; Key Laboratory of Intelligent Computing in Medical Image, Ministry of Education, Northeastern University, Shenyang, China.
| |
Collapse
|
47
|
Peng Q, Chen X, Zhang C, Li W, Liu J, Shi T, Wu Y, Feng H, Nian Y, Hu R. Deep learning-based computed tomography image segmentation and volume measurement of intracerebral hemorrhage. Front Neurosci 2022; 16:965680. [PMID: 36263364 PMCID: PMC9575984 DOI: 10.3389/fnins.2022.965680] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/10/2022] [Accepted: 09/06/2022] [Indexed: 11/25/2022] Open
Abstract
The study aims to enhance the accuracy and practicability of CT image segmentation and volume measurement of ICH by using deep learning technology. A dataset including the brain CT images and clinical data of 1,027 patients with spontaneous ICHs treated from January 2010 to December 2020 were retrospectively analyzed, and a deep segmentation network (AttFocusNet) integrating the focus structure and the attention gate (AG) mechanism is proposed to enable automatic, accurate CT image segmentation and volume measurement of ICHs. In internal validation set, experimental results showed that AttFocusNet achieved a Dice coefficient of 0.908, an intersection-over-union (IoU) of 0.874, a sensitivity of 0.913, a positive predictive value (PPV) of 0.957, and a 95% Hausdorff distance (HD95) (mm) of 5.960. The intraclass correlation coefficient (ICC) of the ICH volume measurement between AttFocusNet and the ground truth was 0.997. The average time of per case achieved by AttFocusNet, Coniglobus formula and manual segmentation is 5.6, 47.7, and 170.1 s. In the two external validation sets, AttFocusNet achieved a Dice coefficient of 0.889 and 0.911, respectively, an IoU of 0.800 and 0.836, respectively, a sensitivity of 0.817 and 0.849, respectively, a PPV of 0.976 and 0.981, respectively, and a HD95 of 5.331 and 4.220, respectively. The ICC of the ICH volume measurement between AttFocusNet and the ground truth were 0.939 and 0.956, respectively. The proposed segmentation network AttFocusNet significantly outperforms the Coniglobus formula in terms of ICH segmentation and volume measurement by acquiring measurement results closer to the true ICH volume and significantly reducing the clinical workload.
Collapse
Affiliation(s)
- Qi Peng
- Department of Digital Medicine, School of Biomedical Engineering and Imaging Medicine, Army Medical University, Third Military Medical University, Chongqing, China
| | - Xingcai Chen
- Department of Digital Medicine, School of Biomedical Engineering and Imaging Medicine, Army Medical University, Third Military Medical University, Chongqing, China
| | - Chao Zhang
- Department of Neurosurgery, First Affiliated Hospital,Southwest Hospital, Army Medical University, Third Military Medical University, Chongqing, China
| | - Wenyan Li
- Department of Neurosurgery, First Affiliated Hospital,Southwest Hospital, Army Medical University, Third Military Medical University, Chongqing, China
| | - Jingjing Liu
- Department of Digital Medicine, School of Biomedical Engineering and Imaging Medicine, Army Medical University, Third Military Medical University, Chongqing, China
| | - Tingxin Shi
- School of Basic Medicine, Army Medical University, Third Military Medical University, Chongqing, China
| | - Yi Wu
- Department of Digital Medicine, School of Biomedical Engineering and Imaging Medicine, Army Medical University, Third Military Medical University, Chongqing, China
| | - Hua Feng
- Department of Neurosurgery, First Affiliated Hospital,Southwest Hospital, Army Medical University, Third Military Medical University, Chongqing, China
| | - Yongjian Nian
- Department of Digital Medicine, School of Biomedical Engineering and Imaging Medicine, Army Medical University, Third Military Medical University, Chongqing, China
- *Correspondence: Yongjian Nian,
| | - Rong Hu
- Department of Neurosurgery, First Affiliated Hospital,Southwest Hospital, Army Medical University, Third Military Medical University, Chongqing, China
- Rong Hu,
| |
Collapse
|
48
|
Huang C, Wang J, Wang SH, Zhang YD. Applicable artificial intelligence for brain disease: A survey. Neurocomputing 2022. [DOI: 10.1016/j.neucom.2022.07.005] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/17/2022]
|
49
|
Matsoukas S, Scaggiante J, Schuldt BR, Smith CJ, Chennareddy S, Kalagara R, Majidi S, Bederson JB, Fifi JT, Mocco J, Kellner CP. Accuracy of artificial intelligence for the detection of intracranial hemorrhage and chronic cerebral microbleeds: a systematic review and pooled analysis. LA RADIOLOGIA MEDICA 2022; 127:1106-1123. [PMID: 35962888 DOI: 10.1007/s11547-022-01530-4] [Citation(s) in RCA: 15] [Impact Index Per Article: 7.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 10/20/2021] [Accepted: 07/12/2022] [Indexed: 11/25/2022]
Abstract
BACKGROUND Artificial intelligence (AI)-driven software has been developed and become commercially available within the past few years for the detection of intracranial hemorrhage (ICH) and chronic cerebral microbleeds (CMBs). However, there is currently no systematic review that summarizes all of these tools or provides pooled estimates of their performance. METHODS In this PROSPERO-registered, PRISMA compliant systematic review, we sought to compile and review all MEDLINE and EMBASE published studies that have developed and/or tested AI algorithms for ICH detection on non-contrast CT scans (NCCTs) or MRI scans and CMBs detection on MRI scans. RESULTS In total, 40 studies described AI algorithms for ICH detection in NCCTs/MRIs and 19 for CMBs detection in MRIs. The overall sensitivity, specificity, and accuracy were 92.06%, 93.54%, and 93.46%, respectively, for ICH detection and 91.6%, 93.9%, and 92.7% for CMBs detection. Some of the challenges encountered in the development of these algorithms include the laborious work of creating large, labeled and balanced datasets, the volumetric nature of the imaging examinations, the fine tuning of the algorithms, and the reduction in false positives. CONCLUSIONS Numerous AI-driven software tools have been developed over the last decade. On average, they are characterized by high performance and expert-level accuracy for the diagnosis of ICH and CMBs. As a result, implementing these tools in clinical practice may improve workflow and act as a failsafe for the detection of such lesions. REGISTRATION-URL: https://www.crd.york.ac.uk/prospero/ Unique Identifier: CRD42021246848.
Collapse
Affiliation(s)
- Stavros Matsoukas
- Department of Neurosurgery, Mount Sinai Health System, Annenberg Building, Room 20-86, 1468 Madison Ave, New York, NY, 10029, USA.
| | - Jacopo Scaggiante
- Department of Neurosurgery, Mount Sinai Health System, Annenberg Building, Room 20-86, 1468 Madison Ave, New York, NY, 10029, USA
| | - Braxton R Schuldt
- Department of Neurosurgery, Mount Sinai Health System, Annenberg Building, Room 20-86, 1468 Madison Ave, New York, NY, 10029, USA
| | - Colton J Smith
- Department of Neurosurgery, Mount Sinai Health System, Annenberg Building, Room 20-86, 1468 Madison Ave, New York, NY, 10029, USA
| | - Susmita Chennareddy
- Department of Neurosurgery, Mount Sinai Health System, Annenberg Building, Room 20-86, 1468 Madison Ave, New York, NY, 10029, USA
| | - Roshini Kalagara
- Department of Neurosurgery, Mount Sinai Health System, Annenberg Building, Room 20-86, 1468 Madison Ave, New York, NY, 10029, USA
| | - Shahram Majidi
- Department of Neurosurgery, Mount Sinai Health System, Annenberg Building, Room 20-86, 1468 Madison Ave, New York, NY, 10029, USA
| | - Joshua B Bederson
- Department of Neurosurgery, Mount Sinai Health System, Annenberg Building, Room 20-86, 1468 Madison Ave, New York, NY, 10029, USA
| | - Johanna T Fifi
- Department of Neurosurgery, Mount Sinai Health System, Annenberg Building, Room 20-86, 1468 Madison Ave, New York, NY, 10029, USA
| | - J Mocco
- Department of Neurosurgery, Mount Sinai Health System, Annenberg Building, Room 20-86, 1468 Madison Ave, New York, NY, 10029, USA
| | - Christopher P Kellner
- Department of Neurosurgery, Mount Sinai Health System, Annenberg Building, Room 20-86, 1468 Madison Ave, New York, NY, 10029, USA
| |
Collapse
|
50
|
Zhu S, Gilbert M, Chetty I, Siddiqui F. The 2021 landscape of FDA-approved artificial intelligence/machine learning-enabled medical devices: An analysis of the characteristics and intended use. Int J Med Inform 2022; 165:104828. [PMID: 35780651 DOI: 10.1016/j.ijmedinf.2022.104828] [Citation(s) in RCA: 25] [Impact Index Per Article: 12.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/09/2022] [Revised: 05/23/2022] [Accepted: 06/28/2022] [Indexed: 10/17/2022]
Abstract
BACKGROUND Machine learning (ML), a type of artificial intelligence (AI) technology that uses a data-driven approach for pattern recognition, has been shown to be beneficial for many tasks across healthcare. To characterize the commercial availability of AI/ML applications in the clinic, we performed a detailed analysis of AI/ML-enabled medical devices approved/cleared by the US Food and Drug Administration (FDA) by June 2021. METHODS/MATERIALS The publicly available approval letters by the FDA on 343 AI/ML-enabled medical devices compiled by the agency were reviewed. The characteristics of the devices and the patterns of their intended use were analyzed, and basic descriptive statistical analysis was performed on the aggregated data. RESULTS Most devices were reviewed by radiology (70.3%) and cardiovascular (12.0%) medical specialty panels. The growth of these devices sharply rose since the mid-2010s. Most (95.0%) devices were cleared under the 510(k) premarket notification pathway, and 69.4% were software as a medical device (SaMD). Of the 241 radiology-related devices, the most common applications were for diagnostic assistance (48.5%) and image reconstruction (14.1%). Of the 117 radiology-related devices for diagnostic assistance, 20.5% were developed for breast lesion assessment and 14.5% for cardiac function assessment on echocardiogram. Of the 41 cardiology-related devices, the most common applications were electrocardiography-based arrhythmia detection (46.3%) and hemodynamics & vital signs monitoring (26.8%). CONCLUSION In this study, we characterized the patterns and trends of AI/ML-enabled medical devices approved or cleared by the FDA. To our knowledge, this is the most up-to-date and comprehensive analysis of the landscape as of 2021.
Collapse
Affiliation(s)
- Simeng Zhu
- Department of Radiation Oncology, Henry Ford Cancer Institute, Detroit, MI, USA
| | - Marissa Gilbert
- Department of Radiation Oncology, Henry Ford Cancer Institute, Detroit, MI, USA
| | - Indrin Chetty
- Department of Radiation Oncology, Henry Ford Cancer Institute, Detroit, MI, USA
| | - Farzan Siddiqui
- Department of Radiation Oncology, Henry Ford Cancer Institute, Detroit, MI, USA.
| |
Collapse
|