1
|
Bartolotta TV, Militello C, Prinzi F, Ferraro F, Rundo L, Zarcaro C, Dimarco M, Orlando AAM, Matranga D, Vitabile S. Artificial intelligence-based, semi-automated segmentation for the extraction of ultrasound-derived radiomics features in breast cancer: a prospective multicenter study. LA RADIOLOGIA MEDICA 2024; 129:977-988. [PMID: 38724697 DOI: 10.1007/s11547-024-01826-7] [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: 07/27/2023] [Accepted: 04/29/2024] [Indexed: 07/17/2024]
Abstract
PURPOSE To investigate the feasibility of an artificial intelligence (AI)-based semi-automated segmentation for the extraction of ultrasound (US)-derived radiomics features in the characterization of focal breast lesions (FBLs). MATERIAL AND METHODS Two expert radiologists classified according to US BI-RADS criteria 352 FBLs detected in 352 patients (237 at Center A and 115 at Center B). An AI-based semi-automated segmentation was used to build a machine learning (ML) model on the basis of B-mode US of 237 images (center A) and then validated on an external cohort of B-mode US images of 115 patients (Center B). RESULTS A total of 202 of 352 (57.4%) FBLs were benign, and 150 of 352 (42.6%) were malignant. The AI-based semi-automated segmentation achieved a success rate of 95.7% for one reviewer and 96% for the other, without significant difference (p = 0.839). A total of 15 (4.3%) and 14 (4%) of 352 semi-automated segmentations were not accepted due to posterior acoustic shadowing at B-Mode US and 13 and 10 of them corresponded to malignant lesions, respectively. In the validation cohort, the characterization made by the expert radiologist yielded values of sensitivity, specificity, PPV and NPV of 0.933, 0.9, 0.857, 0.955, respectively. The ML model obtained values of sensitivity, specificity, PPV and NPV of 0.544, 0.6, 0.416, 0.628, respectively. The combined assessment of radiologists and ML model yielded values of sensitivity, specificity, PPV and NPV of 0.756, 0.928, 0.872, 0.855, respectively. CONCLUSION AI-based semi-automated segmentation is feasible, allowing an instantaneous and reproducible extraction of US-derived radiomics features of FBLs. The combination of radiomics and US BI-RADS classification led to a potential decrease of unnecessary biopsy but at the expense of a not negligible increase of potentially missed cancers.
Collapse
Affiliation(s)
- Tommaso Vincenzo Bartolotta
- Department of Biomedicine, Neuroscience and Advanced Diagnostics (BiND), University of Palermo, Palermo, Italy.
| | - Carmelo Militello
- Institute for High-Performance Computing and Networking (ICAR-CNR), Italian National Research Council, Palermo, Italy
| | - Francesco Prinzi
- Department of Biomedicine, Neuroscience and Advanced Diagnostics (BiND), University of Palermo, Palermo, Italy
- Department of Computer Science and Technology, University of Cambridge, Cambridge, UK
| | - Fabiola Ferraro
- Department of Biomedicine, Neuroscience and Advanced Diagnostics (BiND), University of Palermo, Palermo, Italy
| | - Leonardo Rundo
- Department of Information and Electrical Engineering and Applied Mathematics (DIEM), University of Salerno, Fisciano, SA, Italy
| | - Calogero Zarcaro
- Department of Biomedicine, Neuroscience and Advanced Diagnostics (BiND), University of Palermo, Palermo, Italy
| | | | | | - Domenica Matranga
- Department of Health Promotion, Mother and Child Care, Internal Medicine and Medical Specialties (ProMISE), University of Palermo, Palermo, Italy
| | - Salvatore Vitabile
- Department of Biomedicine, Neuroscience and Advanced Diagnostics (BiND), University of Palermo, Palermo, Italy
| |
Collapse
|
2
|
Prinzi F, Orlando A, Gaglio S, Vitabile S. Interpretable Radiomic Signature for Breast Microcalcification Detection and Classification. JOURNAL OF IMAGING INFORMATICS IN MEDICINE 2024; 37:1038-1053. [PMID: 38351223 PMCID: PMC11169144 DOI: 10.1007/s10278-024-01012-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/28/2023] [Revised: 11/20/2023] [Accepted: 12/05/2023] [Indexed: 06/13/2024]
Abstract
Breast microcalcifications are observed in 80% of mammograms, and a notable proportion can lead to invasive tumors. However, diagnosing microcalcifications is a highly complicated and error-prone process due to their diverse sizes, shapes, and subtle variations. In this study, we propose a radiomic signature that effectively differentiates between healthy tissue, benign microcalcifications, and malignant microcalcifications. Radiomic features were extracted from a proprietary dataset, composed of 380 healthy tissue, 136 benign, and 242 malignant microcalcifications ROIs. Subsequently, two distinct signatures were selected to differentiate between healthy tissue and microcalcifications (detection task) and between benign and malignant microcalcifications (classification task). Machine learning models, namely Support Vector Machine, Random Forest, and XGBoost, were employed as classifiers. The shared signature selected for both tasks was then used to train a multi-class model capable of simultaneously classifying healthy, benign, and malignant ROIs. A significant overlap was discovered between the detection and classification signatures. The performance of the models was highly promising, with XGBoost exhibiting an AUC-ROC of 0.830, 0.856, and 0.876 for healthy, benign, and malignant microcalcifications classification, respectively. The intrinsic interpretability of radiomic features, and the use of the Mean Score Decrease method for model introspection, enabled models' clinical validation. In fact, the most important features, namely GLCM Contrast, FO Minimum and FO Entropy, were compared and found important in other studies on breast cancer.
Collapse
Affiliation(s)
- Francesco Prinzi
- Department of Biomedicine, Neuroscience and Advanced Diagnostics (BiND), University of Palermo, Palermo, Italy.
- Department of Computer Science and Technology, University of Cambridge, CB2 1TN, Cambridge, United Kingdom.
| | - Alessia Orlando
- Section of Radiology - Department of Biomedicine, Neuroscience and Advanced Diagnostics (BiND), University Hospital "Paolo Giaccone", Palermo, Italy
| | - Salvatore Gaglio
- Department of Engineering, University of Palermo, Palermo, Italy
- Institute for High-Performance Computing and Networking, National Research Council (ICAR-CNR), Palermo, Italy
| | - Salvatore Vitabile
- Department of Biomedicine, Neuroscience and Advanced Diagnostics (BiND), University of Palermo, Palermo, Italy
| |
Collapse
|
3
|
Maiti S, Nayak S, Hebbar KD, Pendem S. Differentiation of invasive ductal and lobular carcinoma of the breast using MRI radiomic features: a pilot study. F1000Res 2024; 13:91. [PMID: 38571894 PMCID: PMC10988200 DOI: 10.12688/f1000research.146052.2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Accepted: 04/03/2024] [Indexed: 04/05/2024] Open
Abstract
Background Breast cancer (BC) is one of the main causes of cancer-related mortality among women. For clinical management to help patients survive longer and spend less time on treatment, early and precise cancer identification and differentiation of breast lesions are crucial. To investigate the accuracy of radiomic features (RF) extracted from dynamic contrast-enhanced Magnetic Resonance Imaging (DCE MRI) for differentiating invasive ductal carcinoma (IDC) from invasive lobular carcinoma (ILC). Methods This is a retrospective study. The IDC of 30 and ILC of 28 patients from Dukes breast cancer MRI data set of The Cancer Imaging Archive (TCIA), were included. The RF categories such as shape based, Gray level dependence matrix (GLDM), Gray level co-occurrence matrix (GLCM), First order, Gray level run length matrix (GLRLM), Gray level size zone matrix (GLSZM), NGTDM (Neighbouring gray tone difference matrix) were extracted from the DCE-MRI sequence using a 3D slicer. The maximum relevance and minimum redundancy (mRMR) was applied using Google Colab for identifying the top fifteen relevant radiomic features. The Mann-Whitney U test was performed to identify significant RF for differentiating IDC and ILC. Receiver Operating Characteristic (ROC) curve analysis was performed to ascertain the accuracy of RF in distinguishing between IDC and ILC. Results Ten DCE MRI-based RFs used in our study showed a significant difference (p <0.001) between IDC and ILC. We noticed that DCE RF, such as Gray level run length matrix (GLRLM) gray level variance (sensitivity (SN) 97.21%, specificity (SP) 96.2%, area under curve (AUC) 0.998), Gray level co-occurrence matrix (GLCM) difference average (SN 95.72%, SP 96.34%, AUC 0.983), GLCM interquartile range (SN 95.24%, SP 97.31%, AUC 0.968), had the strongest ability to differentiate IDC and ILC. Conclusions MRI-based RF derived from DCE sequences can be used in clinical settings to differentiate malignant lesions of the breast, such as IDC and ILC, without requiring intrusive procedures.
Collapse
Affiliation(s)
- Sudeepta Maiti
- Department of Medical Imaging Technology, Manipal College of Health Professions, Manipal Academy of Higher Education, Manipal, Karnataka, 576104, India
| | - Shailesh Nayak
- Department of Medical Imaging Technology, Manipal College of Health Professions, Manipal Academy of Higher Education, Manipal, Karnataka, 576104, India
| | - Karthikeya D Hebbar
- Department of Radio diagnosis and Imaging, Kasturba Medical College, Manipal Academy of Higher Education, Manipal, Karnataka, 576140, India
| | - Saikiran Pendem
- Department of Medical Imaging Technology, Manipal College of Health Professions, Manipal Academy of Higher Education, Manipal, Karnataka, 576104, India
| |
Collapse
|
4
|
Prinzi F, Currieri T, Gaglio S, Vitabile S. Shallow and deep learning classifiers in medical image analysis. Eur Radiol Exp 2024; 8:26. [PMID: 38438821 PMCID: PMC10912073 DOI: 10.1186/s41747-024-00428-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/17/2023] [Accepted: 01/03/2024] [Indexed: 03/06/2024] Open
Abstract
An increasingly strong connection between artificial intelligence and medicine has enabled the development of predictive models capable of supporting physicians' decision-making. Artificial intelligence encompasses much more than machine learning, which nevertheless is its most cited and used sub-branch in the last decade. Since most clinical problems can be modeled through machine learning classifiers, it is essential to discuss their main elements. This review aims to give primary educational insights on the most accessible and widely employed classifiers in radiology field, distinguishing between "shallow" learning (i.e., traditional machine learning) algorithms, including support vector machines, random forest and XGBoost, and "deep" learning architectures including convolutional neural networks and vision transformers. In addition, the paper outlines the key steps for classifiers training and highlights the differences between the most common algorithms and architectures. Although the choice of an algorithm depends on the task and dataset dealing with, general guidelines for classifier selection are proposed in relation to task analysis, dataset size, explainability requirements, and available computing resources. Considering the enormous interest in these innovative models and architectures, the problem of machine learning algorithms interpretability is finally discussed, providing a future perspective on trustworthy artificial intelligence.Relevance statement The growing synergy between artificial intelligence and medicine fosters predictive models aiding physicians. Machine learning classifiers, from shallow learning to deep learning, are offering crucial insights for the development of clinical decision support systems in healthcare. Explainability is a key feature of models that leads systems toward integration into clinical practice. Key points • Training a shallow classifier requires extracting disease-related features from region of interests (e.g., radiomics).• Deep classifiers implement automatic feature extraction and classification.• The classifier selection is based on data and computational resources availability, task, and explanation needs.
Collapse
Affiliation(s)
- Francesco Prinzi
- Department of Biomedicine, Neuroscience and Advanced Diagnostics (BiND), University of Palermo, Palermo, Italy
- Department of Computer Science and Technology, University of Cambridge, Cambridge, CB2 1TN, UK
| | - Tiziana Currieri
- Department of Biomedicine, Neuroscience and Advanced Diagnostics (BiND), University of Palermo, Palermo, Italy
| | - Salvatore Gaglio
- Department of Engineering, University of Palermo, Palermo, Italy
- Institute for High-Performance Computing and Networking, National Research Council (ICAR-CNR), Palermo, Italy
| | - Salvatore Vitabile
- Department of Biomedicine, Neuroscience and Advanced Diagnostics (BiND), University of Palermo, Palermo, Italy.
| |
Collapse
|
5
|
Yao Y, Mou F, Kong J, Liu X. Kinetic Heterogeneity Improves the Specificity of Dynamic Enhanced MRI in Differentiating Benign and Malignant Breast Tumours. Acad Radiol 2024; 31:812-821. [PMID: 37980221 DOI: 10.1016/j.acra.2023.10.006] [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: 06/30/2023] [Revised: 09/27/2023] [Accepted: 10/03/2023] [Indexed: 11/20/2023]
Abstract
RATIONALE AND OBJECTIVES To investigate whether kinetic heterogeneity in dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) improves the specificity of breast cancer (BC) diagnosis. MATERIALS AND METHODS The DCE-MRI data of patients with benign breast tumours and BC from June 2020 to July 2022 were retrospectively evaluated. MATLAB and SPM were used to determine six major kinetic parameters: peak, enhancement volume, heterogeneity, as well as persistent, plateau, and washout proportions. Continuous variables were compared using the Student's t-test or Mann-Whitney U tests, and categorical variables were compared using the chi-square or Fisher's exact tests. Receiver operating characteristic curves were plotted. The intraclass correlation coefficient (ICC) was used to evaluate agreement between the two observers. Multivariate logistic regression analysis was conducted to calculate the odds ratios (ORs) with 95% confidence intervals (CIs) for the association between benign and malignant breast tumours. RESULTS In total, 147 patients (mean age, 47 years old) were included in the study, 76 of whom had BC. Data analysis by the two observers showed good consistency in the peak, enhancement volume, persistent proportion, plateau proportion, washout proportion, and heterogeneity, with ICCs of 0.865, 0.988, 0.906, 0.940, 0.740, and 0.867, respectively (p < 0.001). In the DCE kinetic analysis, differences in all the six kinetic parameters were statistically significant (p < 0.05). The area under the curve for heterogeneity was 0.92 (95% CI:0.88,0.97), and the sensitivity and specificity were 0.895 and 0.845, respectively. Multivariate logistic regression analysis showed that heterogeneity was an independent predictor of BC compared to benign breast tumours (OR=2.020; 95% CI:1.316, 3.100; p = 0.001). CONCLUSION The kinetic heterogeneity of DCE-MRI can effectively distinguish between benign and malignant breast tumours and improve the specificity of BC diagnosis.
Collapse
Affiliation(s)
- Yiming Yao
- Department of Radiology, Chongqing University Three Gorges Hospital, 165 Xincheng Road, Chongqing, Wanzhou 404000, China (Y,Y., F.M., J.K., X.L.)
| | - Fangsheng Mou
- Department of Radiology, Chongqing University Three Gorges Hospital, 165 Xincheng Road, Chongqing, Wanzhou 404000, China (Y,Y., F.M., J.K., X.L.)
| | - Junfeng Kong
- Department of Radiology, Chongqing University Three Gorges Hospital, 165 Xincheng Road, Chongqing, Wanzhou 404000, China (Y,Y., F.M., J.K., X.L.)
| | - Xinghua Liu
- Department of Radiology, Chongqing University Three Gorges Hospital, 165 Xincheng Road, Chongqing, Wanzhou 404000, China (Y,Y., F.M., J.K., X.L.).
| |
Collapse
|
6
|
Taleie H, Hajianfar G, Sabouri M, Parsaee M, Houshmand G, Bitarafan-Rajabi A, Zaidi H, Shiri I. Left Ventricular Myocardial Dysfunction Evaluation in Thalassemia Patients Using Echocardiographic Radiomic Features and Machine Learning Algorithms. J Digit Imaging 2023; 36:2494-2506. [PMID: 37735309 PMCID: PMC10584796 DOI: 10.1007/s10278-023-00891-0] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/27/2023] [Revised: 07/23/2023] [Accepted: 07/25/2023] [Indexed: 09/23/2023] Open
Abstract
Heart failure caused by iron deposits in the myocardium is the primary cause of mortality in beta-thalassemia major patients. Cardiac magnetic resonance imaging (CMRI) T2* is the primary screening technique used to detect myocardial iron overload, but inherently bears some limitations. In this study, we aimed to differentiate beta-thalassemia major patients with myocardial iron overload from those without myocardial iron overload (detected by T2*CMRI) based on radiomic features extracted from echocardiography images and machine learning (ML) in patients with normal left ventricular ejection fraction (LVEF > 55%) in echocardiography. Out of 91 cases, 44 patients with thalassemia major with normal LVEF (> 55%) and T2* ≤ 20 ms and 47 people with LVEF > 55% and T2* > 20 ms as the control group were included in the study. Radiomic features were extracted for each end-systolic (ES) and end-diastolic (ED) image. Then, three feature selection (FS) methods and six different classifiers were used. The models were evaluated using various metrics, including the area under the ROC curve (AUC), accuracy (ACC), sensitivity (SEN), and specificity (SPE). Maximum relevance-minimum redundancy-eXtreme gradient boosting (MRMR-XGB) (AUC = 0.73, ACC = 0.73, SPE = 0.73, SEN = 0.73), ANOVA-MLP (AUC = 0.69, ACC = 0.69, SPE = 0.56, SEN = 0.83), and recursive feature elimination-K-nearest neighbors (RFE-KNN) (AUC = 0.65, ACC = 0.65, SPE = 0.64, SEN = 0.65) were the best models in ED, ES, and ED&ES datasets. Using radiomic features extracted from echocardiographic images and ML, it is feasible to predict cardiac problems caused by iron overload.
Collapse
Affiliation(s)
- Haniyeh Taleie
- Department of Medical Physics, Iran University of Medical Sciences, Tehran, Iran
| | - Ghasem Hajianfar
- Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, CH‑1211, Geneva 4, Switzerland
| | - Maziar Sabouri
- Department of Medical Physics, Iran University of Medical Sciences, Tehran, Iran
- Rajaie Cardiovascular Medical and Research Center, Iran University of Medical Sciences, Tehran, Iran
| | - Mozhgan Parsaee
- Echocardiography Research Center, Rajaie Cardiovascular Medical and Research Center, Iran University of Medical Sciences, Tehran, Iran
| | - Golnaz Houshmand
- Rajaie Cardiovascular Medical and Research Center, Iran University of Medical Sciences, Tehran, Iran
| | - Ahmad Bitarafan-Rajabi
- Echocardiography Research Center, Rajaie Cardiovascular Medical and Research Center, Iran University of Medical Sciences, Tehran, Iran.
- Cardiovascular Interventional Research Center, Rajaie Cardiovascular Medical and Research Center, Iran University of Medical Sciences, Tehran, Iran.
| | - Habib Zaidi
- Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, CH‑1211, Geneva 4, Switzerland.
- Geneva University Neurocenter, University of Geneva, Geneva, Switzerland.
- Department of Nuclear Medicine and Molecular Imaging, University of Groningen, University Medical Center Groningen, Groningen, Netherlands.
- Department of Nuclear Medicine, University of Southern Denmark, Odense, Denmark.
| | - Isaac Shiri
- Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, CH‑1211, Geneva 4, Switzerland.
- Department of Cardiology, Inselspital, Bern University Hospital, University of Bern, Bern, Switzerland.
| |
Collapse
|
7
|
Li JW, Sheng DL, Chen JG, You C, Liu S, Xu HX, Chang C. Artificial intelligence in breast imaging: potentials and challenges. Phys Med Biol 2023; 68:23TR01. [PMID: 37722385 DOI: 10.1088/1361-6560/acfade] [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: 01/15/2023] [Accepted: 09/18/2023] [Indexed: 09/20/2023]
Abstract
Breast cancer, which is the most common type of malignant tumor among humans, is a leading cause of death in females. Standard treatment strategies, including neoadjuvant chemotherapy, surgery, postoperative chemotherapy, targeted therapy, endocrine therapy, and radiotherapy, are tailored for individual patients. Such personalized therapies have tremendously reduced the threat of breast cancer in females. Furthermore, early imaging screening plays an important role in reducing the treatment cycle and improving breast cancer prognosis. The recent innovative revolution in artificial intelligence (AI) has aided radiologists in the early and accurate diagnosis of breast cancer. In this review, we introduce the necessity of incorporating AI into breast imaging and the applications of AI in mammography, ultrasonography, magnetic resonance imaging, and positron emission tomography/computed tomography based on published articles since 1994. Moreover, the challenges of AI in breast imaging are discussed.
Collapse
Affiliation(s)
- Jia-Wei Li
- Department of Medical Ultrasound, Fudan University Shanghai Cancer Center; Department of Oncology, Shanghai Medical College, Fudan University, Shanghai, 200032, People's Republic of China
| | - Dan-Li Sheng
- Department of Medical Ultrasound, Fudan University Shanghai Cancer Center; Department of Oncology, Shanghai Medical College, Fudan University, Shanghai, 200032, People's Republic of China
| | - Jian-Gang Chen
- Shanghai Key Laboratory of Multidimensional Information Processing, School of Communication & Electronic Engineering, East China Normal University, People's Republic of China
| | - Chao You
- Department of Radiology, Fudan University Shanghai Cancer Center; Department of Oncology, Shanghai Medical College, Fudan University, Shanghai 200032, People's Republic of China
| | - Shuai Liu
- Department of Nuclear Medicine, Fudan University Shanghai Cancer Center; Department of Oncology, Shanghai Medical College, Fudan University, Shanghai 200032, People's Republic of China
| | - Hui-Xiong Xu
- Department of Ultrasound, Zhongshan Hospital, Institute of Ultrasound in Medicine and Engineering, Fudan University, Shanghai, 200032, People's Republic of China
| | - Cai Chang
- Department of Medical Ultrasound, Fudan University Shanghai Cancer Center; Department of Oncology, Shanghai Medical College, Fudan University, Shanghai, 200032, People's Republic of China
| |
Collapse
|
8
|
Wang G, Guo Q, Shi D, Zhai H, Luo W, Zhang H, Ren Z, Yan G, Ren K. Clinical Breast MRI-based Radiomics for Distinguishing Benign and Malignant Lesions: An Analysis of Sequences and Enhanced Phases. J Magn Reson Imaging 2023. [PMID: 38006286 DOI: 10.1002/jmri.29150] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/25/2023] [Revised: 11/07/2023] [Accepted: 11/09/2023] [Indexed: 11/27/2023] Open
Abstract
BACKGROUND Previous studies have used different imaging sequences and different enhanced phases for breast lesion calsification in radiomics. The optimal sequence and contrast enhanced phase is unclear. PURPOSE To identify the optimal magnetic resonance imaging (MRI) radiomics model for lesion clarification, and to simulate its incremental value for multiparametric MRI (mpMRI)-guided biopsy. STUDY TYPE Retrospective. POPULATION 329 female patients (138 malignant, 191 benign), divided into a training set (first site, n = 192) and an independent test set (second site, n = 137). FIELD STRENGTH/SEQUENCE 3.0-T, fast spoiled gradient-echo and fast spin-echo T1-weighted imaging (T1WI), fast spin-echo T2-weighted imaging (T2WI), echo-planar diffusion-weighted imaging (DWI), and fast spoiled gradient-echo contrast-enhanced MRI (CE-MRI). ASSESSMENT Two breast radiologists with 3 and 10 years' experience developed radiomics model on CE-MRI, CE-MRI + DWI, CE-MRI + DWI + T2WI, CE-MRI + DWI + T2WI + T1WI at each individual phase (P) and for multiple combinations of phases. The optimal radiomics model (Rad-score) was identified as having the highest area under the receiver operating characteristic curve (AUC) in the test set. Specificity was compared between a traditional mpMRI model and an integrated model (mpMRI + Rad-score) at sensitivity >98%. STATISTICAL TESTS Wilcoxon paired-samples signed rank test, Delong test, McNemar test. Significance level was 0.05 and Bonferroni method was used for multiple comparisons (P = 0.007, 0.05/7). RESULTS For radiomics models, CE-MRI/P3 + DWI + T2WI achieved the highest performance in the test set (AUC = 0.888, 95% confidence interval: 0.833-0.944). The integrated model had significantly higher specificity (55.3%) than the mpMRI model (31.6%) in the test set with a sensitivity of 98.4%. DATA CONCLUSION The CE-MRI/P3 + DWI + T2WI model is the optimized choice for breast lesion classification in radiomics, and has potential to reduce benign biopsies (100%-specificity) from 68.4% to 44.7% while retaining sensitivity >98%. LEVEL OF EVIDENCE 3 TECHNICAL EFFICACY: Stage 2.
Collapse
Affiliation(s)
- Guangsong Wang
- Department of Radiology, Xiang'an Hospital of Xiamen University, School of Medicine, Xiamen University, Xiamen, Fujian, China
| | - Qiu Guo
- Department of Radiology, Xiang'an Hospital of Xiamen University, School of Medicine, Xiamen University, Xiamen, Fujian, China
| | - Dafa Shi
- Department of Radiology, Xiang'an Hospital of Xiamen University, School of Medicine, Xiamen University, Xiamen, Fujian, China
| | - Huige Zhai
- Department of Radiology, The Second Affiliated Hospital of Xiamen Medical College, Xiamen, Fujian, China
| | - Wenbin Luo
- Department of Radiology, The Second Affiliated Hospital of Xiamen Medical College, Xiamen, Fujian, China
| | - Haoran Zhang
- Department of Radiology, Xiang'an Hospital of Xiamen University, School of Medicine, Xiamen University, Xiamen, Fujian, China
| | - Zhendong Ren
- Department of Radiology, Xiang'an Hospital of Xiamen University, School of Medicine, Xiamen University, Xiamen, Fujian, China
| | - Gen Yan
- Department of Radiology, The Second Affiliated Hospital of Xiamen Medical College, Xiamen, Fujian, China
| | - Ke Ren
- Department of Radiology, Xiang'an Hospital of Xiamen University, School of Medicine, Xiamen University, Xiamen, Fujian, China
- Xiamen Key Laboratory of Endocrine-Related Cancer Precision Medicine, Xiang'an Hospital of Xiamen university, Xiamen, Fujian, China
| |
Collapse
|
9
|
Fan Y, Zhao D, Su J, Yuan W, Niu S, Guo W, Jiang W. Radiomic Signatures Based on Mammography and Magnetic Resonance Imaging as New Markers for Estimation of Ki-67 and HER-2 Status in Breast Cancer. J Comput Assist Tomogr 2023; 47:890-897. [PMID: 37948363 DOI: 10.1097/rct.0000000000001502] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 07/23/2023]
Abstract
OBJECTIVE The aim of the study is to investigate the values of intratumoral and peritumoral regions based on mammography and magnetic resonance imaging for the prediction of Ki-67 and human epidermal growth factor (HER-2) status in breast cancer (BC). METHODS Two hundred BC patients were consecutively enrolled between January 2017 and March 2021 and divided into training (n = 133) and validation (n = 67) groups. All the patients underwent breast mammography and magnetic resonance imaging screening. Features were derived from intratumoral and peritumoral regions of the tumor and selected using the least absolute shrinkage and selection operator regression to build radiomic signatures (RSs). Receiver operating characteristic curve analysis and the DeLong test were performed to assess and compare each RS. RESULTS For each modality, the combined RSs integrating features from intratumoral and peritumoral regions always showed better prediction performance for predicting Ki-67 and HER-2 status compared with the RSs derived from intratumoral or peritumoral regions separately. The multimodality and multiregional combined RSs achieved the best prediction performance for predicting the Ki-67 and HER-2 status with an area under the receiver operating characteristic curve of 0.888 and 0.868 in the training cohort and 0.800 and 0.848 in the validation cohort, respectively. CONCLUSIONS Peritumoral areas provide complementary information to intratumoral regions of BC. The developed multimodality and multiregional combined RSs have good potential for noninvasive evaluation of Ki-67 and HER-2 status in BC.
Collapse
Affiliation(s)
- Ying Fan
- From the School of Intelligent Medicine, China Medical University, Shenyang
| | - Dan Zhao
- Department of Medical Imaging, Cancer Hospital of China Medical University, Liaoning Cancer Hospital and Institute, Liaoning
| | - Juan Su
- From the School of Intelligent Medicine, China Medical University, Shenyang
| | - Wendi Yuan
- From the School of Intelligent Medicine, China Medical University, Shenyang
| | - Shuxian Niu
- From the School of Intelligent Medicine, China Medical University, Shenyang
| | - Wei Guo
- College of Computer Science, Shenyang Aerospace University, Shenyang
| | - Wenyan Jiang
- Department of Scientific Research and Academic, Cancer Hospital of China Medical University, Liaoning Cancer Hospital and Institute, Liaoning, People's Republic. China
| |
Collapse
|
10
|
Bagher-Ebadian H, Brown SL, Ghassemi MM, Nagaraja TN, Movsas B, Ewing JR, Chetty IJ. Radiomics characterization of tissues in an animal brain tumor model imaged using dynamic contrast enhanced (DCE) MRI. Sci Rep 2023; 13:10693. [PMID: 37394559 DOI: 10.1038/s41598-023-37723-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/05/2022] [Accepted: 06/27/2023] [Indexed: 07/04/2023] Open
Abstract
Here, we investigate radiomics-based characterization of tumor vascular and microenvironmental properties in an orthotopic rat brain tumor model measured using dynamic-contrast-enhanced (DCE) MRI. Thirty-two immune compromised-RNU rats implanted with human U-251N cancer cells were imaged using DCE-MRI (7Tesla, Dual-Gradient-Echo). The aim was to perform pharmacokinetic analysis using a nested model (NM) selection technique to classify brain regions according to vasculature properties considered as the source of truth. A two-dimensional convolutional-based radiomics analysis was performed on the raw-DCE-MRI of the rat brains to generate dynamic radiomics maps. The raw-DCE-MRI and respective radiomics maps were used to build 28 unsupervised Kohonen self-organizing-maps (K-SOMs). A Silhouette-Coefficient (SC), k-fold Nested-Cross-Validation (k-fold-NCV), and feature engineering analyses were performed on the K-SOMs' feature spaces to quantify the distinction power of radiomics features compared to raw-DCE-MRI for classification of different Nested Models. Results showed that eight radiomics features outperformed respective raw-DCE-MRI in prediction of the three nested models. The average percent difference in SCs between radiomics features and raw-DCE-MRI was: 29.875% ± 12.922%, p < 0.001. This work establishes an important first step toward spatiotemporal characterization of brain regions using radiomics signatures, which is fundamental toward staging of tumors and evaluation of tumor response to different treatments.
Collapse
Affiliation(s)
- Hassan Bagher-Ebadian
- Department of Radiation Oncology, Henry Ford Health, Detroit, MI, 48202, USA.
- Department of Radiology, Michigan State University, East Lansing, MI, 48824, USA.
- Department of Osteopathic Medicine, Michigan State University, East Lansing, MI, 48824, USA.
- Department of Physics, Oakland University, Rochester, MI, 48309, USA.
| | - Stephen L Brown
- Department of Radiation Oncology, Henry Ford Health, Detroit, MI, 48202, USA
- Department of Radiology, Michigan State University, East Lansing, MI, 48824, USA
- Department of Radiation Oncology, Wayne State University, Detroit, MI, 48202, USA
| | - Mohammad M Ghassemi
- Department of Computer Science and Engineering, Michigan State University, East Lansing, MI, 48824, USA
| | - Tavarekere N Nagaraja
- Department of Radiology, Michigan State University, East Lansing, MI, 48824, USA
- Department of Neurosurgery, Henry Ford Health, Detroit, MI, 48202, USA
| | - Benjamin Movsas
- Department of Radiation Oncology, Henry Ford Health, Detroit, MI, 48202, USA
- Department of Radiology, Michigan State University, East Lansing, MI, 48824, USA
- Department of Radiation Oncology, Wayne State University, Detroit, MI, 48202, USA
| | - James R Ewing
- Department of Radiology, Michigan State University, East Lansing, MI, 48824, USA
- Department of Physics, Oakland University, Rochester, MI, 48309, USA
- Department of Neurosurgery, Henry Ford Health, Detroit, MI, 48202, USA
- Department of Neurology, Henry Ford Health, Detroit, MI, 48202, USA
- Department of Neurology, Wayne State University, Detroit, MI, 48202, USA
| | - Indrin J Chetty
- Department of Radiation Oncology, Henry Ford Health, Detroit, MI, 48202, USA
- Department of Physics, Oakland University, Rochester, MI, 48309, USA
- Department of Radiation Oncology, Wayne State University, Detroit, MI, 48202, USA
| |
Collapse
|
11
|
Cho P, Park CS, Park GE, Kim SH, Kim HS, Oh SJ. Diagnostic Usefulness of Diffusion-Weighted MRI for Axillary Lymph Node Evaluation in Patients with Breast Cancer. Diagnostics (Basel) 2023; 13:diagnostics13030513. [PMID: 36766617 PMCID: PMC9914452 DOI: 10.3390/diagnostics13030513] [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: 12/26/2022] [Revised: 01/20/2023] [Accepted: 01/21/2023] [Indexed: 02/01/2023] Open
Abstract
This study aimed to determine whether apparent diffusion coefficient (ADC) and morphological features on diffusion-weighted MRI (DW-MRI) can discriminate metastatic axillary lymph nodes (ALNs) from benign in patients with breast cancer. Two radiologists measured ADC, long and short diameters, long-to-short diameter ratio, and cortical thickness and assessed eccentric cortical thickening, loss of fatty hilum, irregular margin, asymmetry in shape or number, and rim sign of ALNs on DW-MRI and categorized them into benign or suspicious ALNs. Pathologic reports were used as a reference standard. Statistical analysis was performed using the Mann-Whitney U test and chi-square test. Overall sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and diagnostic accuracy of DW-MRI were calculated. The ADC of metastatic ALNs was 0.905 × 10-3 mm2/s, and that of benign ALNs was 0.991 × 10-3 mm2/s (p = 0.243). All morphologic features showed significant difference between the two groups. The sensitivity, specificity, PPV, NPV, and diagnostic accuracy of the final categorization on DW-MRI were 77.1%, 93.3%, 79.4%, 92.5%, and 86.2%, respectively. Our results suggest that morphologic evaluation of ALNs on DWI can discriminate metastatic ALNs from benign. The ADC value of metastatic ALNs was lower than that of benign nodes, but the difference was not statistically significant.
Collapse
Affiliation(s)
- Pyeonghwa Cho
- Department of Radiology, Incheon St. Mary’s Hospital, College of Medicine, The Catholic University of Korea School of Medicine, Seoul 21431, Republic of Korea
| | - Chang Suk Park
- Department of Radiology, Incheon St. Mary’s Hospital, College of Medicine, The Catholic University of Korea School of Medicine, Seoul 21431, Republic of Korea
- Correspondence: ; Tel.: +82-32-280-7305; Fax: +82-32-280-5192
| | - Ga Eun Park
- Department of Radiology, Seoul St. Mary’s Hospital, College of Medicine, The Catholic University of Korea School of Medicine, Seoul 06591, Republic of Korea
| | - Sung Hun Kim
- Department of Radiology, Seoul St. Mary’s Hospital, College of Medicine, The Catholic University of Korea School of Medicine, Seoul 06591, Republic of Korea
| | - Hyeon Sook Kim
- Department of Radiology, Incheon St. Mary’s Hospital, College of Medicine, The Catholic University of Korea School of Medicine, Seoul 21431, Republic of Korea
| | - Se-Jeong Oh
- Department of General Surgery, Incheon St. Mary’s Hospital, College of Medicine, The Catholic University of Korea School of Medicine, Seoul 21431, Republic of Korea
| |
Collapse
|
12
|
Balasubramanian PK, Lai WC, Seng GH, C K, Selvaraj J. APESTNet with Mask R-CNN for Liver Tumor Segmentation and Classification. Cancers (Basel) 2023; 15:cancers15020330. [PMID: 36672281 PMCID: PMC9857237 DOI: 10.3390/cancers15020330] [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: 11/29/2022] [Revised: 12/21/2022] [Accepted: 12/30/2022] [Indexed: 01/06/2023] Open
Abstract
Diagnosis and treatment of hepatocellular carcinoma or metastases rely heavily on accurate segmentation and classification of liver tumours. However, due to the liver tumor's hazy borders and wide range of possible shapes, sizes, and positions, accurate and automatic tumour segmentation and classification remains a difficult challenge. With the advancement of computing, new models in artificial intelligence have evolved. Following its success in Natural language processing (NLP), the transformer paradigm has been adopted by the computer vision (CV) community of the NLP. While there are already accepted approaches to classifying the liver, especially in clinical settings, there is room for advancement in terms of their precision. This paper makes an effort to apply a novel model for segmenting and classifying liver tumours built on deep learning. In order to accomplish this, the created model follows a three-stage procedure consisting of (a) pre-processing, (b) liver segmentation, and (c) classification. In the first phase, the collected Computed Tomography (CT) images undergo three stages of pre-processing, including contrast improvement via histogram equalization and noise reduction via the median filter. Next, an enhanced mask region-based convolutional neural networks (Mask R-CNN) model is used to separate the liver from the CT abdominal image. To prevent overfitting, the segmented picture is fed onto an Enhanced Swin Transformer Network with Adversarial Propagation (APESTNet). The experimental results prove the superior performance of the proposed perfect on a wide variety of CT images, as well as its efficiency and low sensitivity to noise.
Collapse
Affiliation(s)
- Prabhu Kavin Balasubramanian
- Department of Data Science and Business System, Kattankulathur Campus, SRM Institute of Science and Technology, Chennai 603203, Tamil Nadu, India
| | - Wen-Cheng Lai
- Bachelor Program in Industrial Projects, National Yunlin University of Science and Technology, Douliu 640301, Taiwan
- Department of Electronic Engineering, National Yunlin University of Science and Technology, Douliu 640301, Taiwan
| | - Gan Hong Seng
- Department of Data Science, UMK City Campus, University Malaysia Kelantan, Pengkalan Chepa, Kelantan 16100, Malaysia
- Correspondence: (G.H.S.); (K.C.)
| | - Kavitha C
- Department of Computer Science and Engineering, Sathyabama Institute of Science and Technology, Chennai 600119, Tamil Nadu, India
- Correspondence: (G.H.S.); (K.C.)
| | - Jeeva Selvaraj
- Department of Data Science and Business System, Kattankulathur Campus, SRM Institute of Science and Technology, Chennai 603203, Tamil Nadu, India
- Department of Data Science, UMK City Campus, University Malaysia Kelantan, Pengkalan Chepa, Kelantan 16100, Malaysia
| |
Collapse
|
13
|
Hatamikia S, Gulyas I, Birkfellner W, Kronreif G, Unger A, Oberoi G, Lorenz A, Unger E, Kettenbach J, Figl M, Patsch J, Strassl A, Georg D, Renner A. Realistic 3D printed CT imaging tumor phantoms for validation of image processing algorithms. Phys Med 2023; 105:102512. [PMID: 36584415 DOI: 10.1016/j.ejmp.2022.102512] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 06/18/2022] [Revised: 11/06/2022] [Accepted: 12/15/2022] [Indexed: 12/30/2022] Open
Abstract
Medical imaging phantoms are widely used for validation and verification of imaging systems and algorithms in surgical guidance and radiation oncology procedures. Especially, for the performance evaluation of new algorithms in the field of medical imaging, manufactured phantoms need to replicate specific properties of the human body, e.g., tissue morphology and radiological properties. Additive manufacturing (AM) technology provides an inexpensive opportunity for accurate anatomical replication with customization capabilities. In this study, we proposed a simple and cheap protocol using Fused Deposition Modeling (FDM) technology to manufacture realistic tumor phantoms based on the filament 3D printing technology. Tumor phantoms with both homogenous and heterogeneous radiodensity were fabricated. The radiodensity similarity between the printed tumor models and real tumor data from CT images of lung cancer patients was evaluated. Additionally, it was investigated whether a heterogeneity in the 3D printed tumor phantoms as observed in the tumor patient data had an influence on the validation of image registration algorithms. A radiodensity range between -217 to 226 HUs was achieved for 3D printed phantoms using different filament materials; this range of radiation attenuation is also observed in the human lung tumor tissue. The resulted HU range could serve as a lookup-table for researchers and phantom manufactures to create realistic CT tumor phantoms with the desired range of radiodensities. The 3D printed tumor phantoms also precisely replicated real lung tumor patient data regarding morphology and could also include life-like heterogeneity of the radiodensity inside the tumor models. An influence of the heterogeneity on accuracy and robustness of the image registration algorithms was not found.
Collapse
Affiliation(s)
- Sepideh Hatamikia
- Austrian Center for Medical Innovation and Technology, Wiener Neustadt, Austria; Research Center for Medical Image Analysis and Artificial Intelligence (MIAAI), Department of Medicine, Danube Private University, Krems, Austria; Center for Medical Physics and Biomedical Engineering, Medical University of Vienna, Vienna, Austria.
| | - Ingo Gulyas
- Department of Radiation Oncology, Medical University of Vienna, Vienna, Austria
| | - Wolfgang Birkfellner
- Center for Medical Physics and Biomedical Engineering, Medical University of Vienna, Vienna, Austria
| | - Gernot Kronreif
- Austrian Center for Medical Innovation and Technology, Wiener Neustadt, Austria
| | - Alexander Unger
- Austrian Center for Medical Innovation and Technology, Wiener Neustadt, Austria
| | - Gunpreet Oberoi
- Center for Medical Physics and Biomedical Engineering, Medical University of Vienna, Vienna, Austria
| | - Andrea Lorenz
- Austrian Center for Medical Innovation and Technology, Wiener Neustadt, Austria
| | - Ewald Unger
- Center for Medical Physics and Biomedical Engineering, Medical University of Vienna, Vienna, Austria
| | - Joachim Kettenbach
- Institute of Diagnostic, Interventional Radiology and Nuclear Medicine, Landesklinikum Wiener Neustadt, Wiener Neustadt, Austria
| | - Michael Figl
- Center for Medical Physics and Biomedical Engineering, Medical University of Vienna, Vienna, Austria
| | - Janina Patsch
- Department of Radiology and Nuclear Medicine, Medical University Vienna, Austria
| | - Andreas Strassl
- Department of Radiology and Nuclear Medicine, Medical University Vienna, Austria
| | - Dietmar Georg
- Department of Radiation Oncology, Medical University of Vienna, Vienna, Austria
| | - Andreas Renner
- Department of Radiation Oncology, Medical University of Vienna, Vienna, Austria
| |
Collapse
|
14
|
A Flexible Wearable Thermography System Based on Bioheat Microsensors Network for Early Breast Cancer Detection: IoT Technology. JOURNAL OF ELECTRICAL AND COMPUTER ENGINEERING 2022. [DOI: 10.1155/2022/5921691] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/24/2022]
Abstract
Many women diagnosed by traditional screening methods, such as palpation, mammography, and MRI, do not discover their cancer until it is relatively advanced. This makes treatment more difficult and reduces the chance of a cure. To deal with this issue, we have developed a noninvasive embedded thermography system that allows for an early detection of breast cancer. Indeed, the surface temperature distribution of the breast, which we will call the thermal image, can be used as a preventive indicator of the subsequent development of a cancerous tumor. This is due to the metabolic activity of the immune system, which induces, in the presence of cancer cells, a local increase of temperature even before the tumor tissue is differentiated and detectable by conventional imaging systems. The proposed system is designed as a network of bioheat microsensors applied to the breast, to measure periodically the temperature gradients on the surface. All the bioheat microsensors are addressed by a microcontroller via the I2C protocol. To calibrate and evaluate the proposed system, we have proposed an experimental model of the breast, inside which we have placed Joule effect heating elements.
Collapse
|
15
|
Jeon SH, Kim SW, Na K, Seo M, Sohn YM, Lim YJ. Radiomic models based on magnetic resonance imaging predict the spatial distribution of CD8 + tumor-infiltrating lymphocytes in breast cancer. Front Immunol 2022; 13:1080048. [PMID: 36601118 PMCID: PMC9806253 DOI: 10.3389/fimmu.2022.1080048] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/25/2022] [Accepted: 12/07/2022] [Indexed: 12/23/2022] Open
Abstract
Infiltration of CD8+ T cells and their spatial contexture, represented by immunophenotype, predict the prognosis and therapeutic response in breast cancer. However, a non-surgical method using radiomics to evaluate breast cancer immunophenotype has not been explored. Here, we assessed the CD8+ T cell-based immunophenotype in patients with breast cancer undergoing upfront surgery (n = 182). We extracted radiomic features from the four phases of dynamic contrast-enhanced magnetic resonance imaging, and randomly divided the patients into training (n = 137) and validation (n = 45) cohorts. For predicting the immunophenotypes, radiomic models (RMs) that combined the four phases demonstrated superior performance to those derived from a single phase. For discriminating the inflamed tumor from the non-inflamed tumor, the feature-based combination model from the whole tumor (RM-wholeFC) showed high performance in both training (area under the receiver operating characteristic curve [AUC] = 0.973) and validation cohorts (AUC = 0.985). Similarly, the feature-based combination model from the peripheral tumor (RM-periFC) discriminated between immune-desert and excluded tumors with high performance in both training (AUC = 0.993) and validation cohorts (AUC = 0.984). Both RM-wholeFC and RM-periFC demonstrated good to excellent performance for every molecular subtype. Furthermore, in patients who underwent neoadjuvant chemotherapy (n = 64), pre-treatment images showed that tumors exhibiting complete response to neoadjuvant chemotherapy had significantly higher scores from RM-wholeFC and lower scores from RM-periFC. Our RMs predicted the immunophenotype of breast cancer based on the spatial distribution of CD8+ T cells with high accuracy. This approach can be used to stratify patients non-invasively based on the status of the tumor-immune microenvironment.
Collapse
Affiliation(s)
- Seung Hyuck Jeon
- Graduate School of Medical Science and Engineering, Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea
| | - So-Woon Kim
- Department of Pathology, Kyung Hee University College of Medicine, Kyung Hee University Medical Center, Seoul, Republic of Korea
| | - Kiyong Na
- Department of Pathology, Kyung Hee University College of Medicine, Kyung Hee University Medical Center, Seoul, Republic of Korea
| | - Mirinae Seo
- Department of Radiology, Kyung Hee University College of Medicine, Kyung Hee University Medical Center, Seoul, Republic of Korea
| | - Yu-Mee Sohn
- Department of Radiology, Kyung Hee University College of Medicine, Kyung Hee University Medical Center, Seoul, Republic of Korea
| | - Yu Jin Lim
- Department of Radiation Oncology, Kyung Hee University College of Medicine, Kyung Hee University Medical Center, Seoul, Republic of Korea,*Correspondence: Yu Jin Lim,
| |
Collapse
|
16
|
A Hybrid Workflow of Residual Convolutional Transformer Encoder for Breast Cancer Classification Using Digital X-ray Mammograms. Biomedicines 2022; 10:biomedicines10112971. [PMID: 36428538 PMCID: PMC9687367 DOI: 10.3390/biomedicines10112971] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/11/2022] [Revised: 11/03/2022] [Accepted: 11/13/2022] [Indexed: 11/19/2022] Open
Abstract
Breast cancer, which attacks the glandular epithelium of the breast, is the second most common kind of cancer in women after lung cancer, and it affects a significant number of people worldwide. Based on the advantages of Residual Convolutional Network and the Transformer Encoder with Multiple Layer Perceptron (MLP), this study proposes a novel hybrid deep learning Computer-Aided Diagnosis (CAD) system for breast lesions. While the backbone residual deep learning network is employed to create the deep features, the transformer is utilized to classify breast cancer according to the self-attention mechanism. The proposed CAD system has the capability to recognize breast cancer in two scenarios: Scenario A (Binary classification) and Scenario B (Multi-classification). Data collection and preprocessing, patch image creation and splitting, and artificial intelligence-based breast lesion identification are all components of the execution framework that are applied consistently across both cases. The effectiveness of the proposed AI model is compared against three separate deep learning models: a custom CNN, the VGG16, and the ResNet50. Two datasets, CBIS-DDSM and DDSM, are utilized to construct and test the proposed CAD system. Five-fold cross validation of the test data is used to evaluate the accuracy of the performance results. The suggested hybrid CAD system achieves encouraging evaluation results, with overall accuracies of 100% and 95.80% for binary and multiclass prediction challenges, respectively. The experimental results reveal that the proposed hybrid AI model could identify benign and malignant breast tissues significantly, which is important for radiologists to recommend further investigation of abnormal mammograms and provide the optimal treatment plan.
Collapse
|
17
|
Altabella L, Benetti G, Camera L, Cardano G, Montemezzi S, Cavedon C. Machine learning for multi-parametric breast MRI: radiomics-based approaches for lesion classification. Phys Med Biol 2022; 67. [DOI: 10.1088/1361-6560/ac7d8f] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/30/2021] [Accepted: 06/30/2022] [Indexed: 11/11/2022]
Abstract
Abstract
In the artificial intelligence era, machine learning (ML) techniques have gained more and more importance in the advanced analysis of medical images in several fields of modern medicine. Radiomics extracts a huge number of medical imaging features revealing key components of tumor phenotype that can be linked to genomic pathways. The multi-dimensional nature of radiomics requires highly accurate and reliable machine-learning methods to create predictive models for classification or therapy response assessment.
Multi-parametric breast magnetic resonance imaging (MRI) is routinely used for dense breast imaging as well for screening in high-risk patients and has shown its potential to improve clinical diagnosis of breast cancer. For this reason, the application of ML techniques to breast MRI, in particular to multi-parametric imaging, is rapidly expanding and enhancing both diagnostic and prognostic power. In this review we will focus on the recent literature related to the use of ML in multi-parametric breast MRI for tumor classification and differentiation of molecular subtypes. Indeed, at present, different models and approaches have been employed for this task, requiring a detailed description of the advantages and drawbacks of each technique and a general overview of their performances.
Collapse
|
18
|
Jayaprakasam VS, Gibbs P, Gangai N, Bajwa R, Sosa RE, Yeh R, Greally M, Ku GY, Gollub MJ, Paroder V. Can 18F-FDG PET/CT Radiomics Features Predict Clinical Outcomes in Patients with Locally Advanced Esophageal Squamous Cell Carcinoma? Cancers (Basel) 2022; 14:cancers14123035. [PMID: 35740700 PMCID: PMC9221147 DOI: 10.3390/cancers14123035] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/02/2022] [Revised: 06/15/2022] [Accepted: 06/16/2022] [Indexed: 02/04/2023] Open
Abstract
Simple Summary PET/CT is an important staging modality in the baseline assessment of locally advanced esophageal squamous cell carcinoma. Accurate staging and response prediction in these patients is essential for management. The aim of this retrospective study was to assess the usefulness of 18F-FDG PET/CT radiomics features in predicting outcomes such as tumor and nodal categories, PET-based response to induction chemotherapy, progression-free survival, and overall survival. In a final cohort of 74 patients, we found that the developed radiomics models can predict these clinical and prognostic outcomes with reasonable accuracy, similar or better than those derived from conventional imaging. Future studies with a larger cohort would be helpful in establishing the significance of these models. Abstract This study aimed to assess the usefulness of radiomics features of 18F-FDG PET/CT in patients with locally advanced esophageal cancers (ESCC) in predicting outcomes such as clinical tumor (cT) and nodal (cN) categories, PET response to induction chemotherapy (PET response), progression-free survival (PFS), and overall survival (OS). Pretreatment PET/CT images from patients who underwent concurrent chemoradiotherapy from July 2002 to February 2017 were segmented, and data were split into training and test sets. Model development was performed on the training datasets and a maximum of five features were selected. Final diagnostic accuracies were determined using the test dataset. A total of 86 PET/CTs (58 men and 28 women, mean age 65 years) were segmented. Due to small lesion size, 12 patients were excluded. The diagnostic accuracies as derived from the CT, PET, and combined PET/CT test datasets were as follows: cT category—70.4%, 70.4%, and 81.5%, respectively; cN category—69.0%, 86.2%, and 86.2%, respectively; PET response—60.0%, 66.7%, and 70.0%, respectively; PFS—60.7%, 75.0%, and 75.0%, respectively; and OS—51.7%, 55.2%, and 62.1%, respectively. A radiomics assessment of locally advanced ESCC has the potential to predict various clinical outcomes. External validation of these models would be further helpful.
Collapse
Affiliation(s)
- Vetri Sudar Jayaprakasam
- Molecular Imaging and Therapy Service, Department of Radiology, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA; (V.S.J.); (R.Y.)
| | - Peter Gibbs
- Department of Radiology, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA; (P.G.); (N.G.); (R.B.); (R.E.S.); (M.J.G.)
| | - Natalie Gangai
- Department of Radiology, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA; (P.G.); (N.G.); (R.B.); (R.E.S.); (M.J.G.)
| | - Raazi Bajwa
- Department of Radiology, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA; (P.G.); (N.G.); (R.B.); (R.E.S.); (M.J.G.)
| | - Ramon E. Sosa
- Department of Radiology, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA; (P.G.); (N.G.); (R.B.); (R.E.S.); (M.J.G.)
| | - Randy Yeh
- Molecular Imaging and Therapy Service, Department of Radiology, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA; (V.S.J.); (R.Y.)
| | | | - Geoffrey Y. Ku
- Department of Medicine, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA;
| | - Marc J. Gollub
- Department of Radiology, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA; (P.G.); (N.G.); (R.B.); (R.E.S.); (M.J.G.)
| | - Viktoriya Paroder
- Department of Radiology, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA; (P.G.); (N.G.); (R.B.); (R.E.S.); (M.J.G.)
- Correspondence:
| |
Collapse
|
19
|
Jayaprakasam VS, Gibbs P, Gangai N, Bajwa R, Sosa RE, Yeh R, Greally M, Ku GY, Gollub MJ, Paroder V. Can 18F-FDG PET/CT Radiomics Features Predict Clinical Outcomes in Patients with Locally Advanced Esophageal Squamous Cell Carcinoma? Cancers (Basel) 2022; 14:3035. [PMID: 35740700 PMCID: PMC9221147 DOI: 10.3390/cancers14123035&n999822=v982537] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/16/2022] Open
Abstract
This study aimed to assess the usefulness of radiomics features of 18F-FDG PET/CT in patients with locally advanced esophageal cancers (ESCC) in predicting outcomes such as clinical tumor (cT) and nodal (cN) categories, PET response to induction chemotherapy (PET response), progression-free survival (PFS), and overall survival (OS). Pretreatment PET/CT images from patients who underwent concurrent chemoradiotherapy from July 2002 to February 2017 were segmented, and data were split into training and test sets. Model development was performed on the training datasets and a maximum of five features were selected. Final diagnostic accuracies were determined using the test dataset. A total of 86 PET/CTs (58 men and 28 women, mean age 65 years) were segmented. Due to small lesion size, 12 patients were excluded. The diagnostic accuracies as derived from the CT, PET, and combined PET/CT test datasets were as follows: cT category-70.4%, 70.4%, and 81.5%, respectively; cN category-69.0%, 86.2%, and 86.2%, respectively; PET response-60.0%, 66.7%, and 70.0%, respectively; PFS-60.7%, 75.0%, and 75.0%, respectively; and OS-51.7%, 55.2%, and 62.1%, respectively. A radiomics assessment of locally advanced ESCC has the potential to predict various clinical outcomes. External validation of these models would be further helpful.
Collapse
Affiliation(s)
- Vetri Sudar Jayaprakasam
- Molecular Imaging and Therapy Service, Department of Radiology, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA; (V.S.J.); (R.Y.)
| | - Peter Gibbs
- Department of Radiology, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA; (P.G.); (N.G.); (R.B.); (R.E.S.); (M.J.G.)
| | - Natalie Gangai
- Department of Radiology, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA; (P.G.); (N.G.); (R.B.); (R.E.S.); (M.J.G.)
| | - Raazi Bajwa
- Department of Radiology, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA; (P.G.); (N.G.); (R.B.); (R.E.S.); (M.J.G.)
| | - Ramon E. Sosa
- Department of Radiology, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA; (P.G.); (N.G.); (R.B.); (R.E.S.); (M.J.G.)
| | - Randy Yeh
- Molecular Imaging and Therapy Service, Department of Radiology, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA; (V.S.J.); (R.Y.)
| | | | - Geoffrey Y. Ku
- Department of Medicine, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA;
| | - Marc J. Gollub
- Department of Radiology, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA; (P.G.); (N.G.); (R.B.); (R.E.S.); (M.J.G.)
| | - Viktoriya Paroder
- Department of Radiology, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA; (P.G.); (N.G.); (R.B.); (R.E.S.); (M.J.G.)
- Correspondence:
| |
Collapse
|
20
|
Ammar M, Mahmoudi S. A New Strategy for Automatic Breast Cancer Segmentation in MRI images. J MECH MED BIOL 2022. [DOI: 10.1142/s0219519422500555] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/18/2022]
|
21
|
Robustness Analysis of DCE-MRI-Derived Radiomic Features in Breast Masses: Assessing Quantization Levels and Segmentation Agreement. APPLIED SCIENCES-BASEL 2022. [DOI: 10.3390/app12115512] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
Abstract
Machine learning models based on radiomic features allow us to obtain biomarkers that are capable of modeling the disease and that are able to support the clinical routine. Recent studies have shown that it is fundamental that the computed features are robust and reproducible. Although several initiatives to standardize the definition and extraction process of biomarkers are ongoing, there is a lack of comprehensive guidelines. Therefore, no standardized procedures are available for ROI selection, feature extraction, and processing, with the risk of undermining the effective use of radiomic models in clinical routine. In this study, we aim to assess the impact that the different segmentation methods and the quantization level (defined by means of the number of bins used in the feature-extraction phase) may have on the robustness of the radiomic features. In particular, the robustness of texture features extracted by PyRadiomics, and belonging to five categories—GLCM, GLRLM, GLSZM, GLDM, and NGTDM—was evaluated using the intra-class correlation coefficient (ICC) and mean differences between segmentation raters. In addition to the robustness of each single feature, an overall index for each feature category was quantified. The analysis showed that the level of quantization (i.e., the `bincount’ parameter) plays a key role in defining robust features: in fact, in our study focused on a dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) dataset of 111 breast masses, sets with cardinality varying between 34 and 43 robust features were obtained with `binCount’ values equal to 256 and 32, respectively. Moreover, both manual segmentation methods demonstrated good reliability and agreement, while automated segmentation achieved lower ICC values. Considering the dependence on the quantization level, taking into account only the intersection subset among all the values of `binCount’ could be the best selection strategy. Among radiomic feature categories, GLCM, GLRLM, and GLDM showed the best overall robustness with varying segmentation methods.
Collapse
|
22
|
Evaluation of Post-Stroke Impairment in Fine Tactile Sensation by Electroencephalography (EEG)-Based Machine Learning. APPLIED SCIENCES-BASEL 2022. [DOI: 10.3390/app12094796] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/28/2022]
Abstract
Electroencephalography (EEG)-based measurements of fine tactile sensation produce large amounts of data, with high costs for manual evaluation. In this study, an EEG-based machine-learning (ML) model with support vector machine (SVM) was established to automatically evaluate post-stroke impairments in fine tactile sensation. Stroke survivors (n = 12, stroke group) and unimpaired participants (n = 15, control group) received stimulations with cotton, nylon, and wool fabrics to the different upper limbs of a stroke participant and the dominant side of the control. The average and maximal values of relative spectral power (RSP) of EEG in the stimulations were used as the inputs to the SVM-ML model, which was first optimized for classification accuracies for different limb sides through hyperparameter selection (γ, C) in radial basis function (RBF) kernel and cross-validation during cotton stimulation. Model generalization was investigated by comparing accuracies during stimulations with different fabrics to different limbs. The highest accuracies were achieved with (γ = 21, C = 23) for the RBF kernel (76.8%) and six-fold cross-validation (75.4%), respectively, in the gamma band for cotton stimulation; these were selected as optimal parameters for the SVM-ML model. In model generalization, significant differences in the post-stroke fabric stimulation accuracies were shifted to higher (beta/gamma) bands. The EEG-based SVM-ML model generated results similar to manual evaluation of cortical responses to fabric stimulations; this may aid automatic assessments of post-stroke fine tactile sensations.
Collapse
|