1
|
Wang J, Liu G, Zhou C, Cui X, Wang W, Wang J, Huang Y, Jiang J, Wang Z, Tang Z, Zhang A, Cui D. Application of artificial intelligence in cancer diagnosis and tumor nanomedicine. NANOSCALE 2024; 16:14213-14246. [PMID: 39021117 DOI: 10.1039/d4nr01832j] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 07/20/2024]
Abstract
Cancer is a major health concern due to its high incidence and mortality rates. Advances in cancer research, particularly in artificial intelligence (AI) and deep learning, have shown significant progress. The swift evolution of AI in healthcare, especially in tools like computer-aided diagnosis, has the potential to revolutionize early cancer detection. This technology offers improved speed, accuracy, and sensitivity, bringing a transformative impact on cancer diagnosis, treatment, and management. This paper provides a concise overview of the application of artificial intelligence in the realms of medicine and nanomedicine, with a specific emphasis on the significance and challenges associated with cancer diagnosis. It explores the pivotal role of AI in cancer diagnosis, leveraging structured, unstructured, and multimodal fusion data. Additionally, the article delves into the applications of AI in nanomedicine sensors and nano-oncology drugs. The fundamentals of deep learning and convolutional neural networks are clarified, underscoring their relevance to AI-driven cancer diagnosis. A comparative analysis is presented, highlighting the accuracy and efficiency of traditional methods juxtaposed with AI-based approaches. The discussion not only assesses the current state of AI in cancer diagnosis but also delves into the challenges faced by AI in this context. Furthermore, the article envisions the future development direction and potential application of artificial intelligence in cancer diagnosis, offering a hopeful prospect for enhanced cancer detection and improved patient prognosis.
Collapse
Affiliation(s)
- Junhao Wang
- School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China.
| | - Guan Liu
- School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China.
| | - Cheng Zhou
- School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China.
| | - Xinyuan Cui
- Imaging Department of Rui Jin Hospital, Medical School of Shanghai Jiao Tong University, Shanghai, China
| | - Wei Wang
- School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China.
| | - Jiulin Wang
- School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China.
| | - Yixin Huang
- School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China.
| | - Jinlei Jiang
- School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China.
| | - Zhitao Wang
- School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China.
| | - Zengyi Tang
- School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China.
| | - Amin Zhang
- Department of Food Science & Technology, School of Agriculture & Biology, Shanghai Jiao Tong University, Shanghai, China.
| | - Daxiang Cui
- School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China.
- School of Medicine, Henan University, Henan, China
| |
Collapse
|
2
|
Martis JE, M S S, R B, Mutawa AM, Murugappan M. Novel Hybrid Quantum Architecture-Based Lung Cancer Detection Using Chest Radiograph and Computerized Tomography Images. Bioengineering (Basel) 2024; 11:799. [PMID: 39199758 PMCID: PMC11351577 DOI: 10.3390/bioengineering11080799] [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: 06/20/2024] [Revised: 07/28/2024] [Accepted: 08/02/2024] [Indexed: 09/01/2024] Open
Abstract
Lung cancer, the second most common type of cancer worldwide, presents significant health challenges. Detecting this disease early is essential for improving patient outcomes and simplifying treatment. In this study, we propose a hybrid framework that combines deep learning (DL) with quantum computing to enhance the accuracy of lung cancer detection using chest radiographs (CXR) and computerized tomography (CT) images. Our system utilizes pre-trained models for feature extraction and quantum circuits for classification, achieving state-of-the-art performance in various metrics. Not only does our system achieve an overall accuracy of 92.12%, it also excels in other crucial performance measures, such as sensitivity (94%), specificity (90%), F1-score (93%), and precision (92%). These results demonstrate that our hybrid approach can more accurately identify lung cancer signatures compared to traditional methods. Moreover, the incorporation of quantum computing enhances processing speed and scalability, making our system a promising tool for early lung cancer screening and diagnosis. By leveraging the strengths of quantum computing, our approach surpasses traditional methods in terms of speed, accuracy, and efficiency. This study highlights the potential of hybrid computational technologies to transform early cancer detection, paving the way for wider clinical applications and improved patient care outcomes.
Collapse
Affiliation(s)
- Jason Elroy Martis
- Department of ISE, NMAM Institute of Technology, Nitte Deemed to be University, Udupi 574110, Karnataka, India (B.R.)
| | - Sannidhan M S
- Department of CSE, NMAM Institute of Technology, Nitte Deemed to be University, Udupi 574110, Karnataka, India;
| | - Balasubramani R
- Department of ISE, NMAM Institute of Technology, Nitte Deemed to be University, Udupi 574110, Karnataka, India (B.R.)
| | - A. M. Mutawa
- Computer Engineering Department, College of Engineering and Petroleum, Kuwait University, Safat 13060, Kuwait
- Computer Sciences Department, University of Hamburg, 22527 Hamburg, Germany
| | - M. Murugappan
- Intelligent Signal Processing (ISP) Research Lab, Department of Electronics and Communication Engineering, Kuwait College of Science and Technology, Block 4, Doha 13133, Kuwait
- Department of Electronics and Communication Engineering, School of Engineering, Vels Institute of Sciences, Technology, and Advanced Studies, Chennai 600117, Tamil Nadu, India
- Center of Excellence for Unmanned Aerial Systems (CoEUAS), Universiti Malaysia Perlis, Arau 02600, Malaysia
| |
Collapse
|
3
|
Ali IE, Sumita Y, Wakabayashi N. Advancing maxillofacial prosthodontics by using pre-trained convolutional neural networks: Image-based classification of the maxilla. J Prosthodont 2024; 33:645-654. [PMID: 38566564 DOI: 10.1111/jopr.13853] [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: 11/21/2023] [Accepted: 03/15/2024] [Indexed: 04/04/2024] Open
Abstract
PURPOSE The study aimed to compare the performance of four pre-trained convolutional neural networks in recognizing seven distinct prosthodontic scenarios involving the maxilla, as a preliminary step in developing an artificial intelligence (AI)-powered prosthesis design system. MATERIALS AND METHODS Seven distinct classes, including cleft palate, dentulous maxillectomy, edentulous maxillectomy, reconstructed maxillectomy, completely dentulous, partially edentulous, and completely edentulous, were considered for recognition. Utilizing transfer learning and fine-tuned hyperparameters, four AI models (VGG16, Inception-ResNet-V2, DenseNet-201, and Xception) were employed. The dataset, consisting of 3541 preprocessed intraoral occlusal images, was divided into training, validation, and test sets. Model performance metrics encompassed accuracy, precision, recall, F1 score, area under the receiver operating characteristic curve (AUC), and confusion matrix. RESULTS VGG16, Inception-ResNet-V2, DenseNet-201, and Xception demonstrated comparable performance, with maximum test accuracies of 0.92, 0.90, 0.94, and 0.95, respectively. Xception and DenseNet-201 slightly outperformed the other models, particularly compared with InceptionResNet-V2. Precision, recall, and F1 scores exceeded 90% for most classes in Xception and DenseNet-201 and the average AUC values for all models ranged between 0.98 and 1.00. CONCLUSIONS While DenseNet-201 and Xception demonstrated superior performance, all models consistently achieved diagnostic accuracy exceeding 90%, highlighting their potential in dental image analysis. This AI application could help work assignments based on difficulty levels and enable the development of an automated diagnosis system at patient admission. It also facilitates prosthesis designing by integrating necessary prosthesis morphology, oral function, and treatment difficulty. Furthermore, it tackles dataset size challenges in model optimization, providing valuable insights for future research.
Collapse
Affiliation(s)
- Islam E Ali
- Department of Advanced Prosthodontics, Graduate School of Medical and Dental Sciences, Tokyo Medical and Dental University, Tokyo, Japan
- Department of Prosthodontics, Faculty of Dentistry, Mansoura University, Mansoura, Egypt
| | - Yuka Sumita
- Division of General Dentistry 4, The Nippon Dental University Hospital, Tokyo, Japan
- Graduate School of Medical and Dental Sciences, Tokyo Medical and Dental University, Tokyo, Japan
| | - Noriyuki Wakabayashi
- Department of Advanced Prosthodontics, Graduate School of Medical and Dental Sciences, Tokyo Medical and Dental University, Tokyo, Japan
| |
Collapse
|
4
|
Okazaki S, Mine Y, Yoshimi Y, Iwamoto Y, Ito S, Peng TY, Nishimura T, Suehiro T, Koizumi Y, Nomura R, Tanimoto K, Kakimoto N, Murayama T. RadImageNet and ImageNet as Datasets for Transfer Learning in the Assessment of Dental Radiographs: A Comparative Study. JOURNAL OF IMAGING INFORMATICS IN MEDICINE 2024:10.1007/s10278-024-01204-9. [PMID: 39048809 DOI: 10.1007/s10278-024-01204-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 01/29/2024] [Revised: 07/14/2024] [Accepted: 07/15/2024] [Indexed: 07/27/2024]
Abstract
Transfer learning (TL) is an alternative approach to the full training of deep learning (DL) models from scratch and can transfer knowledge gained from large-scale data to solve different problems. ImageNet, which is a publicly available large-scale dataset, is a commonly used dataset for TL-based image analysis; many studies have applied pre-trained models from ImageNet to clinical prediction tasks and have reported promising results. However, some have questioned the effectiveness of using ImageNet, which consists solely of natural images, for medical image analysis. The aim of this study was to evaluate whether pre-trained models using RadImageNet, which is a large-scale medical image dataset, could achieve superior performance in classification tasks in dental imaging modalities compared with ImageNet pre-trained models. To evaluate the classification performance of RadImageNet and ImageNet pre-trained models for TL, two dental imaging datasets were used. The tasks were (1) classifying the presence or absence of supernumerary teeth from a dataset of panoramic radiographs and (2) classifying sex from a dataset of lateral cephalometric radiographs. Performance was evaluated by comparing the area under the curve (AUC). On the panoramic radiograph dataset, the RadImageNet models gave average AUCs of 0.68 ± 0.15 (p < 0.01), and the ImageNet models had values of 0.74 ± 0.19. In contrast, on the lateral cephalometric dataset, the RadImageNet models demonstrated average AUCs of 0.76 ± 0.09, and the ImageNet models achieved values of 0.75 ± 0.17. The difference in performance between RadImageNet and ImageNet models in TL depends on the dental image dataset used.
Collapse
Affiliation(s)
- Shota Okazaki
- Department of Medical Systems Engineering, Graduate School of Biomedical and Health Sciences, Hiroshima University, Hiroshima, Japan
- Project Research Center for Integrating Digital Dentistry, Hiroshima University, Hiroshima, Japan
| | - Yuichi Mine
- Department of Medical Systems Engineering, Graduate School of Biomedical and Health Sciences, Hiroshima University, Hiroshima, Japan.
- Project Research Center for Integrating Digital Dentistry, Hiroshima University, Hiroshima, Japan.
| | - Yuki Yoshimi
- Department of Orthodontics and Craniofacial Developmental Biology, Graduate School of Biomedical and Health Sciences, Hiroshima University, Hiroshima, Japan
| | - Yuko Iwamoto
- Department of Pediatric Dentistry, Graduate School of Biomedical and Health Sciences, Hiroshima University, Hiroshima, Japan
| | - Shota Ito
- Department of Orthodontics and Craniofacial Developmental Biology, Graduate School of Biomedical and Health Sciences, Hiroshima University, Hiroshima, Japan
| | - Tzu-Yu Peng
- School of Dentistry, College of Oral Medicine, Taipei Medical University, Taipei, Taiwan
| | - Taku Nishimura
- Department of Pediatric Dentistry, Graduate School of Biomedical and Health Sciences, Hiroshima University, Hiroshima, Japan
| | - Tomoya Suehiro
- Department of Genomic Oncology and Oral Medicine, Graduate School of Biomedical and Health Science, Hiroshima University, Hiroshima, Japan
| | - Yuma Koizumi
- Department of Orthodontics and Craniofacial Developmental Biology, Graduate School of Biomedical and Health Sciences, Hiroshima University, Hiroshima, Japan
| | - Ryota Nomura
- Department of Pediatric Dentistry, Graduate School of Biomedical and Health Sciences, Hiroshima University, Hiroshima, Japan
| | - Kotaro Tanimoto
- Department of Orthodontics and Craniofacial Developmental Biology, Graduate School of Biomedical and Health Sciences, Hiroshima University, Hiroshima, Japan
| | - Naoya Kakimoto
- Department of Oral and Maxillofacial Radiology, Graduate School of Biomedical and Health Sciences, Hiroshima University, Hiroshima, Japan
| | - Takeshi Murayama
- Department of Medical Systems Engineering, Graduate School of Biomedical and Health Sciences, Hiroshima University, Hiroshima, Japan.
- Project Research Center for Integrating Digital Dentistry, Hiroshima University, Hiroshima, Japan.
| |
Collapse
|
5
|
Choopong P, Kusakunniran W. Selection of pre-trained weights for transfer learning in automated cytomegalovirus retinitis classification. Sci Rep 2024; 14:15899. [PMID: 38987446 PMCID: PMC11237151 DOI: 10.1038/s41598-024-67121-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/27/2024] [Accepted: 07/08/2024] [Indexed: 07/12/2024] Open
Abstract
Cytomegalovirus retinitis (CMVR) is a significant cause of vision loss. Regular screening is crucial but challenging in resource-limited settings. A convolutional neural network is a state-of-the-art deep learning technique to generate automatic diagnoses from retinal images. However, there are limited numbers of CMVR images to train the model properly. Transfer learning (TL) is a strategy to train a model with a scarce dataset. This study explores the efficacy of TL with different pre-trained weights for automated CMVR classification using retinal images. We utilised a dataset of 955 retinal images (524 CMVR and 431 normal) from Siriraj Hospital, Mahidol University, collected between 2005 and 2015. Images were processed using Kowa VX-10i or VX-20 fundus cameras and augmented for training. We employed DenseNet121 as a backbone model, comparing the performance of TL with weights pre-trained on ImageNet, APTOS2019, and CheXNet datasets. The models were evaluated based on accuracy, loss, and other performance metrics, with the depth of fine-tuning varied across different pre-trained weights. The study found that TL significantly enhances model performance in CMVR classification. The best results were achieved with weights sequentially transferred from ImageNet to APTOS2019 dataset before application to our CMVR dataset. This approach yielded the highest mean accuracy (0.99) and lowest mean loss (0.04), outperforming other methods. The class activation heatmaps provided insights into the model's decision-making process. The model with APTOS2019 pre-trained weights offered the best explanation and highlighted the pathologic lesions resembling human interpretation. Our findings demonstrate the potential of sequential TL in improving the accuracy and efficiency of CMVR diagnosis, particularly in settings with limited data availability. They highlight the importance of domain-specific pre-training in medical image classification. This approach streamlines the diagnostic process and paves the way for broader applications in automated medical image analysis, offering a scalable solution for early disease detection.
Collapse
Affiliation(s)
- Pitipol Choopong
- Department of Ophthalmology, Faculty of Medicine Siriraj Hospital, Mahidol University, Bangkok, Thailand
- Faculty of Information and Communication Technology, Mahidol University, Nakhon Pathom, Thailand
| | - Worapan Kusakunniran
- Faculty of Information and Communication Technology, Mahidol University, Nakhon Pathom, Thailand.
| |
Collapse
|
6
|
Sandnes AT, Grimstad B, Kolbjørnsen O. Multi-task neural networks by learned contextual inputs. Neural Netw 2024; 179:106528. [PMID: 39024706 DOI: 10.1016/j.neunet.2024.106528] [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: 06/07/2023] [Revised: 05/29/2024] [Accepted: 07/07/2024] [Indexed: 07/20/2024]
Abstract
This paper explores learned-context neural networks. It is a multi-task learning architecture based on a fully shared neural network and an augmented input vector containing trainable task parameters. The architecture is interesting due to its powerful task adaption mechanism, which facilitates a low-dimensional task parameter space. Theoretically, we show that a scalar task parameter is sufficient for universal approximation of all tasks, which is not necessarily the case for more common architectures. Empirically it is shown that, for homogeneous tasks, the dimension of the task parameter may vary with the complexity of the tasks, but a small task parameter space is generally viable. The task parameter space is found to be well-behaved, which simplifies workflows related to updating models as new data arrives, and learning new tasks with the shared parameters are frozen. Additionally, the architecture displays robustness towards datasets where tasks have few data points. The architecture's performance is compared to similar neural network architectures on ten datasets, with competitive results.
Collapse
Affiliation(s)
- Anders T Sandnes
- Solution Seeker AS, Oslo, Norway; Department of Mathematics, University of Oslo, Oslo, Norway.
| | - Bjarne Grimstad
- Solution Seeker AS, Oslo, Norway; Department of Engineering Cybernetics, Norwegian University of Science and Technology, Trondheim, Norway
| | | |
Collapse
|
7
|
Chattopadhyay T, Ozarkar SS, Buwa K, Joshy NA, Komandur D, Naik J, Thomopoulos SI, Ver Steeg G, Ambite JL, Thompson PM. Comparison of deep learning architectures for predicting amyloid positivity in Alzheimer's disease, mild cognitive impairment, and healthy aging, from T1-weighted brain structural MRI. Front Neurosci 2024; 18:1387196. [PMID: 39015378 PMCID: PMC11250587 DOI: 10.3389/fnins.2024.1387196] [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: 02/16/2024] [Accepted: 06/14/2024] [Indexed: 07/18/2024] Open
Abstract
Abnormal β-amyloid (Aβ) accumulation in the brain is an early indicator of Alzheimer's disease (AD) and is typically assessed through invasive procedures such as PET (positron emission tomography) or CSF (cerebrospinal fluid) assays. As new anti-Alzheimer's treatments can now successfully target amyloid pathology, there is a growing interest in predicting Aβ positivity (Aβ+) from less invasive, more widely available types of brain scans, such as T1-weighted (T1w) MRI. Here we compare multiple approaches to infer Aβ + from standard anatomical MRI: (1) classical machine learning algorithms, including logistic regression, XGBoost, and shallow artificial neural networks, (2) deep learning models based on 2D and 3D convolutional neural networks (CNNs), (3) a hybrid ANN-CNN, combining the strengths of shallow and deep neural networks, (4) transfer learning models based on CNNs, and (5) 3D Vision Transformers. All models were trained on paired MRI/PET data from 1,847 elderly participants (mean age: 75.1 yrs. ± 7.6SD; 863 females/984 males; 661 healthy controls, 889 with mild cognitive impairment (MCI), and 297 with Dementia), scanned as part of the Alzheimer's Disease Neuroimaging Initiative. We evaluated each model's balanced accuracy and F1 scores. While further tests on more diverse data are warranted, deep learning models trained on standard MRI showed promise for estimating Aβ + status, at least in people with MCI. This may offer a potential screening option before resorting to more invasive procedures.
Collapse
Affiliation(s)
- Tamoghna Chattopadhyay
- Imaging Genetics Center, Mark and Mary Stevens Neuroimaging and Informatics Institute, Keck School of Medicine, University of Southern California, Marina del Rey, CA, United States
| | - Saket S. Ozarkar
- Imaging Genetics Center, Mark and Mary Stevens Neuroimaging and Informatics Institute, Keck School of Medicine, University of Southern California, Marina del Rey, CA, United States
| | - Ketaki Buwa
- Imaging Genetics Center, Mark and Mary Stevens Neuroimaging and Informatics Institute, Keck School of Medicine, University of Southern California, Marina del Rey, CA, United States
| | - Neha Ann Joshy
- Imaging Genetics Center, Mark and Mary Stevens Neuroimaging and Informatics Institute, Keck School of Medicine, University of Southern California, Marina del Rey, CA, United States
| | - Dheeraj Komandur
- Imaging Genetics Center, Mark and Mary Stevens Neuroimaging and Informatics Institute, Keck School of Medicine, University of Southern California, Marina del Rey, CA, United States
| | - Jayati Naik
- Imaging Genetics Center, Mark and Mary Stevens Neuroimaging and Informatics Institute, Keck School of Medicine, University of Southern California, Marina del Rey, CA, United States
| | - Sophia I. Thomopoulos
- Imaging Genetics Center, Mark and Mary Stevens Neuroimaging and Informatics Institute, Keck School of Medicine, University of Southern California, Marina del Rey, CA, United States
| | | | - Jose Luis Ambite
- Information Sciences Institute, University of Southern California, Marina del Rey, CA, United States
| | - Paul M. Thompson
- Imaging Genetics Center, Mark and Mary Stevens Neuroimaging and Informatics Institute, Keck School of Medicine, University of Southern California, Marina del Rey, CA, United States
| |
Collapse
|
8
|
Jeong HK, Park C, Jiang SW, Nicholas M, Chen S, Henao R, Kheterpal M. Image Quality Assessment Using Convolutional Neural Network in Clinical Skin Images. JID INNOVATIONS 2024; 4:100285. [PMID: 39036289 PMCID: PMC11260318 DOI: 10.1016/j.xjidi.2024.100285] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/03/2023] [Revised: 12/24/2023] [Accepted: 03/06/2024] [Indexed: 07/23/2024] Open
Abstract
The image quality received for clinical evaluation is often suboptimal. The goal is to develop an image quality analysis tool to assess patient- and primary care physician-derived images using deep learning model. Dataset included patient- and primary care physician-derived images from August 21, 2018 to June 30, 2022 with 4 unique quality labels. VGG16 model was fine tuned with input data, and optimal threshold was determined by Youden's index. Ordinal labels were transformed to binary labels using a majority vote because model distinguishes between 2 categories (good vs bad). At a threshold of 0.587, area under the curve for the test set was 0.885 (95% confidence interval = 0.838-0.933); sensitivity, specificity, positive predictive value, and negative predictive value were 0.829, 0.784, 0.906, and 0.645, respectively. Independent validation of 300 additional images (from patients and primary care physicians) demonstrated area under the curve of 0.864 (95% confidence interval = 0.818-0.909) and area under the curve of 0.902 (95% confidence interval = 0.85-0.95), respectively. The sensitivity, specificity, positive predictive value, and negative predictive value for the 300 images were 0.827, 0.800, 0.959, and 0.450, respectively. We demonstrate a practical approach improving the image quality for clinical workflow. Although users may have to capture additional images, this is offset by the improved workload and efficiency for clinical teams.
Collapse
Affiliation(s)
- Hyeon Ki Jeong
- Department of Biostatistics & Bioinformatics, Duke University School of Medicine, Durham, North Carolina, USA
| | - Christine Park
- Duke University School of Medicine, Durham, North Carolina, USA
| | - Simon W. Jiang
- Duke University School of Medicine, Durham, North Carolina, USA
| | - Matilda Nicholas
- Department of Dermatology, Duke University School of Medicine, Durham, North Carolina, USA
| | - Suephy Chen
- Department of Dermatology, Duke University School of Medicine, Durham, North Carolina, USA
- Durham VA Medical Center, Durham, North Carolina, USA
| | - Ricardo Henao
- Department of Biostatistics & Bioinformatics, Duke University School of Medicine, Durham, North Carolina, USA
| | - Meenal Kheterpal
- Department of Dermatology, Duke University School of Medicine, Durham, North Carolina, USA
| |
Collapse
|
9
|
Kolhar M, Al Rajeh AM, Kazi RNA. Augmenting Radiological Diagnostics with AI for Tuberculosis and COVID-19 Disease Detection: Deep Learning Detection of Chest Radiographs. Diagnostics (Basel) 2024; 14:1334. [PMID: 39001228 PMCID: PMC11240993 DOI: 10.3390/diagnostics14131334] [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: 05/11/2024] [Revised: 06/18/2024] [Accepted: 06/21/2024] [Indexed: 07/16/2024] Open
Abstract
In this research, we introduce a network that can identify pneumonia, COVID-19, and tuberculosis using X-ray images of patients' chests. The study emphasizes tuberculosis, COVID-19, and healthy lung conditions, discussing how advanced neural networks, like VGG16 and ResNet50, can improve the detection of lung issues from images. To prepare the images for the model's input requirements, we enhanced them through data augmentation techniques for training purposes. We evaluated the model's performance by analyzing the precision, recall, and F1 scores across training, validation, and testing datasets. The results show that the ResNet50 model outperformed VGG16 with accuracy and resilience. It displayed superior ROC AUC values in both validation and test scenarios. Particularly impressive were ResNet50's precision and recall rates, nearing 0.99 for all conditions in the test set. On the hand, VGG16 also performed well during testing-detecting tuberculosis with a precision of 0.99 and a recall of 0.93. Our study highlights the performance of our deep learning method by showcasing the effectiveness of ResNet50 over traditional approaches like VGG16. This progress utilizes methods to enhance classification accuracy by augmenting data and balancing them. This positions our approach as an advancement in using state-of-the-art deep learning applications in imaging. By enhancing the accuracy and reliability of diagnosing ailments such as COVID-19 and tuberculosis, our models have the potential to transform care and treatment strategies, highlighting their role in clinical diagnostics.
Collapse
Affiliation(s)
- Manjur Kolhar
- Department Health Informatics, College of Applied Medical Sciences, King Faisal University, Al-Hofuf 31982, Saudi Arabia
| | - Ahmed M Al Rajeh
- College of Applied Medical Sciences, King Faisal University, Al-Hofuf 31982, Saudi Arabia
| | - Raisa Nazir Ahmed Kazi
- College of Applied Medical Sciences, King Faisal University, Al-Hofuf 31982, Saudi Arabia
| |
Collapse
|
10
|
Hase H, Mine Y, Okazaki S, Yoshimi Y, Ito S, Peng TY, Sano M, Koizumi Y, Kakimoto N, Tanimoto K, Murayama T. Sex estimation from maxillofacial radiographs using a deep learning approach. Dent Mater J 2024; 43:394-399. [PMID: 38599831 DOI: 10.4012/dmj.2023-253] [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: 04/12/2024]
Abstract
The purpose of this study was to construct deep learning models for more efficient and reliable sex estimation. Two deep learning models, VGG16 and DenseNet-121, were used in this retrospective study. In total, 600 lateral cephalograms were analyzed. A saliency map was generated by gradient-weighted class activation mapping for each output. The two deep learning models achieved high values in each performance metric according to accuracy, sensitivity (recall), precision, F1 score, and areas under the receiver operating characteristic curve. Both models showed substantial differences in the positions indicated in saliency maps for male and female images. The positions in saliency maps also differed between VGG16 and DenseNet-121, regardless of sex. This analysis of our proposed system suggested that sex estimation from lateral cephalograms can be achieved with high accuracy using deep learning.
Collapse
Affiliation(s)
- Hiroki Hase
- Department of Medical Systems Engineering, Graduate School of Biomedical and Health Sciences, Hiroshima University
| | - Yuichi Mine
- Department of Medical Systems Engineering, Graduate School of Biomedical and Health Sciences, Hiroshima University
- Project Research Center for Integrating Digital Dentistry, Hiroshima University
| | - Shota Okazaki
- Department of Medical Systems Engineering, Graduate School of Biomedical and Health Sciences, Hiroshima University
- Project Research Center for Integrating Digital Dentistry, Hiroshima University
| | - Yuki Yoshimi
- Department of Orthodontics and Craniofacial Developmental Biology, Graduate School of Biomedical and Health Sciences, Hiroshima University
| | - Shota Ito
- Department of Orthodontics and Craniofacial Developmental Biology, Graduate School of Biomedical and Health Sciences, Hiroshima University
| | - Tzu-Yu Peng
- School of Dentistry, College of Oral Medicine, Taipei Medical University
| | - Mizuho Sano
- Department of Medical Systems Engineering, Graduate School of Biomedical and Health Sciences, Hiroshima University
| | - Yuma Koizumi
- Department of Orthodontics and Craniofacial Developmental Biology, Graduate School of Biomedical and Health Sciences, Hiroshima University
| | - Naoya Kakimoto
- School of Dentistry, College of Oral Medicine, Taipei Medical University
| | - Kotaro Tanimoto
- Department of Oral and Maxillofacial Radiology, Graduate School of Biomedical and Health Sciences, Hiroshima University
| | - Takeshi Murayama
- Department of Medical Systems Engineering, Graduate School of Biomedical and Health Sciences, Hiroshima University
- Project Research Center for Integrating Digital Dentistry, Hiroshima University
| |
Collapse
|
11
|
Connolly L, Fooladgar F, Jamzad A, Kaufmann M, Syeda A, Ren K, Abolmaesumi P, Rudan JF, McKay D, Fichtinger G, Mousavi P. ImSpect: Image-driven self-supervised learning for surgical margin evaluation with mass spectrometry. Int J Comput Assist Radiol Surg 2024; 19:1129-1136. [PMID: 38600411 DOI: 10.1007/s11548-024-03106-1] [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: 03/07/2024] [Accepted: 03/08/2024] [Indexed: 04/12/2024]
Abstract
PURPOSE Real-time assessment of surgical margins is critical for favorable outcomes in cancer patients. The iKnife is a mass spectrometry device that has demonstrated potential for margin detection in cancer surgery. Previous studies have shown that using deep learning on iKnife data can facilitate real-time tissue characterization. However, none of the existing literature on the iKnife facilitate the use of publicly available, state-of-the-art pretrained networks or datasets that have been used in computer vision and other domains. METHODS In a new framework we call ImSpect, we convert 1D iKnife data, captured during basal cell carcinoma (BCC) surgery, into 2D images in order to capitalize on state-of-the-art image classification networks. We also use self-supervision to leverage large amounts of unlabeled, intraoperative data to accommodate the data requirements of these networks. RESULTS Through extensive ablation studies, we show that we can surpass previous benchmarks of margin evaluation in BCC surgery using iKnife data, achieving an area under the receiver operating characteristic curve (AUC) of 81%. We also depict the attention maps of the developed DL models to evaluate the biological relevance of the embedding space CONCLUSIONS: We propose a new method for characterizing tissue at the surgical margins, using mass spectrometry data from cancer surgery.
Collapse
Affiliation(s)
| | | | | | | | | | - Kevin Ren
- Queen's University, Kingston, ON, Canada
| | | | | | - Doug McKay
- Queen's University, Kingston, ON, Canada
| | | | | |
Collapse
|
12
|
Han X, Chen Z, Lin G, Lv W, Zheng C, Lu W, Sun Y, Lu L. Semi-supervised model based on implicit neural representation and mutual learning (SIMN) for multi-center nasopharyngeal carcinoma segmentation on MRI. Comput Biol Med 2024; 175:108368. [PMID: 38663351 DOI: 10.1016/j.compbiomed.2024.108368] [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: 08/25/2023] [Revised: 03/06/2024] [Accepted: 03/24/2024] [Indexed: 05/15/2024]
Abstract
BACKGROUND The issue of using deep learning to obtain accurate gross tumor volume (GTV) and metastatic lymph nodes (MLN) segmentation for nasopharyngeal carcinoma (NPC) on heterogeneous magnetic resonance imaging (MRI) images with limited labeling remains unsolved. METHOD We collected 918 patients with MRI images from three hospitals to develop and validate models and proposed a semi-supervised framework for the fine delineation of multi-center NPC boundaries by integrating uncertainty-based implicit neural representations named SIMN. The framework utilizes the deep mutual learning approach with CNN and Transformer, incorporating dynamic thresholds. Additionally, domain adaptive algorithms are employed to enhance the performance. RESULTS SIMN predictions have a high overlap ratio with the ground truth. Under the 20 % labeled cases, for the internal test cohorts, the average DSC in GTV and MLN are 0.7981 and 0.7804, respectively; for external test cohort Wu Zhou Red Cross Hospital, the average DSC in GTV and MLN are 0.7217 and 0.7581, respectively; for external test cohorts First People Hospital of Foshan, the average DSC in GTV and MLN are 0.7004 and 0.7692, respectively. No significant differences are found in DSC, HD95, ASD, and Recall for patients with different clinical categories. Moreover, SIMN outperformed existing classical semi-supervised methods. CONCLUSIONS SIMN showed a highly accurate GTV and MLN segmentation for NPC on multi-center MRI images under Semi-Supervised Learning (SSL), which can easily transfer to other centers without fine-tuning. It suggests that it has the potential to act as a generalized delineation solution for heterogeneous MRI images with limited labels in clinical deployment.
Collapse
Affiliation(s)
- Xu Han
- School of Biomedical Engineering, Southern Medical University, 1023 Shatai Road, Guangzhou, 510515, China; School of Biomedical Engineering and Guangdong Provincial Key Laboratory of Medical Image Processing, Southern Medical University, 1023 Shatai Road, Guangzhou, 510515, China; Guangdong Province Engineering Laboratory for Medical Imaging and Diagnostic Technology, Southern Medical University, 1023 Shatai Road, Guangzhou, 510515, China; Pazhou Lab, Guangzhou, 510515, China
| | - Zihang Chen
- Department of Radiation Oncology, Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy, Guangzhou, 510060, China
| | - Guoyu Lin
- School of Biomedical Engineering, Southern Medical University, 1023 Shatai Road, Guangzhou, 510515, China; School of Biomedical Engineering and Guangdong Provincial Key Laboratory of Medical Image Processing, Southern Medical University, 1023 Shatai Road, Guangzhou, 510515, China; Department of Radiation Oncology, Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy, Guangzhou, 510060, China
| | - Wenbing Lv
- School of Information Science and Engineering, Yunnan University, Kunming, 650504, China
| | - Chundan Zheng
- School of Biomedical Engineering, Southern Medical University, 1023 Shatai Road, Guangzhou, 510515, China; School of Biomedical Engineering and Guangdong Provincial Key Laboratory of Medical Image Processing, Southern Medical University, 1023 Shatai Road, Guangzhou, 510515, China; Guangdong Province Engineering Laboratory for Medical Imaging and Diagnostic Technology, Southern Medical University, 1023 Shatai Road, Guangzhou, 510515, China; Pazhou Lab, Guangzhou, 510515, China
| | - Wantong Lu
- School of Biomedical Engineering, Southern Medical University, 1023 Shatai Road, Guangzhou, 510515, China; School of Biomedical Engineering and Guangdong Provincial Key Laboratory of Medical Image Processing, Southern Medical University, 1023 Shatai Road, Guangzhou, 510515, China; Guangdong Province Engineering Laboratory for Medical Imaging and Diagnostic Technology, Southern Medical University, 1023 Shatai Road, Guangzhou, 510515, China; Pazhou Lab, Guangzhou, 510515, China
| | - Ying Sun
- Department of Radiation Oncology, Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy, Guangzhou, 510060, China.
| | - Lijun Lu
- School of Biomedical Engineering, Southern Medical University, 1023 Shatai Road, Guangzhou, 510515, China; School of Biomedical Engineering and Guangdong Provincial Key Laboratory of Medical Image Processing, Southern Medical University, 1023 Shatai Road, Guangzhou, 510515, China; Guangdong Province Engineering Laboratory for Medical Imaging and Diagnostic Technology, Southern Medical University, 1023 Shatai Road, Guangzhou, 510515, China; Pazhou Lab, Guangzhou, 510515, China.
| |
Collapse
|
13
|
Sheng H, Ma L, Samson JF, Liu D. BarlowTwins-CXR: enhancing chest X-ray abnormality localization in heterogeneous data with cross-domain self-supervised learning. BMC Med Inform Decis Mak 2024; 24:126. [PMID: 38755563 PMCID: PMC11097466 DOI: 10.1186/s12911-024-02529-9] [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: 02/16/2024] [Accepted: 05/07/2024] [Indexed: 05/18/2024] Open
Abstract
BACKGROUND Chest X-ray imaging based abnormality localization, essential in diagnosing various diseases, faces significant clinical challenges due to complex interpretations and the growing workload of radiologists. While recent advances in deep learning offer promising solutions, there is still a critical issue of domain inconsistency in cross-domain transfer learning, which hampers the efficiency and accuracy of diagnostic processes. This study aims to address the domain inconsistency problem and improve autonomic abnormality localization performance of heterogeneous chest X-ray image analysis, particularly in detecting abnormalities, by developing a self-supervised learning strategy called "BarlwoTwins-CXR". METHODS We utilized two publicly available datasets: the NIH Chest X-ray Dataset and the VinDr-CXR. The BarlowTwins-CXR approach was conducted in a two-stage training process. Initially, self-supervised pre-training was performed using an adjusted Barlow Twins algorithm on the NIH dataset with a Resnet50 backbone pre-trained on ImageNet. This was followed by supervised fine-tuning on the VinDr-CXR dataset using Faster R-CNN with Feature Pyramid Network (FPN). The study employed mean Average Precision (mAP) at an Intersection over Union (IoU) of 50% and Area Under the Curve (AUC) for performance evaluation. RESULTS Our experiments showed a significant improvement in model performance with BarlowTwins-CXR. The approach achieved a 3% increase in mAP50 accuracy compared to traditional ImageNet pre-trained models. In addition, the Ablation CAM method revealed enhanced precision in localizing chest abnormalities. The study involved 112,120 images from the NIH dataset and 18,000 images from the VinDr-CXR dataset, indicating robust training and testing samples. CONCLUSION BarlowTwins-CXR significantly enhances the efficiency and accuracy of chest X-ray image-based abnormality localization, outperforming traditional transfer learning methods and effectively overcoming domain inconsistency in cross-domain scenarios. Our experiment results demonstrate the potential of using self-supervised learning to improve the generalizability of models in medical settings with limited amounts of heterogeneous data. This approach can be instrumental in aiding radiologists, particularly in high-workload environments, offering a promising direction for future AI-driven healthcare solutions.
Collapse
Affiliation(s)
- Haoyue Sheng
- Département d'informatique et de recherche opérationnelle, Université de Montréal, 2920 chemin de la Tour, Montréal, H3T 1J4, QC, Canada.
- Mila - Quebec AI Institute, 6666 Rue Saint-Urbain, Montréal, H2S 3H1, QC, Canada.
- Direction des ressources informationnelles, CIUSSS du Centre-Sud-de-l'Île-de-Montréal, 400 Blvd. De Maisonneuve Ouest, Montréal, H3A 1L4, QC, Canada.
| | - Linrui Ma
- Département d'informatique et de recherche opérationnelle, Université de Montréal, 2920 chemin de la Tour, Montréal, H3T 1J4, QC, Canada
- Mila - Quebec AI Institute, 6666 Rue Saint-Urbain, Montréal, H2S 3H1, QC, Canada
| | - Jean-François Samson
- Direction des ressources informationnelles, CIUSSS du Centre-Sud-de-l'Île-de-Montréal, 400 Blvd. De Maisonneuve Ouest, Montréal, H3A 1L4, QC, Canada
| | - Dianbo Liu
- Mila - Quebec AI Institute, 6666 Rue Saint-Urbain, Montréal, H2S 3H1, QC, Canada
- School of Medicine and College of Design and Engineering, National University of Singapore, 21 Lower Kent Ridge Rd, Singapore, 119077, SG, Singapore
| |
Collapse
|
14
|
Shobayo O, Saatchi R, Ramlakhan S. Convolutional Neural Network to Classify Infrared Thermal Images of Fractured Wrists in Pediatrics. Healthcare (Basel) 2024; 12:994. [PMID: 38786405 PMCID: PMC11121475 DOI: 10.3390/healthcare12100994] [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: 04/09/2024] [Revised: 05/02/2024] [Accepted: 05/10/2024] [Indexed: 05/25/2024] Open
Abstract
Convolutional neural network (CNN) models were devised and evaluated to classify infrared thermal (IRT) images of pediatric wrist fractures. The images were recorded from 19 participants with a wrist fracture and 21 without a fracture (sprain). The injury diagnosis was by X-ray radiography. For each participant, 299 IRT images of their wrists were recorded. These generated 11,960 images (40 participants × 299 images). For each image, the wrist region of interest (ROI) was selected and fast Fourier transformed (FFT) to obtain a magnitude frequency spectrum. The spectrum was resized to 100 × 100 pixels from its center as this region represented the main frequency components. Image augmentations of rotation, translation and shearing were applied to the 11,960 magnitude frequency spectra to assist with the CNN generalization during training. The CNN had 34 layers associated with convolution, batch normalization, rectified linear unit, maximum pooling and SoftMax and classification. The ratio of images for the training and test was 70:30, respectively. The effects of augmentation and dropout on CNN performance were explored. Wrist fracture identification sensitivity and accuracy of 88% and 76%, respectively, were achieved. The CNN model was able to identify wrist fractures; however, a larger sample size would improve accuracy.
Collapse
Affiliation(s)
- Olamilekan Shobayo
- Department of Computing, Sheffield Hallam University, Sheffield S1 2NU, UK;
| | - Reza Saatchi
- Department of Engineering and Mathematics, Sheffield Hallam University, Sheffield S1 1WB, UK
| | - Shammi Ramlakhan
- Emergency Department, Sheffield Children’s Hospital NHS Foundation Trust, Sheffield S10 2TH, UK;
| |
Collapse
|
15
|
Büyükçakır B, Bertels J, Claes P, Vandermeulen D, de Tobel J, Thevissen PW. OPG-based dental age estimation using a data-technical exploration of deep learning techniques. J Forensic Sci 2024; 69:919-931. [PMID: 38291770 DOI: 10.1111/1556-4029.15473] [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: 11/07/2023] [Revised: 01/07/2024] [Accepted: 01/16/2024] [Indexed: 02/01/2024]
Abstract
Dental age estimation, a cornerstone in forensic age assessment, has been extensively tried and tested, yet manual methods are impeded by tedium and interobserver variability. Automated approaches using deep transfer learning encounter challenges like data scarcity, suboptimal training, and fine-tuning complexities, necessitating robust training methods. This study explores the impact of convolutional neural network hyperparameters, model complexity, training batch size, and sample quantity on age estimation. EfficientNet-B4, DenseNet-201, and MobileNet V3 models underwent cross-validation on a dataset of 3896 orthopantomograms (OPGs) with batch sizes escalating from 10 to 160 in a doubling progression, as well as random subsets of this training dataset. Results demonstrate the EfficientNet-B4 model, trained on the complete dataset with a batch size of 160, as the top performer with a mean absolute error of 0.562 years on the test set, notably surpassing the MAE of 1.01 at a batch size of 10. Increasing batch size consistently improved performance for EfficientNet-B4 and DenseNet-201, whereas MobileNet V3 performance peaked at batch size 40. Similar trends emerged in training with reduced sample sizes, though they were outperformed by the complete models. This underscores the critical role of hyperparameter optimization in adopting deep learning for age estimation from complete OPGs. The findings not only highlight the nuanced interplay of hyperparameters and performance but also underscore the potential for accurate age estimation models through optimization. This study contributes to advancing the application of deep learning in forensic age estimation, emphasizing the significance of tailored training methodologies for optimal outcomes.
Collapse
Affiliation(s)
- Barkın Büyükçakır
- ESAT, Center for Processing Speech and Images, KU Leuven, Leuven, Belgium
| | - Jeroen Bertels
- ESAT, Center for Processing Speech and Images, KU Leuven, Leuven, Belgium
| | - Peter Claes
- ESAT, Center for Processing Speech and Images, KU Leuven, Leuven, Belgium
| | - Dirk Vandermeulen
- ESAT, Center for Processing Speech and Images, KU Leuven, Leuven, Belgium
| | - Jannick de Tobel
- Department of Diagnostic Sciences and Radiology, Ghent University, Ghent, Belgium
| | | |
Collapse
|
16
|
Moharrami M, Farmer J, Singhal S, Watson E, Glogauer M, Johnson AEW, Schwendicke F, Quinonez C. Detecting dental caries on oral photographs using artificial intelligence: A systematic review. Oral Dis 2024; 30:1765-1783. [PMID: 37392423 DOI: 10.1111/odi.14659] [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: 03/21/2023] [Revised: 05/19/2023] [Accepted: 06/15/2023] [Indexed: 07/03/2023]
Abstract
OBJECTIVES This systematic review aimed at evaluating the performance of artificial intelligence (AI) models in detecting dental caries on oral photographs. METHODS Methodological characteristics and performance metrics of clinical studies reporting on deep learning and other machine learning algorithms were assessed. The risk of bias was evaluated using the quality assessment of diagnostic accuracy studies 2 (QUADAS-2) tool. A systematic search was conducted in EMBASE, Medline, and Scopus. RESULTS Out of 3410 identified records, 19 studies were included with six and seven studies having low risk of biases and applicability concerns for all the domains, respectively. Metrics varied widely and were assessed on multiple levels. F1-scores for classification and detection tasks were 68.3%-94.3% and 42.8%-95.4%, respectively. Irrespective of the task, F1-scores were 68.3%-95.4% for professional cameras, 78.8%-87.6%, for intraoral cameras, and 42.8%-80% for smartphone cameras. Limited studies allowed assessing AI performance for lesions of different severity. CONCLUSION Automatic detection of dental caries using AI may provide objective verification of clinicians' diagnoses and facilitate patient-clinician communication and teledentistry. Future studies should consider more robust study designs, employ comparable and standardized metrics, and focus on the severity of caries lesions.
Collapse
Affiliation(s)
- Mohammad Moharrami
- Faculty of Dentistry, University of Toronto, Toronto, Ontario, Canada
- Topic Group Dental Diagnostics and Digital Dentistry, ITU/WHO Focus Group AI on Health, Geneva, Switzerland
| | - Julie Farmer
- Faculty of Dentistry, University of Toronto, Toronto, Ontario, Canada
| | - Sonica Singhal
- Faculty of Dentistry, University of Toronto, Toronto, Ontario, Canada
- Health Promotion, Chronic Disease and Injury Prevention Department, Public Health Ontario, Toronto, Canada
| | - Erin Watson
- Faculty of Dentistry, University of Toronto, Toronto, Ontario, Canada
- Department of Dental Oncology, Princess Margaret Cancer Centre, Toronto, Ontario, Canada
| | - Michael Glogauer
- Faculty of Dentistry, University of Toronto, Toronto, Ontario, Canada
- Department of Dental Oncology, Princess Margaret Cancer Centre, Toronto, Ontario, Canada
- Department of Dentistry, Centre for Advanced Dental Research and Care, Mount Sinai Hospital, Toronto, Ontario, Canada
| | - Alistair E W Johnson
- Program in Child Health Evaluative Sciences, The Hospital for Sick Children, Toronto, Ontario, Canada
| | - Falk Schwendicke
- Topic Group Dental Diagnostics and Digital Dentistry, ITU/WHO Focus Group AI on Health, Geneva, Switzerland
- Oral Diagnostics, Digital Health and Health Services Research, Charité - Universitätsmedizin Berlin, Berlin, Germany
| | - Carlos Quinonez
- Faculty of Dentistry, University of Toronto, Toronto, Ontario, Canada
- Schulich School of Medicine and Dentistry, Western University, London, Ontario, Canada
| |
Collapse
|
17
|
Wang Z, Song J, Lin K, Hong W, Mao S, Wu X, Zhang J. Automated detection of otosclerosis with interpretable deep learning using temporal bone computed tomography images. Heliyon 2024; 10:e29670. [PMID: 38655358 PMCID: PMC11036044 DOI: 10.1016/j.heliyon.2024.e29670] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/25/2023] [Revised: 04/10/2024] [Accepted: 04/12/2024] [Indexed: 04/26/2024] Open
Abstract
Objective This study aimed to develop an automated detection schema for otosclerosis with interpretable deep learning using temporal bone computed tomography images. Methods With approval from the institutional review board, we retrospectively analyzed high-resolution computed tomography scans of the temporal bone of 182 participants with otosclerosis (67 male subjects and 115 female subjects; average age, 36.42 years) and 157 participants without otosclerosis (52 male subjects and 102 female subjects; average age, 30.61 years) using deep learning. Transfer learning with the pretrained VGG19, Mask RCNN, and EfficientNet models was used. In addition, 3 clinical experts compared the system's performance by reading the same computed tomography images for a subset of 35 unseen subjects. An area under the receiver operating characteristic curve and a saliency map were used to further evaluate the diagnostic performance. Results In prospective unseen test data, the diagnostic performance of the automatically interpretable otosclerosis detection system at the optimal threshold was 0.97 and 0.98 for sensitivity and specificity, respectively. In comparison with the clinical acumen of otolaryngologists at P < 0.05, the proposed system was not significantly different. Moreover, the area under the receiver operating characteristic curve for the proposed system was 0.99, indicating satisfactory diagnostic accuracy. Conclusion Our research develops and evaluates a deep learning system that detects otosclerosis at a level comparable with clinical otolaryngologists. Our system is an effective schema for the differential diagnosis of otosclerosis in computed tomography examinations.
Collapse
Affiliation(s)
- Zheng Wang
- School of Computer Science, Hunan First Normal University, Changsha, 410205, China
- Key Laboratory of Informalization Technology for Basic Education in Hunan Province, Changsha, 410205, China
| | - Jian Song
- Department of Otorhinolaryngology, Xiangya Hospital Central South University, Changsha, Hunan, China
- Province Key Laboratory of Otolaryngology Critical Diseases, Changsha, Hunan, China
| | - Kaibin Lin
- School of Computer Science, Hunan First Normal University, Changsha, 410205, China
- Key Laboratory of Informalization Technology for Basic Education in Hunan Province, Changsha, 410205, China
| | - Wei Hong
- School of Computer Science, Hunan First Normal University, Changsha, 410205, China
- Key Laboratory of Informalization Technology for Basic Education in Hunan Province, Changsha, 410205, China
| | - Shuang Mao
- Department of Otorhinolaryngology, Xiangya Hospital Central South University, Changsha, Hunan, China
- Province Key Laboratory of Otolaryngology Critical Diseases, Changsha, Hunan, China
| | - Xuewen Wu
- Department of Otorhinolaryngology, Xiangya Hospital Central South University, Changsha, Hunan, China
- Province Key Laboratory of Otolaryngology Critical Diseases, Changsha, Hunan, China
| | - Jianglin Zhang
- Department of Dermatology, Shenzhen People's Hospital, The Second Clinical Medical College, Jinan University. The First Affiliated Hospital, Southern University of Science and Technology, Shenzhen, 518020, Guangdong, China
- Candidate Branch of National Clinical Research Center for Skin Diseases, Shenzhen, 518020, Guangdong, China
- Department of Geriatrics, Shenzhen People's Hospital, The Second Clinical Medical College, Jinan University. The First Affiliated Hospital, Southern University of Science and Technology, Shenzhen, 518020, Guangdong, China
| |
Collapse
|
18
|
Chen M, Zhang M, Yin L, Ma L, Ding R, Zheng T, Yue Q, Lui S, Sun H. Medical image foundation models in assisting diagnosis of brain tumors: a pilot study. Eur Radiol 2024:10.1007/s00330-024-10728-1. [PMID: 38627290 DOI: 10.1007/s00330-024-10728-1] [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: 10/23/2023] [Revised: 02/08/2024] [Accepted: 03/04/2024] [Indexed: 04/23/2024]
Abstract
OBJECTIVES To build self-supervised foundation models for multicontrast MRI of the whole brain and evaluate their efficacy in assisting diagnosis of brain tumors. METHODS In this retrospective study, foundation models were developed using 57,621 enhanced head MRI scans through self-supervised learning with a pretext task of cross-contrast context restoration with two different content dropout schemes. Downstream classifiers were constructed based on the pretrained foundation models and fine-tuned for brain tumor detection, discrimination, and molecular status prediction. Metrics including accuracy, sensitivity, specificity, and area under the ROC curve (AUC) were used to evaluate the performance. Convolutional neural networks trained exclusively on downstream task data were employed for comparative analysis. RESULTS The pretrained foundation models demonstrated their ability to extract effective representations from multicontrast whole-brain volumes. The best classifiers, endowed with pretrained weights, showed remarkable performance with accuracies of 94.9, 92.3, and 80.4%, and corresponding AUC values of 0.981, 0.972, and 0.852 on independent test datasets in brain tumor detection, discrimination, and molecular status prediction, respectively. The classifiers with pretrained weights outperformed the convolutional classifiers trained from scratch by approximately 10% in terms of accuracy and AUC across all tasks. The saliency regions in the correctly predicted cases are mainly clustered around the tumors. Classifiers derived from the two dropout schemes differed significantly only in the detection of brain tumors. CONCLUSIONS Foundation models obtained from self-supervised learning have demonstrated encouraging potential for scalability and interpretability in downstream brain tumor-related tasks and hold promise for extension to neurological diseases with diffusely distributed lesions. CLINICAL RELEVANCE STATEMENT The application of our proposed method to the prediction of key molecular status in gliomas is expected to improve treatment planning and patient outcomes. Additionally, the foundation model we developed could serve as a cornerstone for advancing AI applications in the diagnosis of brain-related diseases.
Collapse
Affiliation(s)
- Mengyao Chen
- Department of Radiology, West China Hospital of Sichuan University, Chengdu, China
- Huaxi MR Research Center (HMRRC), West China Hospital of Sichuan University, Chengdu, China
| | | | - Lijuan Yin
- Department of Pathology, West China Hospital of Sichuan University, Chengdu, China
| | - Lu Ma
- Department of Neurosurgery, West China Hospital of Sichuan University, Chengdu, China
| | - Renxing Ding
- IT center, West China Hospital of Sichuan University, Chengdu, China
| | - Tao Zheng
- IT center, West China Hospital of Sichuan University, Chengdu, China
| | - Qiang Yue
- Department of Radiology, West China Hospital of Sichuan University, Chengdu, China
- Huaxi MR Research Center (HMRRC), West China Hospital of Sichuan University, Chengdu, China
| | - Su Lui
- Department of Radiology, West China Hospital of Sichuan University, Chengdu, China
- Huaxi MR Research Center (HMRRC), West China Hospital of Sichuan University, Chengdu, China
| | - Huaiqiang Sun
- Department of Radiology, West China Hospital of Sichuan University, Chengdu, China.
- Huaxi MR Research Center (HMRRC), West China Hospital of Sichuan University, Chengdu, China.
| |
Collapse
|
19
|
Tang Z, Mahmoodi S, Meng D, Darekar A, Vollmer B. Rule-based deep learning method for prognosis of neonatal hypoxic-ischemic encephalopathy by using susceptibility weighted image analysis. MAGMA (NEW YORK, N.Y.) 2024; 37:227-239. [PMID: 38252196 DOI: 10.1007/s10334-023-01139-2] [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: 07/09/2023] [Revised: 12/06/2023] [Accepted: 12/11/2023] [Indexed: 01/23/2024]
Abstract
OBJECTIVE Susceptibility weighted imaging (SWI) of neonatal hypoxic-ischemic brain injury can provide assistance in the prognosis of neonatal hypoxic-ischemic encephalopathy (HIE). We propose a convolutional neural network model to classify SWI images with HIE. MATERIALS AND METHODS Due to the lack of a large dataset, transfer learning method with fine-tuning a pre-trained ResNet 50 is introduced. We randomly select 11 datasets from patients with normal neurology outcomes (n = 31) and patients with abnormal neurology outcomes (n = 11) at 24 months of age to avoid bias in classification due to any imbalance in the data. RESULTS We develop a rule-based system to improve the classification performance, with an accuracy of 0.93 ± 0.09. We also compute heatmaps produced by the Grad-CAM technique to analyze which areas of SWI images contributed more to the classification patients with abnormal neurology outcome. CONCLUSION Such regions that are important in the classification accuracy can interpret the relationship between the brain regions affected by hypoxic-ischemic and neurodevelopmental outcomes of infants with HIE at the age of 2 years.
Collapse
Affiliation(s)
- Zhen Tang
- School of Computer Science and Technology, AnHui University of Technology, Maxiang Street, Maanshan, 243032, Anhui, China.
| | - Sasan Mahmoodi
- School of Electronics and Computer Science, University of Southampton, Southampton, SO17 1BJ, UK
| | - Di Meng
- School of Computer Science and Technology, AnHui University of Technology, Maxiang Street, Maanshan, 243032, Anhui, China
| | - Angela Darekar
- Department of Medical Physics, University Hospital Southampton NHS Foundation Trust, Southampton, SO16 6YD, UK
| | - Brigitte Vollmer
- Clinical Neurosciences and Clinical and Experimental Sciences, Faculty of Medicine, University of Southampton, Southampton, SO17 1BJ, UK
| |
Collapse
|
20
|
Africano G, Arponen O, Rinta-Kiikka I, Pertuz S. Transfer learning for the generalization of artificial intelligence in breast cancer detection: a case-control study. Acta Radiol 2024; 65:334-340. [PMID: 38115699 DOI: 10.1177/02841851231218960] [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: 12/21/2023]
Abstract
BACKGROUND Some researchers have questioned whether artificial intelligence (AI) systems maintain their performance when used for women from populations not considered during the development of the system. PURPOSE To evaluate the impact of transfer learning as a way of improving the generalization of AI systems in the detection of breast cancer. MATERIAL AND METHODS This retrospective case-control Finnish study involved 191 women diagnosed with breast cancer and 191 matched healthy controls. We selected a state-of-the-art AI system for breast cancer detection trained using a large US dataset. The selected baseline system was evaluated in two experimental settings. First, we examined our private Finnish sample as an independent test set that had not been considered in the development of the system (unseen population). Second, the baseline system was retrained to attempt to improve its performance in the unseen population by means of transfer learning. To analyze performance, we used areas under the receiver operating characteristic curve (AUCs) with DeLong's test. RESULTS Two versions of the baseline system were considered: ImageOnly and Heatmaps. The ImageOnly and Heatmaps versions yielded mean AUC values of 0.82±0.008 and 0.88±0.003 in the US dataset and 0.56 (95% CI=0.50-0.62) and 0.72 (95% CI=0.67-0.77) when evaluated in the unseen population, respectively. The retrained systems achieved AUC values of 0.61 (95% CI=0.55-0.66) and 0.69 (95% CI=0.64-0.75), respectively. There was no statistical difference between the baseline system and the retrained system. CONCLUSION Transfer learning with a small study sample did not yield a significant improvement in the generalization of the system.
Collapse
Affiliation(s)
- Gerson Africano
- School of Electrical, Electronics and Telecommunications Engineering, Universidad Industrial de Santander, Bucaramanga, Colombia
| | - Otso Arponen
- Department of Radiology, Tampere University Hospital, Tampere, Finland
- Faculty of Medicine and Health Technology, Tampere University, Tampere, Finland
| | - Irina Rinta-Kiikka
- Department of Radiology, Tampere University Hospital, Tampere, Finland
- Faculty of Medicine and Health Technology, Tampere University, Tampere, Finland
| | - Said Pertuz
- School of Electrical, Electronics and Telecommunications Engineering, Universidad Industrial de Santander, Bucaramanga, Colombia
| |
Collapse
|
21
|
Yang J, Lü J, Qiu Z, Zhang M, Yan H. Risk prediction of pulse wave for hypertensive target organ damage based on frequency-domain feature map. Med Eng Phys 2024; 126:104161. [PMID: 38621841 DOI: 10.1016/j.medengphy.2024.104161] [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: 07/17/2023] [Revised: 02/29/2024] [Accepted: 03/27/2024] [Indexed: 04/17/2024]
Abstract
The application of deep learning to the classification of pulse waves in Traditional Chinese Medicine (TCM) related to hypertensive target organ damage (TOD) is hindered by challenges such as low classification accuracy and inadequate generalization performance. To address these challenges, we introduce a lightweight transfer learning model named MobileNetV2SCP. This model transforms time-domain pulse waves into 36-dimensional frequency-domain waveform feature maps and establishes a dedicated pre-training network based on these maps to enhance the learning capability for small samples. To improve global feature correlation, we incorporate a novel fusion attention mechanism (SAS) into the inverted residual structure, along with the utilization of 3 × 3 convolutional layers and BatchNorm layers to mitigate model overfitting. The proposed model is evaluated using cross-validation results from 805 cases of pulse waves associated with hypertensive TOD. The assessment metrics, including Accuracy (92.74 %), F1-score (91.47 %), and Area Under Curve (AUC) (97.12 %), demonstrate superior classification accuracy and generalization performance compared to various state-of-the-art models. Furthermore, this study investigates the correlations between time-domain and frequency-domain features in pulse waves and their classification in hypertensive TOD. It analyzes key factors influencing pulse wave classification, providing valuable insights for the clinical diagnosis of TOD.
Collapse
Affiliation(s)
- Jingdong Yang
- Autonomous Robot Lab, School of Optical-Electrical and Computer Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China.
| | - Jiangtao Lü
- Autonomous Robot Lab, School of Optical-Electrical and Computer Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China
| | - Zehao Qiu
- Autonomous Robot Lab, School of Optical-Electrical and Computer Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China
| | - Mengchu Zhang
- Shanghai Key Laboratory of Health Identification and Assessment, Shanghai University of Traditional Chinese Medicine, Shanghai 201203, China
| | - Haixia Yan
- Shanghai Key Laboratory of Health Identification and Assessment, Shanghai University of Traditional Chinese Medicine, Shanghai 201203, China.
| |
Collapse
|
22
|
Iwata H, Hayashi Y, Koyama T, Hasegawa A, Ohgi K, Kobayashi I, Okuno Y. Feature extraction of particle morphologies of pharmaceutical excipients from scanning electron microscope images using convolutional neural networks. Int J Pharm 2024; 653:123873. [PMID: 38336179 DOI: 10.1016/j.ijpharm.2024.123873] [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: 10/23/2023] [Revised: 01/08/2024] [Accepted: 01/30/2024] [Indexed: 02/12/2024]
Abstract
Scanning electron microscopy (SEM) images are the most widely used tool for evaluating particle morphology; however, quantitative evaluation using SEM images is time-consuming and often neglected. In this study, we aimed to extract features related to particle morphology of pharmaceutical excipients from SEM images using a convolutional neural network (CNN). SEM images of 67 excipients were acquired and used as models. A classification CNN model of the excipients was constructed based on the SEM images. Further, features were extracted from the middle layer of this CNN model, and the data was compressed to two dimensions using uniform manifold approximation and projection. Lastly, hierarchical clustering analysis (HCA) was performed to categorize the excipients into several clusters and identify similarities among the samples. The classification CNN model showed high accuracy, allowing each excipient to be identified with a high degree of accuracy. HCA revealed that the 67 excipients were classified into seven clusters. Additionally, the particle morphologies of excipients belonging to the same cluster were found to be very similar. These results suggest that CNN models are useful tools for extracting information and identifying similarities among the particle morphologies of excipients.
Collapse
Affiliation(s)
- Hiroaki Iwata
- Graduate School of Medicine, Kyoto University, 53 Shogoin-kawaharacho, Sakyo-ku, Kyoto 606-8507, Japan.
| | - Yoshihiro Hayashi
- Graduate School of Medicine, Kyoto University, 53 Shogoin-kawaharacho, Sakyo-ku, Kyoto 606-8507, Japan; Pharmaceutical Technology Management Department, Production Division, Nichi-Iko Pharmaceutical Co., Ltd., 205-1, Shimoumezawa Namerikawa-shi, Toyama 936-0857, Japan.
| | - Takuto Koyama
- Graduate School of Medicine, Kyoto University, 53 Shogoin-kawaharacho, Sakyo-ku, Kyoto 606-8507, Japan
| | - Aki Hasegawa
- Graduate School of Medicine, Kyoto University, 53 Shogoin-kawaharacho, Sakyo-ku, Kyoto 606-8507, Japan
| | - Kosuke Ohgi
- Formulation Development Department, Development & Planning Division, Nichi-Iko Pharmaceutical Co., Ltd., 205-1, Shimoumezawa Namerikawa-shi, Toyama 936-0857, Japan
| | - Ippei Kobayashi
- Formulation Development Department, Development & Planning Division, Nichi-Iko Pharmaceutical Co., Ltd., 205-1, Shimoumezawa Namerikawa-shi, Toyama 936-0857, Japan
| | - Yasushi Okuno
- Graduate School of Medicine, Kyoto University, 53 Shogoin-kawaharacho, Sakyo-ku, Kyoto 606-8507, Japan; RIKEN Center for Computational Science, Kobe 650-0047, Japan
| |
Collapse
|
23
|
Bottani S, Thibeau-Sutre E, Maire A, Ströer S, Dormont D, Colliot O, Burgos N. Contrast-enhanced to non-contrast-enhanced image translation to exploit a clinical data warehouse of T1-weighted brain MRI. BMC Med Imaging 2024; 24:67. [PMID: 38504179 PMCID: PMC10953143 DOI: 10.1186/s12880-024-01242-3] [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: 05/22/2023] [Accepted: 03/07/2024] [Indexed: 03/21/2024] Open
Abstract
BACKGROUND Clinical data warehouses provide access to massive amounts of medical images, but these images are often heterogeneous. They can for instance include images acquired both with or without the injection of a gadolinium-based contrast agent. Harmonizing such data sets is thus fundamental to guarantee unbiased results, for example when performing differential diagnosis. Furthermore, classical neuroimaging software tools for feature extraction are typically applied only to images without gadolinium. The objective of this work is to evaluate how image translation can be useful to exploit a highly heterogeneous data set containing both contrast-enhanced and non-contrast-enhanced images from a clinical data warehouse. METHODS We propose and compare different 3D U-Net and conditional GAN models to convert contrast-enhanced T1-weighted (T1ce) into non-contrast-enhanced (T1nce) brain MRI. These models were trained using 230 image pairs and tested on 77 image pairs from the clinical data warehouse of the Greater Paris area. RESULTS Validation using standard image similarity measures demonstrated that the similarity between real and synthetic T1nce images was higher than between real T1nce and T1ce images for all the models compared. The best performing models were further validated on a segmentation task. We showed that tissue volumes extracted from synthetic T1nce images were closer to those of real T1nce images than volumes extracted from T1ce images. CONCLUSION We showed that deep learning models initially developed with research quality data could synthesize T1nce from T1ce images of clinical quality and that reliable features could be extracted from the synthetic images, thus demonstrating the ability of such methods to help exploit a data set coming from a clinical data warehouse.
Collapse
Affiliation(s)
- Simona Bottani
- Sorbonne Université, Institut du Cerveau - Paris Brain Institute - ICM, CNRS, Inria, Inserm, AP-HP, Hôpital de la Pitié-Salpêtrière, Paris, 75013, France
| | - Elina Thibeau-Sutre
- Sorbonne Université, Institut du Cerveau - Paris Brain Institute - ICM, CNRS, Inria, Inserm, AP-HP, Hôpital de la Pitié-Salpêtrière, Paris, 75013, France
| | - Aurélien Maire
- Innovation & Données - Département des Services Numériques, AP-HP, Paris, 75013, France
| | - Sebastian Ströer
- Hôpital Pitié Salpêtrière, Department of Neuroradiology, AP-HP, Paris, 75012, France
| | - Didier Dormont
- Sorbonne Université, Institut du Cerveau - Paris Brain Institute - ICM, CNRS, Inria, Inserm, AP-HP, Hôpital de la Pitié-Salpêtrière, DMU DIAMENT, Paris, 75013, France
| | - Olivier Colliot
- Sorbonne Université, Institut du Cerveau - Paris Brain Institute - ICM, CNRS, Inria, Inserm, AP-HP, Hôpital de la Pitié-Salpêtrière, Paris, 75013, France
| | - Ninon Burgos
- Sorbonne Université, Institut du Cerveau - Paris Brain Institute - ICM, CNRS, Inria, Inserm, AP-HP, Hôpital de la Pitié-Salpêtrière, Paris, 75013, France.
| |
Collapse
|
24
|
Jahan I, Laskar MTR, Peng C, Huang JX. A comprehensive evaluation of large Language models on benchmark biomedical text processing tasks. Comput Biol Med 2024; 171:108189. [PMID: 38447502 DOI: 10.1016/j.compbiomed.2024.108189] [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: 10/11/2023] [Revised: 02/14/2024] [Accepted: 02/18/2024] [Indexed: 03/08/2024]
Abstract
Recently, Large Language Models (LLMs) have demonstrated impressive capability to solve a wide range of tasks. However, despite their success across various tasks, no prior work has investigated their capability in the biomedical domain yet. To this end, this paper aims to evaluate the performance of LLMs on benchmark biomedical tasks. For this purpose, a comprehensive evaluation of 4 popular LLMs in 6 diverse biomedical tasks across 26 datasets has been conducted. To the best of our knowledge, this is the first work that conducts an extensive evaluation and comparison of various LLMs in the biomedical domain. Interestingly, we find based on our evaluation that in biomedical datasets that have smaller training sets, zero-shot LLMs even outperform the current state-of-the-art models when they were fine-tuned only on the training set of these datasets. This suggests that pre-training on large text corpora makes LLMs quite specialized even in the biomedical domain. We also find that not a single LLM can outperform other LLMs in all tasks, with the performance of different LLMs may vary depending on the task. While their performance is still quite poor in comparison to the biomedical models that were fine-tuned on large training sets, our findings demonstrate that LLMs have the potential to be a valuable tool for various biomedical tasks that lack large annotated data.
Collapse
Affiliation(s)
- Israt Jahan
- Department of Biology, York University, Canada; Information Retrieval and Knowledge Management Research Lab, York University, Canada.
| | - Md Tahmid Rahman Laskar
- School of Information Technology, York University, Canada; Information Retrieval and Knowledge Management Research Lab, York University, Canada; Dialpad Inc., Canada.
| | - Chun Peng
- Department of Biology, York University, Canada.
| | - Jimmy Xiangji Huang
- School of Information Technology, York University, Canada; Information Retrieval and Knowledge Management Research Lab, York University, Canada.
| |
Collapse
|
25
|
Albano D, Galiano V, Basile M, Di Luca F, Gitto S, Messina C, Cagetti MG, Del Fabbro M, Tartaglia GM, Sconfienza LM. Artificial intelligence for radiographic imaging detection of caries lesions: a systematic review. BMC Oral Health 2024; 24:274. [PMID: 38402191 PMCID: PMC10894487 DOI: 10.1186/s12903-024-04046-7] [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: 11/11/2023] [Accepted: 02/17/2024] [Indexed: 02/26/2024] Open
Abstract
BACKGROUND The aim of this systematic review is to evaluate the diagnostic performance of Artificial Intelligence (AI) models designed for the detection of caries lesion (CL). MATERIALS AND METHODS An electronic literature search was conducted on PubMed, Web of Science, SCOPUS, LILACS and Embase databases for retrospective, prospective and cross-sectional studies published until January 2023, using the following keywords: artificial intelligence (AI), machine learning (ML), deep learning (DL), artificial neural networks (ANN), convolutional neural networks (CNN), deep convolutional neural networks (DCNN), radiology, detection, diagnosis and dental caries (DC). The quality assessment was performed using the guidelines of QUADAS-2. RESULTS Twenty articles that met the selection criteria were evaluated. Five studies were performed on periapical radiographs, nine on bitewings, and six on orthopantomography. The number of imaging examinations included ranged from 15 to 2900. Four studies investigated ANN models, fifteen CNN models, and two DCNN models. Twelve were retrospective studies, six cross-sectional and two prospective. The following diagnostic performance was achieved in detecting CL: sensitivity from 0.44 to 0.86, specificity from 0.85 to 0.98, precision from 0.50 to 0.94, PPV (Positive Predictive Value) 0.86, NPV (Negative Predictive Value) 0.95, accuracy from 0.73 to 0.98, area under the curve (AUC) from 0.84 to 0.98, intersection over union of 0.3-0.4 and 0.78, Dice coefficient 0.66 and 0.88, F1-score from 0.64 to 0.92. According to the QUADAS-2 evaluation, most studies exhibited a low risk of bias. CONCLUSION AI-based models have demonstrated good diagnostic performance, potentially being an important aid in CL detection. Some limitations of these studies are related to the size and heterogeneity of the datasets. Future studies need to rely on comparable, large, and clinically meaningful datasets. PROTOCOL PROSPERO identifier: CRD42023470708.
Collapse
Affiliation(s)
- Domenico Albano
- IRCCS Istituto Ortopedico Galeazzi, Milan, Italy.
- Department of Biomedical, Surgical and Dental Sciences, University of Milan, Milan, Italy.
| | | | - Mariachiara Basile
- Postgraduate School of Diagnostic and Interventional Radiology, University of Milan, Milan, Italy
| | - Filippo Di Luca
- Postgraduate School of Diagnostic and Interventional Radiology, University of Milan, Milan, Italy
| | - Salvatore Gitto
- IRCCS Istituto Ortopedico Galeazzi, Milan, Italy
- Department of Biomedical Sciences for Health, University of Milan, Milan, Italy
| | - Carmelo Messina
- IRCCS Istituto Ortopedico Galeazzi, Milan, Italy
- Department of Biomedical Sciences for Health, University of Milan, Milan, Italy
| | - Maria Grazia Cagetti
- Department of Biomedical, Surgical and Dental Sciences, University of Milan, Milan, Italy
| | - Massimo Del Fabbro
- Department of Biomedical, Surgical and Dental Sciences, University of Milan, Milan, Italy
- Ospedale Maggiore Policlinico, UOC Maxillo-Facial Surgery and Dentistry Fondazione IRCCS Cà Granda, Milan, Italy
| | - Gianluca Martino Tartaglia
- Department of Biomedical, Surgical and Dental Sciences, University of Milan, Milan, Italy
- Ospedale Maggiore Policlinico, UOC Maxillo-Facial Surgery and Dentistry Fondazione IRCCS Cà Granda, Milan, Italy
| | - Luca Maria Sconfienza
- IRCCS Istituto Ortopedico Galeazzi, Milan, Italy
- Department of Biomedical Sciences for Health, University of Milan, Milan, Italy
| |
Collapse
|
26
|
Magnéli M, Borjali A, Takahashi E, Axenhus M, Malchau H, Moratoglu OK, Varadarajan KM. Application of deep learning for automated diagnosis and classification of hip dysplasia on plain radiographs. BMC Musculoskelet Disord 2024; 25:117. [PMID: 38336666 PMCID: PMC10854089 DOI: 10.1186/s12891-024-07244-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 10/08/2023] [Accepted: 01/30/2024] [Indexed: 02/12/2024] Open
Abstract
BACKGROUND Hip dysplasia is a condition where the acetabulum is too shallow to support the femoral head and is commonly considered a risk factor for hip osteoarthritis. The objective of this study was to develop a deep learning model to diagnose hip dysplasia from plain radiographs and classify dysplastic hips based on their severity. METHODS We collected pelvic radiographs of 571 patients from two single-center cohorts and one multicenter cohort. The radiographs were split in half to create hip radiographs (n = 1022). One orthopaedic surgeon and one resident assessed the radiographs for hip dysplasia on either side. We used the center edge (CE) angle as the primary diagnostic criteria. Hips with a CE angle < 20°, 20° to 25°, and > 25° were labeled as dysplastic, borderline, and normal, respectively. The dysplastic hips were also classified with both Crowe and Hartofilakidis classification of dysplasia. The dataset was divided into train, validation, and test subsets using 80:10:10 split-ratio that were used to train two deep learning models to classify images into normal, borderline and (1) Crowe grade 1-4 or (2) Hartofilakidis grade 1-3. A pre-trained on Imagenet VGG16 convolutional neural network (CNN) was utilized by performing layer-wise fine-turning. RESULTS Both models struggled with distinguishing between normal and borderline hips. However, achieved high accuracy (Model 1: 92.2% and Model 2: 83.3%) in distinguishing between normal/borderline vs. dysplastic hips. The overall accuracy of Model 1 was 68% and for Model 2 73.5%. Most misclassifications for the Crowe and Hartofilakidis classifications were +/- 1 class from the correct class. CONCLUSIONS This pilot study shows promising results that a deep learning model distinguish between normal and dysplastic hips with high accuracy. Future research and external validation are warranted regarding the ability of deep learning models to perform complex tasks such as identifying and classifying disorders using plain radiographs. LEVEL OF EVIDENCE Diagnostic level IV.
Collapse
Affiliation(s)
- Martin Magnéli
- Department of Orthopaedic Surgery, Harvard Medical School, Boston, MA, USA
- Department of Orthopaedic Surgery, Harris Orthopaedics Laboratory, Massachusetts General Hospital, Boston, MA, USA
- Karolinska Institutet, Department of Clinical Sciences, Danderyd Hospital, Stockholm, Sweden
| | - Alireza Borjali
- Department of Orthopaedic Surgery, Harvard Medical School, Boston, MA, USA
- Department of Orthopaedic Surgery, Harris Orthopaedics Laboratory, Massachusetts General Hospital, Boston, MA, USA
| | - Eiji Takahashi
- Department of Orthopaedic Surgery, Harvard Medical School, Boston, MA, USA
- Department of Orthopaedic Surgery, Harris Orthopaedics Laboratory, Massachusetts General Hospital, Boston, MA, USA
- Department of Orthopaedic Surgery, Kanazawa Medical University, Uchinada, Japan
| | - Michael Axenhus
- Karolinska Institutet, Department of Clinical Sciences, Danderyd Hospital, Stockholm, Sweden.
- Department of Orthopaedic Surgery, Danderyd Hospital, Stockholm, Sweden.
| | - Henrik Malchau
- Department of Orthopaedic Surgery, Harris Orthopaedics Laboratory, Massachusetts General Hospital, Boston, MA, USA
- Department of Orthopaedic Surgery, Sahlgrenska University Hospital, Gothenburg, Sweden
| | - Orhun K Moratoglu
- Department of Orthopaedic Surgery, Harvard Medical School, Boston, MA, USA
- Department of Orthopaedic Surgery, Harris Orthopaedics Laboratory, Massachusetts General Hospital, Boston, MA, USA
| | | |
Collapse
|
27
|
Fan L, Gong X, Zheng C, Li J. Data pyramid structure for optimizing EUS-based GISTs diagnosis in multi-center analysis with missing label. Comput Biol Med 2024; 169:107897. [PMID: 38171262 DOI: 10.1016/j.compbiomed.2023.107897] [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: 11/01/2023] [Revised: 12/04/2023] [Accepted: 12/23/2023] [Indexed: 01/05/2024]
Abstract
This study introduces the Data Pyramid Structure (DPS) to address data sparsity and missing labels in medical image analysis. The DPS optimizes multi-task learning and enables sustainable expansion of multi-center data analysis. Specifically, It facilitates attribute prediction and malignant tumor diagnosis tasks by implementing a segmentation and aggregation strategy on data with absent attribute labels. To leverage multi-center data, we propose the Unified Ensemble Learning Framework (UELF) and the Unified Federated Learning Framework (UFLF), which incorporate strategies for data transfer and incremental learning in scenarios with missing labels. The proposed method was evaluated on a challenging EUS patient dataset from five centers, achieving promising diagnostic performance. The average accuracy was 0.984 with an AUC of 0.927 for multi-center analysis, surpassing state-of-the-art approaches. The interpretability of the predictions further highlights the potential clinical relevance of our method.
Collapse
Affiliation(s)
- Lin Fan
- School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu, Sichuan 611756, China; Manufacturing Industry Chains Collaboration and Information Support Technology Key Laboratory of Sichuan Province, China; Engineering Research Center of Sustainable Urban Intelligent Transportation, Ministry of Education, China; National Engineering Laboratory of Integrated Transportation Big Data Application Technology, China
| | - Xun Gong
- School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu, Sichuan 611756, China; Manufacturing Industry Chains Collaboration and Information Support Technology Key Laboratory of Sichuan Province, China; Engineering Research Center of Sustainable Urban Intelligent Transportation, Ministry of Education, China; National Engineering Laboratory of Integrated Transportation Big Data Application Technology, China.
| | - Cenyang Zheng
- School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu, Sichuan 611756, China; Manufacturing Industry Chains Collaboration and Information Support Technology Key Laboratory of Sichuan Province, China; Engineering Research Center of Sustainable Urban Intelligent Transportation, Ministry of Education, China; National Engineering Laboratory of Integrated Transportation Big Data Application Technology, China
| | - Jiao Li
- Department of Gastroenterology, The Third People's Hospital of Chendu, Affiliated Hospital of Southwest Jiaotong University, Chengdu 610031, China
| |
Collapse
|
28
|
Pyun KR, Kwon K, Yoo MJ, Kim KK, Gong D, Yeo WH, Han S, Ko SH. Machine-learned wearable sensors for real-time hand-motion recognition: toward practical applications. Natl Sci Rev 2024; 11:nwad298. [PMID: 38213520 PMCID: PMC10776364 DOI: 10.1093/nsr/nwad298] [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: 07/25/2023] [Revised: 09/23/2023] [Accepted: 11/01/2023] [Indexed: 01/13/2024] Open
Abstract
Soft electromechanical sensors have led to a new paradigm of electronic devices for novel motion-based wearable applications in our daily lives. However, the vast amount of random and unidentified signals generated by complex body motions has hindered the precise recognition and practical application of this technology. Recent advancements in artificial-intelligence technology have enabled significant strides in extracting features from massive and intricate data sets, thereby presenting a breakthrough in utilizing wearable sensors for practical applications. Beyond traditional machine-learning techniques for classifying simple gestures, advanced machine-learning algorithms have been developed to handle more complex and nuanced motion-based tasks with restricted training data sets. Machine-learning techniques have improved the ability to perceive, and thus machine-learned wearable soft sensors have enabled accurate and rapid human-gesture recognition, providing real-time feedback to users. This forms a crucial component of future wearable electronics, contributing to a robust human-machine interface. In this review, we provide a comprehensive summary covering materials, structures and machine-learning algorithms for hand-gesture recognition and possible practical applications through machine-learned wearable electromechanical sensors.
Collapse
Affiliation(s)
- Kyung Rok Pyun
- Department of Mechanical Engineering, Seoul National University, Seoul08826, South Korea
| | - Kangkyu Kwon
- Department of Mechanical Engineering, Seoul National University, Seoul08826, South Korea
- IEN Center for Human-Centric Interfaces and Engineering, Institute for Electronics and Nanotechnology, Georgia Institute of Technology, Atlanta, GA30332, USA
- School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA30332, USA
| | - Myung Jin Yoo
- Department of Mechanical Engineering, Seoul National University, Seoul08826, South Korea
| | - Kyun Kyu Kim
- Department of Chemical Engineering, Stanford University, Stanford, CA94305, USA
| | - Dohyeon Gong
- Department of Mechanical Engineering, Ajou University, Suwon-si16499, South Korea
| | - Woon-Hong Yeo
- IEN Center for Human-Centric Interfaces and Engineering, Institute for Electronics and Nanotechnology, Georgia Institute of Technology, Atlanta, GA30332, USA
- George W. Woodruff School of Mechanical Engineering, Georgia Institute of Technology, Atlanta, GA30332, USA
| | - Seungyong Han
- Department of Mechanical Engineering, Ajou University, Suwon-si16499, South Korea
| | - Seung Hwan Ko
- Department of Mechanical Engineering, Seoul National University, Seoul08826, South Korea
- Institute of Advanced Machinery and Design (SNU-IAMD), Seoul National University, Seoul08826, South Korea
| |
Collapse
|
29
|
Leong LT, Wong MC, Liu YE, Glaser Y, Quon BK, Kelly NN, Cataldi D, Sadowski P, Heymsfield SB, Shepherd JA. Generative deep learning furthers the understanding of local distributions of fat and muscle on body shape and health using 3D surface scans. COMMUNICATIONS MEDICINE 2024; 4:13. [PMID: 38287144 PMCID: PMC10824755 DOI: 10.1038/s43856-024-00434-w] [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: 07/14/2023] [Accepted: 01/10/2024] [Indexed: 01/31/2024] Open
Abstract
BACKGROUND Body shape, an intuitive health indicator, is deterministically driven by body composition. We developed and validated a deep learning model that generates accurate dual-energy X-ray absorptiometry (DXA) scans from three-dimensional optical body scans (3DO), enabling compositional analysis of the whole body and specified subregions. Previous works on generative medical imaging models lack quantitative validation and only report quality metrics. METHODS Our model was self-supervised pretrained on two large clinical DXA datasets and fine-tuned using the Shape Up! Adults study dataset. Model-predicted scans from a holdout test set were evaluated using clinical commercial DXA software for compositional accuracy. RESULTS Predicted DXA scans achieve R2 of 0.73, 0.89, and 0.99 and RMSEs of 5.32, 6.56, and 4.15 kg for total fat mass (FM), fat-free mass (FFM), and total mass, respectively. Custom subregion analysis results in R2s of 0.70-0.89 for left and right thigh composition. We demonstrate the ability of models to produce quantitatively accurate visualizations of soft tissue and bone, confirming a strong relationship between body shape and composition. CONCLUSIONS This work highlights the potential of generative models in medical imaging and reinforces the importance of quantitative validation for assessing their clinical utility.
Collapse
Affiliation(s)
- Lambert T Leong
- Molecular Bioscience and Bioengineering at University of Hawaii, Honolulu, HI, USA
- Department of Epidemiology, University of Hawaii Cancer Center, Honolulu, HI, USA
| | - Michael C Wong
- Department of Epidemiology, University of Hawaii Cancer Center, Honolulu, HI, USA
| | - Yong E Liu
- Department of Epidemiology, University of Hawaii Cancer Center, Honolulu, HI, USA
| | - Yannik Glaser
- Information and Computer Science at University of Hawaii, Honolulu, HI, USA
| | - Brandon K Quon
- Department of Epidemiology, University of Hawaii Cancer Center, Honolulu, HI, USA
| | - Nisa N Kelly
- Department of Epidemiology, University of Hawaii Cancer Center, Honolulu, HI, USA
| | - Devon Cataldi
- Department of Epidemiology, University of Hawaii Cancer Center, Honolulu, HI, USA
| | - Peter Sadowski
- Information and Computer Science at University of Hawaii, Honolulu, HI, USA
| | - Steven B Heymsfield
- Pennington Biomedical Research Center, Louisiana State University, Baton Rouge, LO, USA
| | - John A Shepherd
- Molecular Bioscience and Bioengineering at University of Hawaii, Honolulu, HI, USA.
- Department of Epidemiology, University of Hawaii Cancer Center, Honolulu, HI, USA.
| |
Collapse
|
30
|
Tang Y, Zhang Y, Li J. A time series driven model for early sepsis prediction based on transformer module. BMC Med Res Methodol 2024; 24:23. [PMID: 38273257 PMCID: PMC10809699 DOI: 10.1186/s12874-023-02138-6] [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: 09/10/2023] [Accepted: 12/27/2023] [Indexed: 01/27/2024] Open
Abstract
Sepsis remains a critical concern in intensive care units due to its high mortality rate. Early identification and intervention are paramount to improving patient outcomes. In this study, we have proposed predictive models for early sepsis prediction based on time-series data, utilizing both CNN-Transformer and LSTM-Transformer architectures. By collecting time-series data from patients at 4, 8, and 12 h prior to sepsis diagnosis and subjecting it to various network models for analysis and comparison. In contrast to traditional recurrent neural networks, our model exhibited a substantial improvement of approximately 20%. On average, our model demonstrated an accuracy of 0.964 (± 0.018), a precision of 0.956 (± 0.012), a recall of 0.967 (± 0.012), and an F1 score of 0.959 (± 0.014). Furthermore, by adjusting the time window, it was observed that the Transformer-based model demonstrated exceptional predictive capabilities, particularly within the earlier time window (i.e., 12 h before onset), thus holding significant promise for early clinical diagnosis and intervention. Besides, we employed the SHAP algorithm to visualize the weight distribution of different features, enhancing the interpretability of our model and facilitating early clinical diagnosis and intervention.
Collapse
Affiliation(s)
- Yan Tang
- Department of Clinical Laboratory Medicine, Jinniu Maternity and Child Health Hospital of Chengdu, Chengdu, China
| | - Yu Zhang
- Information Center, West China Hospital, Sichuan University, Chengdu, China
| | - Jiaxi Li
- Department of Clinical Laboratory Medicine, Jinniu Maternity and Child Health Hospital of Chengdu, Chengdu, China.
| |
Collapse
|
31
|
Tao S, Tian Z, Bai L, Xu Y, Kuang C, Liu X. Phase retrieval for X-ray differential phase contrast radiography with knowledge transfer learning from virtual differential absorption model. Comput Biol Med 2024; 168:107711. [PMID: 37995534 DOI: 10.1016/j.compbiomed.2023.107711] [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: 07/03/2023] [Revised: 10/31/2023] [Accepted: 11/15/2023] [Indexed: 11/25/2023]
Abstract
Grating-based X-ray phase contrast radiography and computed tomography (CT) are promising modalities for future medical applications. However, the ill-posed phase retrieval problem in X-ray phase contrast imaging has hindered its use for quantitative analysis in biomedical imaging. Deep learning has been proved as an effective tool for image retrieval. However, in practical grating-based X-ray phase contrast imaging system, acquiring the ground truth of phase to form image pairs is challenging, which poses a great obstacle for using deep leaning methods. Transfer learning is widely used to address the problem with knowledge inheritance from similar tasks. In the present research, we propose a virtual differential absorption model and generate a training dataset with differential absorption images and absorption images. The knowledge learned from the training is transferred to phase retrieval with transfer learning techniques. Numerical simulations and experiments both demonstrate its feasibility. Image quality of retrieved phase radiograph and phase CT slices is improved when compared with representative phase retrieval methods. We conclude that this method is helpful in both X-ray 2D and 3D imaging and may find its applications in X-ray phase contrast radiography and X-ray phase CT.
Collapse
Affiliation(s)
- Siwei Tao
- State Key Laboratory of Extreme Photonics and Instrumentation, College of Optical Science and Engineering, Zhejiang University, Hangzhou, 310027, China
| | - Zonghan Tian
- State Key Laboratory of Extreme Photonics and Instrumentation, College of Optical Science and Engineering, Zhejiang University, Hangzhou, 310027, China
| | - Ling Bai
- State Key Laboratory of Extreme Photonics and Instrumentation, College of Optical Science and Engineering, Zhejiang University, Hangzhou, 310027, China
| | - Yueshu Xu
- State Key Laboratory of Extreme Photonics and Instrumentation, College of Optical Science and Engineering, Zhejiang University, Hangzhou, 310027, China; State Key Laboratory of Extreme Photonics and Instrumentation, ZJU-Hangzhou Global Scientific and Technological Innovation Center, Zhejiang University, Hangzhou, 315100, China
| | - Cuifang Kuang
- State Key Laboratory of Extreme Photonics and Instrumentation, College of Optical Science and Engineering, Zhejiang University, Hangzhou, 310027, China; State Key Laboratory of Extreme Photonics and Instrumentation, ZJU-Hangzhou Global Scientific and Technological Innovation Center, Zhejiang University, Hangzhou, 315100, China; Collaborative Innovation Center of Extreme Optics, Shanxi University, Taiyuan, 030006, China.
| | - Xu Liu
- State Key Laboratory of Extreme Photonics and Instrumentation, College of Optical Science and Engineering, Zhejiang University, Hangzhou, 310027, China; State Key Laboratory of Extreme Photonics and Instrumentation, ZJU-Hangzhou Global Scientific and Technological Innovation Center, Zhejiang University, Hangzhou, 315100, China; Ningbo Research Institute, Zhejiang University, Ningbo, 315100, China.
| |
Collapse
|
32
|
Hossain MM, Hossain MM, Arefin MB, Akhtar F, Blake J. Combining State-of-the-Art Pre-Trained Deep Learning Models: A Noble Approach for Skin Cancer Detection Using Max Voting Ensemble. Diagnostics (Basel) 2023; 14:89. [PMID: 38201399 PMCID: PMC10795598 DOI: 10.3390/diagnostics14010089] [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: 10/03/2023] [Revised: 12/21/2023] [Accepted: 12/22/2023] [Indexed: 01/12/2024] Open
Abstract
Skin cancer poses a significant healthcare challenge, requiring precise and prompt diagnosis for effective treatment. While recent advances in deep learning have dramatically improved medical image analysis, including skin cancer classification, ensemble methods offer a pathway for further enhancing diagnostic accuracy. This study introduces a cutting-edge approach employing the Max Voting Ensemble Technique for robust skin cancer classification on ISIC 2018: Task 1-2 dataset. We incorporate a range of cutting-edge, pre-trained deep neural networks, including MobileNetV2, AlexNet, VGG16, ResNet50, DenseNet201, DenseNet121, InceptionV3, ResNet50V2, InceptionResNetV2, and Xception. These models have been extensively trained on skin cancer datasets, achieving individual accuracies ranging from 77.20% to 91.90%. Our method leverages the synergistic capabilities of these models by combining their complementary features to elevate classification performance further. In our approach, input images undergo preprocessing for model compatibility. The ensemble integrates the pre-trained models with their architectures and weights preserved. For each skin lesion image under examination, every model produces a prediction. These are subsequently aggregated using the max voting ensemble technique to yield the final classification, with the majority-voted class serving as the conclusive prediction. Through comprehensive testing on a diverse dataset, our ensemble outperformed individual models, attaining an accuracy of 93.18% and an AUC score of 0.9320, thus demonstrating superior diagnostic reliability and accuracy. We evaluated the effectiveness of our proposed method on the HAM10000 dataset to ensure its generalizability. Our ensemble method delivers a robust, reliable, and effective tool for the classification of skin cancer. By utilizing the power of advanced deep neural networks, we aim to assist healthcare professionals in achieving timely and accurate diagnoses, ultimately reducing mortality rates and enhancing patient outcomes.
Collapse
Affiliation(s)
- Md. Mamun Hossain
- Department of Computer Science and Engineering, Bangladesh Army University of Science and Technology, Saidpur 5310, Bangladesh
| | - Md. Moazzem Hossain
- Department of Computer Science and Engineering, Bangladesh Army University of Science and Technology, Saidpur 5310, Bangladesh
| | - Most. Binoee Arefin
- Department of Computer Science and Engineering, Bangladesh Army University of Science and Technology, Saidpur 5310, Bangladesh
| | - Fahima Akhtar
- Department of Computer Science and Engineering, Bangladesh Army University of Science and Technology, Saidpur 5310, Bangladesh
| | - John Blake
- School of Computer Science and Engineering, University of Aizu, Aizuwakamatsu 965-8580, Japan
| |
Collapse
|
33
|
Lee GP, Kim YJ, Park DK, Kim YJ, Han SK, Kim KG. Gastro-BaseNet: A Specialized Pre-Trained Model for Enhanced Gastroscopic Data Classification and Diagnosis of Gastric Cancer and Ulcer. Diagnostics (Basel) 2023; 14:75. [PMID: 38201385 PMCID: PMC10795822 DOI: 10.3390/diagnostics14010075] [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: 11/29/2023] [Revised: 12/25/2023] [Accepted: 12/26/2023] [Indexed: 01/12/2024] Open
Abstract
Most of the development of gastric disease prediction models has utilized pre-trained models from natural data, such as ImageNet, which lack knowledge of medical domains. This study proposes Gastro-BaseNet, a classification model trained using gastroscopic image data for abnormal gastric lesions. To prove performance, we compared transfer-learning based on two pre-trained models (Gastro-BaseNet and ImageNet) and two training methods (freeze and fine-tune modes). The effectiveness was verified in terms of classification at the image-level and patient-level, as well as the localization performance of lesions. The development of Gastro-BaseNet had demonstrated superior transfer learning performance compared to random weight settings in ImageNet. When developing a model for predicting the diagnosis of gastric cancer and gastric ulcers, the transfer-learned model based on Gastro-BaseNet outperformed that based on ImageNet. Furthermore, the model's performance was highest when fine-tuning the entire layer in the fine-tune mode. Additionally, the trained model was based on Gastro-BaseNet, which showed higher localization performance, which confirmed its accurate detection and classification of lesions in specific locations. This study represents a notable advancement in the development of image analysis models within the medical field, resulting in improved diagnostic predictive accuracy and aiding in making more informed clinical decisions in gastrointestinal endoscopy.
Collapse
Affiliation(s)
- Gi Pyo Lee
- Department of Health Sciences and Technology, Gachon Advanced Institute for Health Sciences and Technology (GAIHST), Gachon University, Incheon 21565, Republic of Korea;
| | - Young Jae Kim
- Department of Biomedical Engineering, Gachon University Gil Medical Center, College of Medicine, Gachon University, Incheon 21565, Republic of Korea;
| | - Dong Kyun Park
- Division of Gastroenterology, Department of Internal Medicine, Gachon University Gil Medical Center, College of Medicine, Gachon University, Incheon 21565, Republic of Korea; (D.K.P.); (Y.J.K.)
| | - Yoon Jae Kim
- Division of Gastroenterology, Department of Internal Medicine, Gachon University Gil Medical Center, College of Medicine, Gachon University, Incheon 21565, Republic of Korea; (D.K.P.); (Y.J.K.)
| | - Su Kyeong Han
- Health IT Research Center, Gachon University Gil Medical Center, Incheon 21565, Republic of Korea;
| | - Kwang Gi Kim
- Department of Biomedical Engineering, Gachon University Gil Medical Center, College of Medicine, Gachon University, Incheon 21565, Republic of Korea;
| |
Collapse
|
34
|
Borjali A, Ashkani-Esfahani S, Bhimani R, Guss D, Muratoglu OK, DiGiovanni CW, Varadarajan KM, Lubberts B. The use of deep learning enables high diagnostic accuracy in detecting syndesmotic instability on weight-bearing CT scanning. Knee Surg Sports Traumatol Arthrosc 2023; 31:6039-6045. [PMID: 37823903 DOI: 10.1007/s00167-023-07565-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/09/2022] [Accepted: 09/02/2023] [Indexed: 10/13/2023]
Abstract
PURPOSE Delayed diagnosis of syndesmosis instability can lead to significant morbidity and accelerated arthritic change in the ankle joint. Weight-bearing computed tomography (WBCT) has shown promising potential for early and reliable detection of isolated syndesmotic instability using 3D volumetric measurements. While these measurements have been reported to be highly accurate, they are also experience-dependent, time-consuming, and need a particular 3D measurement software tool that leads the clinicians to still show more interest in the conventional diagnostic methods for syndesmotic instability. The purpose of this study was to increase accuracy, accelerate analysis time, and reduce interobserver bias by automating 3D volume assessment of syndesmosis anatomy using WBCT scans. METHODS A retrospective study was conducted using previously collected WBCT scans of patients with unilateral syndesmotic instability. One-hundred and forty-four bilateral ankle WBCT scans were evaluated (48 unstable, 96 control). We developed three deep learning models for analyzing WBCT scans to recognize syndesmosis instability. These three models included two state-of-the-art models (Model 1-3D Convolutional Neural Network [CNN], and Model 2-CNN with long short-term memory [LSTM]), and a new model (Model 3-differential CNN LSTM) that we introduced in this study. RESULTS Model 1 failed to analyze the WBCT scans (F1 score = 0). Model 2 only misclassified two cases (F1 score = 0.80). Model 3 outperformed Model 2 and achieved a nearly perfect performance, misclassifying only one case (F1 score = 0.91) in the control group as unstable while being faster than Model 2. CONCLUSIONS In this study, a deep learning model for 3D WBCT syndesmosis assessment was developed that achieved very high accuracy and accelerated analytics. This deep learning model shows promise for use by clinicians to improve diagnostic accuracy, reduce measurement bias, and save both time and expenditure for the healthcare system. LEVEL OF EVIDENCE II.
Collapse
Affiliation(s)
- Alireza Borjali
- Harris Orthopaedics Laboratory, Department of Orthopaedic Surgery, Massachusetts General Hospital, 55 Fruit St. GRJ 1121B, Boston, MA, 02114, USA.
- Department of Orthopaedic Surgery, Harvard Medical School, Boston, MA, USA.
| | - Soheil Ashkani-Esfahani
- Department of Orthopaedic Surgery, Harvard Medical School, Boston, MA, USA
- Foot & Ankle Research and Innovation Laboratory, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA
| | - Rohan Bhimani
- Foot & Ankle Research and Innovation Laboratory, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA
| | - Daniel Guss
- Department of Orthopaedic Surgery, Harvard Medical School, Boston, MA, USA
- Foot & Ankle Research and Innovation Laboratory, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA
| | - Orhun K Muratoglu
- Harris Orthopaedics Laboratory, Department of Orthopaedic Surgery, Massachusetts General Hospital, 55 Fruit St. GRJ 1121B, Boston, MA, 02114, USA
- Department of Orthopaedic Surgery, Harvard Medical School, Boston, MA, USA
| | - Christopher W DiGiovanni
- Department of Orthopaedic Surgery, Harvard Medical School, Boston, MA, USA
- Foot & Ankle Research and Innovation Laboratory, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA
| | | | - Bart Lubberts
- Foot & Ankle Research and Innovation Laboratory, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA
| |
Collapse
|
35
|
Benhenneda R, Brouard T, Charousset C, Berhouet J. Can artificial intelligence help decision-making in arthroscopy? Part 2: The IA-RTRHO model - a decision-making aid for long head of the biceps diagnoses in small rotator cuff tears. Orthop Traumatol Surg Res 2023; 109:103652. [PMID: 37380127 DOI: 10.1016/j.otsr.2023.103652] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 03/17/2023] [Revised: 05/09/2023] [Accepted: 05/17/2023] [Indexed: 06/30/2023]
Abstract
INTRODUCTION The possible applications of artificial intelligence (AI) in orthopedic surgery are promising. Deep learning can be utilized in arthroscopic surgery due to the video signal used by computer vision. The intraoperative management of the long head of biceps (LHB) tendon is the subject of a long-standing controversy. The main objective of this study was to model a diagnostic AI capable of determining the healthy or pathological state of the LHB on arthroscopic images. The secondary objective was to create a second diagnostic AI model based on arthroscopic images and the medical, clinical and imaging data of each patient, to determine the healthy or pathological state of the LHB. HYPOTHESIS The hypothesis of this study was that it was possible to construct an AI model from operative arthroscopic images to aid in the diagnosis of the healthy or pathological state of the LHB, and its analysis would be superior to a human analysis. MATERIALS AND METHODS Prospective clinical and imaging data from 199 patients were collected and associated with images from a validated protocoled arthroscopic video analysis, called "ground truth", made by the operating surgeon. A model based on a convolutional neural network (CNN) modeled via transfer learning on the Inception V3 model was built for the analysis of arthroscopic images. This model was then coupled to MultiLayer Perceptron (MLP), integrating clinical and imaging data. Each model was trained and tested using supervised learning. RESULTS The accuracy of the CNN in diagnosing the healthy or pathological state of the LHB was 93.7% in learning and 80.66% in generalization. Coupled with the clinical data of each patient, the accuracy of the model assembling the CNN and MLP were respectively 77% and 58% in learning and in generalization. CONCLUSION The AI model built from a CNN manages to determine the healthy or pathological state of the LHB with an accuracy rate of 80.66%. An increase in input data to limit overfitting, and the automation of the detection phase by a Mask-R-CNN are ways of improving the model. This study is the first to assess the ability of an AI to analyze arthroscopic images, and its results need to be confirmed by further studies on this subject. LEVEL OF EVIDENCE III Diagnostic study.
Collapse
Affiliation(s)
- Rayane Benhenneda
- Service de chirurgie orthopédique, hôpital Trousseau, CHRU de Tours, faculté de médecine, université de Tours, Centre-Val-de-Loire, France.
| | - Thierry Brouard
- LIFAT (EA6300), école polytechnique universitaire de Tours, 64, avenue Jean-Portalis, 37200 Tours, France
| | | | - Julien Berhouet
- Service de chirurgie orthopédique, hôpital Trousseau, CHRU de Tours, faculté de médecine, université de Tours, Centre-Val-de-Loire, France; LIFAT (EA6300), école polytechnique universitaire de Tours, 64, avenue Jean-Portalis, 37200 Tours, France
| |
Collapse
|
36
|
Gao W, Wang D, Huang Y. Designing a Deep Learning-Driven Resource-Efficient Diagnostic System for Metastatic Breast Cancer: Reducing Long Delays of Clinical Diagnosis and Improving Patient Survival in Developing Countries. Cancer Inform 2023; 22:11769351231214446. [PMID: 38033362 PMCID: PMC10683375 DOI: 10.1177/11769351231214446] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/02/2023] [Accepted: 10/27/2023] [Indexed: 12/02/2023] Open
Abstract
Breast cancer is one of the leading causes of cancer mortality. Breast cancer patients in developing countries, especially sub-Saharan Africa, South Asia, and South America, suffer from the highest mortality rate in the world. One crucial factor contributing to the global disparity in mortality rate is long delay of diagnosis due to a severe shortage of trained pathologists, which consequently has led to a large proportion of late-stage presentation at diagnosis. To tackle this critical healthcare disparity, we have developed a deep learning-based diagnosis system for metastatic breast cancer that can achieve high diagnostic accuracy as well as computational efficiency and mobile readiness suitable for an under-resourced environment. We evaluated 4 Convolutional Neural Network (CNN) architectures: MobileNetV2, VGG16, ResNet50 and ResNet101. The MobileNetV2-based diagnostic model outperformed the more complex VGG16, ResNet50 and ResNet101 models in diagnostic accuracy, model generalization, and model training efficiency. The ROC AUC of MobilenetV2 (0.933, 95% CI: 0.930, 0.936) was higher than VGG16 (0.911, 95% CI: 0.908, 0.915), ResNet50 (0.869, 95% CI: 0.866, 0.873), and ResNet101 (0.873, 95% CI: 0.869, 0.876). The time per inference step for the MobileNetV2 model (15 ms/step) was substantially lower than that of VGG16 (48 ms/step), ResNet50 (37 ms/step), and ResNet110 (56 ms/step). The visual comparisons between the model prediction and ground truth have demonstrated that the MobileNetV2 diagnostic models can identify very small cancerous nodes embedded in a large area of normal cells which is challenging for manual image analysis. Equally Important, the light weight MobleNetV2 models were computationally efficient and ready for mobile devices or devices of low computational power. These advances empower the development of a resource-efficient and high performing AI-based metastatic breast cancer diagnostic system that can adapt to under-resourced healthcare facilities in developing countries.
Collapse
Affiliation(s)
- William Gao
- Department of Mathematics and Statistics, University of Maryland, Baltimore County, Baltimore, MD, USA
| | | | - Yi Huang
- Department of Mathematics and Statistics, University of Maryland, Baltimore County, Baltimore, MD, USA
| |
Collapse
|
37
|
Yousefpour Shahrivar R, Karami F, Karami E. Enhancing Fetal Anomaly Detection in Ultrasonography Images: A Review of Machine Learning-Based Approaches. Biomimetics (Basel) 2023; 8:519. [PMID: 37999160 PMCID: PMC10669151 DOI: 10.3390/biomimetics8070519] [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: 08/29/2023] [Revised: 10/05/2023] [Accepted: 10/26/2023] [Indexed: 11/25/2023] Open
Abstract
Fetal development is a critical phase in prenatal care, demanding the timely identification of anomalies in ultrasound images to safeguard the well-being of both the unborn child and the mother. Medical imaging has played a pivotal role in detecting fetal abnormalities and malformations. However, despite significant advances in ultrasound technology, the accurate identification of irregularities in prenatal images continues to pose considerable challenges, often necessitating substantial time and expertise from medical professionals. In this review, we go through recent developments in machine learning (ML) methods applied to fetal ultrasound images. Specifically, we focus on a range of ML algorithms employed in the context of fetal ultrasound, encompassing tasks such as image classification, object recognition, and segmentation. We highlight how these innovative approaches can enhance ultrasound-based fetal anomaly detection and provide insights for future research and clinical implementations. Furthermore, we emphasize the need for further research in this domain where future investigations can contribute to more effective ultrasound-based fetal anomaly detection.
Collapse
Affiliation(s)
- Ramin Yousefpour Shahrivar
- Department of Biology, College of Convergent Sciences and Technologies, Science and Research Branch, Islamic Azad University, Tehran, 14515-775, Iran
| | - Fatemeh Karami
- Department of Medical Genetics, Applied Biophotonics Research Center, Science and Research Branch, Islamic Azad University, Tehran, 14515-775, Iran
| | - Ebrahim Karami
- Department of Engineering and Applied Sciences, Memorial University of Newfoundland, St. John’s, NL A1B 3X5, Canada
| |
Collapse
|
38
|
Yi W, Zhao J, Tang W, Yin H, Yu L, Wang Y, Tian W. Deep learning-based high-accuracy detection for lumbar and cervical degenerative disease on T2-weighted MR images. EUROPEAN SPINE JOURNAL : OFFICIAL PUBLICATION OF THE EUROPEAN SPINE SOCIETY, THE EUROPEAN SPINAL DEFORMITY SOCIETY, AND THE EUROPEAN SECTION OF THE CERVICAL SPINE RESEARCH SOCIETY 2023; 32:3807-3814. [PMID: 36943484 DOI: 10.1007/s00586-023-07641-4] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 08/24/2022] [Revised: 01/31/2023] [Accepted: 03/05/2023] [Indexed: 03/23/2023]
Abstract
PURPOSE To develop and validate a deep learning (DL) model for detecting lumbar degenerative disease in both sagittal and axial views of T2-weighted MRI and evaluate its generalized performance in detecting cervical degenerative disease. METHODS T2-weighted MRI scans of 804 patients with symptoms of lumbar degenerative disease were retrospectively collected from three hospitals. The training dataset (n = 456) and internal validation dataset (n = 134) were randomly selected from the center I. Two external validation datasets comprising 100 and 114 patients were from center II and center III, respectively. A DL model based on 3D ResNet18 and transformer architecture was proposed to detect lumbar degenerative disease. In addition, a cervical MR image dataset comprising 200 patients from an independent hospital was used to evaluate the generalized performance of the DL model. The diagnostic performance was assessed by the free-response receiver operating characteristic (fROC) curve and precision-recall (PR) curve. Precision, recall, and F1-score were used to measure the DL model. RESULTS A total of 2497 three-dimension retrogression annotations were labeled for training (n = 1157) and multicenter validation (n = 1340). The DL model showed excellent detection efficiency in the internal validation dataset, with F1-score achieving 0.971 and 0.903 on the sagittal and axial MR images, respectively. Good performance was also observed in the external validation dataset I (F1-score, 0.768 on sagittal MR images and 0.837 on axial MR images) and external validation dataset II (F1-score, 0.787 on sagittal MR images and 0.770 on axial MR images). Furthermore, the robustness of the DL model was demonstrated via transfer learning and generalized performance evaluation on the external cervical dataset, with the F1-score yielding 0.931 and 0.919 on the sagittal and axial MR images, respectively. CONCLUSION The proposed DL model can automatically detect lumbar and cervical degenerative disease on T2-weighted MR images with good performance, robustness, and feasibility in clinical practice.
Collapse
Affiliation(s)
- Wei Yi
- Department of Spine Surgery, Beijing Jishuitan Hospital, Beijing, 100035, China.
| | - Jingwei Zhao
- Beijing Jishuitan Hospital, Research Unit of Intelligent Orthopedics, Chinese Academy of Medical Sciences, Beijing, China.
| | - Wen Tang
- Institute of Advanced Research, Infervision Medical Technology Co., Ltd, Beijing, Beijing, China
| | - Hongkun Yin
- Institute of Advanced Research, Infervision Medical Technology Co., Ltd, Beijing, Beijing, China
| | - Lifeng Yu
- The Second Hospital of Zhangjiakou City, Zhangjiakou, Hebei Province, China
| | - Yaohui Wang
- Department of Trauma, Beijing Water Conservancy Hospital, Beijing, 10036, China
| | - Wei Tian
- Beijing Jishuitan Hospital, Research Unit of Intelligent Orthopedics, Chinese Academy of Medical Sciences, Beijing, China
| |
Collapse
|
39
|
Alshahrani H, Sharma G, Anand V, Gupta S, Sulaiman A, Elmagzoub MA, Reshan MSA, Shaikh A, Azar AT. An Intelligent Attention-Based Transfer Learning Model for Accurate Differentiation of Bone Marrow Stains to Diagnose Hematological Disorder. Life (Basel) 2023; 13:2091. [PMID: 37895472 PMCID: PMC10607952 DOI: 10.3390/life13102091] [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: 09/07/2023] [Revised: 10/17/2023] [Accepted: 10/19/2023] [Indexed: 10/29/2023] Open
Abstract
Bone marrow (BM) is an essential part of the hematopoietic system, which generates all of the body's blood cells and maintains the body's overall health and immune system. The classification of bone marrow cells is pivotal in both clinical and research settings because many hematological diseases, such as leukemia, myelodysplastic syndromes, and anemias, are diagnosed based on specific abnormalities in the number, type, or morphology of bone marrow cells. There is a requirement for developing a robust deep-learning algorithm to diagnose bone marrow cells to keep a close check on them. This study proposes a framework for categorizing bone marrow cells into seven classes. In the proposed framework, five transfer learning models-DenseNet121, EfficientNetB5, ResNet50, Xception, and MobileNetV2-are implemented into the bone marrow dataset to classify them into seven classes. The best-performing DenseNet121 model was fine-tuned by adding one batch-normalization layer, one dropout layer, and two dense layers. The proposed fine-tuned DenseNet121 model was optimized using several optimizers, such as AdaGrad, AdaDelta, Adamax, RMSprop, and SGD, along with different batch sizes of 16, 32, 64, and 128. The fine-tuned DenseNet121 model was integrated with an attention mechanism to improve its performance by allowing the model to focus on the most relevant features or regions of the image, which can be particularly beneficial in medical imaging, where certain regions might have critical diagnostic information. The proposed fine-tuned and integrated DenseNet121 achieved the highest accuracy, with a training success rate of 99.97% and a testing success rate of 97.01%. The key hyperparameters, such as batch size, number of epochs, and different optimizers, were all considered for optimizing these pre-trained models to select the best model. This study will help in medical research to effectively classify the BM cells to prevent diseases like leukemia.
Collapse
Affiliation(s)
- Hani Alshahrani
- Department of Computer Science, College of Computer Science and Information Systems, Najran University, Najran 66462, Saudi Arabia; (H.A.); (A.S.)
| | - Gunjan Sharma
- Chitkara University Institute of Engineering and Technology, Chitkara University, Rajpura 140401, India; (G.S.); (V.A.); (S.G.)
| | - Vatsala Anand
- Chitkara University Institute of Engineering and Technology, Chitkara University, Rajpura 140401, India; (G.S.); (V.A.); (S.G.)
| | - Sheifali Gupta
- Chitkara University Institute of Engineering and Technology, Chitkara University, Rajpura 140401, India; (G.S.); (V.A.); (S.G.)
| | - Adel Sulaiman
- Department of Computer Science, College of Computer Science and Information Systems, Najran University, Najran 66462, Saudi Arabia; (H.A.); (A.S.)
| | - M. A. Elmagzoub
- Department of Network and Communication Engineering, College of Computer Science and Information Systems, Najran University, Najran 61441, Saudi Arabia;
| | - Mana Saleh Al Reshan
- Department of Information Systems, College of Computer Science and Information Systems, Najran University, Najran 66462, Saudi Arabia; (M.S.A.R.); (A.S.)
| | - Asadullah Shaikh
- Department of Information Systems, College of Computer Science and Information Systems, Najran University, Najran 66462, Saudi Arabia; (M.S.A.R.); (A.S.)
| | - Ahmad Taher Azar
- College of Computer and Information Sciences, Prince Sultan University, Riyadh 11586, Saudi Arabia
- Automated Systems and Soft Computing Lab (ASSCL), Prince Sultan University, Riyadh 11586, Saudi Arabia
| |
Collapse
|
40
|
Alsaidi FA, Moria KM. Flatfeet Severity-Level Detection Based on Alignment Measuring. SENSORS (BASEL, SWITZERLAND) 2023; 23:8219. [PMID: 37837049 PMCID: PMC10574869 DOI: 10.3390/s23198219] [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: 08/05/2023] [Revised: 09/17/2023] [Accepted: 09/25/2023] [Indexed: 10/15/2023]
Abstract
Flat foot is a postural deformity in which the plantar part of the foot is either completely or partially contacted with the ground. In recent clinical practices, X-ray radiographs have been introduced to detect flat feet because they are more affordable to many clinics than using specialized devices. This research aims to develop an automated model that detects flat foot cases and their severity levels from lateral foot X-ray images by measuring three different foot angles: the Arch Angle, Meary's Angle, and the Calcaneal Inclination Angle. Since these angles are formed by connecting a set of points on the image, Template Matching is used to allocate a set of potential points for each angle, and then a classifier is used to select the points with the highest predicted likelihood to be the correct point. Inspired by literature, this research constructed and compared two models: a Convolutional Neural Network-based model and a Random Forest-based model. These models were trained on 8000 images and tested on 240 unseen cases. As a result, the highest overall accuracy rate was 93.13% achieved by the Random Forest model, with mean values for all foot types (normal foot, mild flat foot, and moderate flat foot) being: 93.38 precision, 92.56 recall, 96.46 specificity, 95.42 accuracy, and 92.90 F-Score. The main conclusions that were deduced from this research are: (1) Using transfer learning (VGG-16) as a feature-extractor-only, in addition to image augmentation, has greatly increased the overall accuracy rate. (2) Relying on three different foot angles shows more accurate estimations than measuring a single foot angle.
Collapse
Affiliation(s)
- Fatmah A. Alsaidi
- Department of Computer Science, King Abdulaziz University, Jeddah 21589, Saudi Arabia
| | - Kawthar M. Moria
- Department of Electrical and Computer Engineering, King Abdulaziz University, Jeddah 21589, Saudi Arabia
| |
Collapse
|
41
|
Gil J, Choi H, Paeng JC, Cheon GJ, Kang KW. Deep Learning-Based Feature Extraction from Whole-Body PET/CT Employing Maximum Intensity Projection Images: Preliminary Results of Lung Cancer Data. Nucl Med Mol Imaging 2023; 57:216-222. [PMID: 37720886 PMCID: PMC10504178 DOI: 10.1007/s13139-023-00802-9] [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: 04/13/2022] [Revised: 03/20/2023] [Accepted: 04/03/2023] [Indexed: 09/19/2023] Open
Abstract
Purpose Deep learning (DL) has been widely used in various medical imaging analyses. Because of the difficulty in processing volume data, it is difficult to train a DL model as an end-to-end approach using PET volume as an input for various purposes including diagnostic classification. We suggest an approach employing two maximum intensity projection (MIP) images generated by whole-body FDG PET volume to employ pre-trained models based on 2-D images. Methods As a retrospective, proof-of-concept study, 562 [18F]FDG PET/CT images and clinicopathological factors of lung cancer patients were collected. MIP images of anterior and lateral views were used as inputs, and image features were extracted by a pre-trained convolutional neural network (CNN) model, ResNet-50. The relationship between the images was depicted on a parametric 2-D axes map using t-distributed stochastic neighborhood embedding (t-SNE), with clinicopathological factors. Results A DL-based feature map extracted by two MIP images was embedded by t-SNE. According to the visualization of the t-SNE map, PET images were clustered by clinicopathological features. The representative difference between the clusters of PET patterns according to the posture of a patient was visually identified. This map showed a pattern of clustering according to various clinicopathological factors including sex as well as tumor staging. Conclusion A 2-D image-based pre-trained model could extract image patterns of whole-body FDG PET volume by using anterior and lateral views of MIP images bypassing the direct use of 3-D PET volume that requires large datasets and resources. We suggest that this approach could be implemented as a backbone model for various applications for whole-body PET image analyses.
Collapse
Affiliation(s)
- Joonhyung Gil
- Department of Nuclear Medicine, Seoul National University Hospital, 101 Daehak-ro, Jongno-gu, Seoul, 03080 Republic of Korea
- Department of Nuclear Medicine, Seoul National University College of Medicine, 101 Daehak-ro, Jongno-gu, Seoul, 03080 Republic of Korea
| | - Hongyoon Choi
- Department of Nuclear Medicine, Seoul National University Hospital, 101 Daehak-ro, Jongno-gu, Seoul, 03080 Republic of Korea
- Department of Nuclear Medicine, Seoul National University College of Medicine, 101 Daehak-ro, Jongno-gu, Seoul, 03080 Republic of Korea
| | - Jin Chul Paeng
- Department of Nuclear Medicine, Seoul National University Hospital, 101 Daehak-ro, Jongno-gu, Seoul, 03080 Republic of Korea
- Department of Nuclear Medicine, Seoul National University College of Medicine, 101 Daehak-ro, Jongno-gu, Seoul, 03080 Republic of Korea
| | - Gi Jeong Cheon
- Department of Nuclear Medicine, Seoul National University Hospital, 101 Daehak-ro, Jongno-gu, Seoul, 03080 Republic of Korea
- Department of Nuclear Medicine, Seoul National University College of Medicine, 101 Daehak-ro, Jongno-gu, Seoul, 03080 Republic of Korea
| | - Keon Wook Kang
- Department of Nuclear Medicine, Seoul National University Hospital, 101 Daehak-ro, Jongno-gu, Seoul, 03080 Republic of Korea
- Department of Nuclear Medicine, Seoul National University College of Medicine, 101 Daehak-ro, Jongno-gu, Seoul, 03080 Republic of Korea
| |
Collapse
|
42
|
Ishizawa M, Tanaka S, Takagi H, Kadoya N, Sato K, Umezawa R, Jingu K, Takeda K. Development of a prediction model for head and neck volume reduction by clinical factors, dose-volume histogram parameters and radiomics in head and neck cancer†. JOURNAL OF RADIATION RESEARCH 2023; 64:783-794. [PMID: 37466450 PMCID: PMC10516738 DOI: 10.1093/jrr/rrad052] [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: 03/09/2023] [Revised: 05/05/2023] [Indexed: 07/20/2023]
Abstract
In external radiotherapy of head and neck (HN) cancers, the reduction of irradiation accuracy due to HN volume reduction often causes a problem. Adaptive radiotherapy (ART) can effectively solve this problem; however, its application to all cases is impractical because of cost and time. Therefore, finding priority cases is essential. This study aimed to predict patients with HN cancers are more likely to need ART based on a quantitative measure of large HN volume reduction and evaluate model accuracy. The study included 172 cases of patients with HN cancer who received external irradiation. The HN volume was calculated using cone-beam computed tomography (CT) for irradiation-guided radiotherapy for all treatment fractions and classified into two groups: cases with a large reduction in the HN volume and cases without a large reduction. Radiomic features were extracted from the primary gross tumor volume (GTV) and nodal GTV of the planning CT. To develop the prediction model, four feature selection methods and two machine-learning algorithms were tested. Predictive performance was evaluated by the area under the curve (AUC), accuracy, sensitivity and specificity. Predictive performance was the highest for the random forest, with an AUC of 0.662. Furthermore, its accuracy, sensitivity and specificity were 0.692, 0.700 and 0.813, respectively. Selected features included radiomic features of the primary GTV, human papillomavirus in oropharyngeal cancer and the implementation of chemotherapy; thus, these features might be related to HN volume change. Our model suggested the potential to predict ART requirements based on HN volume reduction .
Collapse
Affiliation(s)
- Miyu Ishizawa
- Department of Radiological Technology, Faculty of Medicine, School of Health Sciences, Tohoku University, 21 Seiryo-machi, Aoba-ku, Sendai, Miyagi, 980-8575, Japan
| | - Shohei Tanaka
- Department of Radiation Oncology, Tohoku University Graduate School of Medicine, 1-1 Seiryo-machi, Aoba-ku, Sendai, Miyagi, 980-8574, Japan
| | - Hisamichi Takagi
- Department of Radiological Technology, Faculty of Medicine, School of Health Sciences, Tohoku University, 21 Seiryo-machi, Aoba-ku, Sendai, Miyagi, 980-8575, Japan
| | - Noriyuki Kadoya
- Department of Radiation Oncology, Tohoku University Graduate School of Medicine, 1-1 Seiryo-machi, Aoba-ku, Sendai, Miyagi, 980-8574, Japan
| | - Kiyokazu Sato
- Department of Radiation Technology, Tohoku University Hospital, 1-1 Seiryo-machi, Aoba-ku, Sendai, Miyagi, 980-8574, Japan
| | - Rei Umezawa
- Department of Radiation Oncology, Tohoku University Graduate School of Medicine, 1-1 Seiryo-machi, Aoba-ku, Sendai, Miyagi, 980-8574, Japan
| | - Keiichi Jingu
- Department of Radiation Oncology, Tohoku University Graduate School of Medicine, 1-1 Seiryo-machi, Aoba-ku, Sendai, Miyagi, 980-8574, Japan
| | - Ken Takeda
- Department of Radiation Oncology, Tohoku University Graduate School of Medicine, 1-1 Seiryo-machi, Aoba-ku, Sendai, Miyagi, 980-8574, Japan
- Department of Radiological Technology, Faculty of Medicine, School of Health Sciences, Tohoku University, 21 Seiryo-machi, Aoba-ku, Sendai, Miyagi, 980-8575, Japan
| |
Collapse
|
43
|
Ahalya RK, Almutairi FM, Snekhalatha U, Dhanraj V, Aslam SM. RANet: a custom CNN model and quanvolutional neural network for the automated detection of rheumatoid arthritis in hand thermal images. Sci Rep 2023; 13:15638. [PMID: 37730717 PMCID: PMC10511741 DOI: 10.1038/s41598-023-42111-3] [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: 03/29/2023] [Accepted: 09/05/2023] [Indexed: 09/22/2023] Open
Abstract
Rheumatoid arthritis is an autoimmune disease which affects the small joints. Early prediction of RA is necessary for the treatment and management of the disease. The current work presents a deep learning and quantum computing-based automated diagnostic approach for RA in hand thermal imaging. The study's goals are (i) to develop a custom RANet model and compare its performance with the pretrained models and quanvolutional neural network (QNN) to distinguish between the healthy subjects and RA patients, (ii) To validate the performance of the custom model using feature selection method and classification using machine learning (ML) classifiers. The present study developed a custom RANet model and employed pre-trained models such as ResNet101V2, InceptionResNetV2, and DenseNet201 to classify the RA patients and normal subjects. The deep features extracted from the RA Net model are fed into the ML classifiers after the feature selection process. The RANet model, RA Net+ SVM, and QNN model produced an accuracy of 95%, 97% and 93.33% respectively in the classification of healthy groups and RA patients. The developed RANet and QNN models based on thermal imaging could be employed as an accurate automated diagnostic tool to differentiate between the RA and control groups.
Collapse
Affiliation(s)
- R K Ahalya
- Department of Biomedical Engineering, College of Engineering and Technology, SRM Institute of Science and Technology, Kattankulathur, Chennai, Tamil Nadu, 603203, India
- Department of Biomedical Engineering, Easwari Engineering college, Ramapuram, Chennai, Tamil Nadu, India
| | - Fadiyah M Almutairi
- Department of Information Systems, College of Computer and Information Sciences, Majmaah University, 11952, Al Majmaah, Saudi Arabia
| | - U Snekhalatha
- Department of Biomedical Engineering, College of Engineering and Technology, SRM Institute of Science and Technology, Kattankulathur, Chennai, Tamil Nadu, 603203, India.
| | - Varun Dhanraj
- Department of Physics and Astronomy, University of Waterloo, Waterloo, ON, Canada
| | - Shabnam M Aslam
- Department of Information Technology, College of Computer and Information Sciences, Majmaah University, 11952, Al Majmaah, Saudi Arabia
| |
Collapse
|
44
|
Canales-Fiscal MR, Tamez-Peña JG. Hybrid morphological-convolutional neural networks for computer-aided diagnosis. Front Artif Intell 2023; 6:1253183. [PMID: 37795497 PMCID: PMC10546173 DOI: 10.3389/frai.2023.1253183] [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: 07/08/2023] [Accepted: 08/30/2023] [Indexed: 10/06/2023] Open
Abstract
Training deep Convolutional Neural Networks (CNNs) presents challenges in terms of memory requirements and computational resources, often resulting in issues such as model overfitting and lack of generalization. These challenges can only be mitigated by using an excessive number of training images. However, medical image datasets commonly suffer from data scarcity due to the complexities involved in their acquisition, preparation, and curation. To address this issue, we propose a compact and hybrid machine learning architecture based on the Morphological and Convolutional Neural Network (MCNN), followed by a Random Forest classifier. Unlike deep CNN architectures, the MCNN was specifically designed to achieve effective performance with medical image datasets limited to a few hundred samples. It incorporates various morphological operations into a single layer and uses independent neural networks to extract information from each signal channel. The final classification is obtained by utilizing a Random Forest classifier on the outputs of the last neural network layer. We compare the classification performance of our proposed method with three popular deep CNN architectures (ResNet-18, ShuffleNet-V2, and MobileNet-V2) using two training approaches: full training and transfer learning. The evaluation was conducted on two distinct medical image datasets: the ISIC dataset for melanoma classification and the ORIGA dataset for glaucoma classification. Results demonstrate that the MCNN method exhibits reliable performance in melanoma classification, achieving an AUC of 0.94 (95% CI: 0.91 to 0.97), outperforming the popular CNN architectures. For the glaucoma dataset, the MCNN achieved an AUC of 0.65 (95% CI: 0.53 to 0.74), which was similar to the performance of the popular CNN architectures. This study contributes to the understanding of mathematical morphology in shallow neural networks for medical image classification and highlights the potential of hybrid architectures in effectively learning from medical image datasets that are limited by a small number of case samples.
Collapse
|
45
|
Boyd A, Ye Z, Prabhu S, Tjong MC, Zha Y, Zapaishchykova A, Vajapeyam S, Hayat H, Chopra R, Liu KX, Nabavidazeh A, Resnick A, Mueller S, Haas-Kogan D, Aerts HJ, Poussaint T, Kann BH. Expert-level pediatric brain tumor segmentation in a limited data scenario with stepwise transfer learning. MEDRXIV : THE PREPRINT SERVER FOR HEALTH SCIENCES 2023:2023.06.29.23292048. [PMID: 37425854 PMCID: PMC10327271 DOI: 10.1101/2023.06.29.23292048] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 07/11/2023]
Abstract
Purpose Artificial intelligence (AI)-automated tumor delineation for pediatric gliomas would enable real-time volumetric evaluation to support diagnosis, treatment response assessment, and clinical decision-making. Auto-segmentation algorithms for pediatric tumors are rare, due to limited data availability, and algorithms have yet to demonstrate clinical translation. Methods We leveraged two datasets from a national brain tumor consortium (n=184) and a pediatric cancer center (n=100) to develop, externally validate, and clinically benchmark deep learning neural networks for pediatric low-grade glioma (pLGG) segmentation using a novel in-domain, stepwise transfer learning approach. The best model [via Dice similarity coefficient (DSC)] was externally validated and subject to randomized, blinded evaluation by three expert clinicians wherein clinicians assessed clinical acceptability of expert- and AI-generated segmentations via 10-point Likert scales and Turing tests. Results The best AI model utilized in-domain, stepwise transfer learning (median DSC: 0.877 [IQR 0.715-0.914]) versus baseline model (median DSC 0.812 [IQR 0.559-0.888]; p<0.05). On external testing (n=60), the AI model yielded accuracy comparable to inter-expert agreement (median DSC: 0.834 [IQR 0.726-0.901] vs. 0.861 [IQR 0.795-0.905], p=0.13). On clinical benchmarking (n=100 scans, 300 segmentations from 3 experts), the experts rated the AI model higher on average compared to other experts (median Likert rating: 9 [IQR 7-9]) vs. 7 [IQR 7-9], p<0.05 for each). Additionally, the AI segmentations had significantly higher (p<0.05) overall acceptability compared to experts on average (80.2% vs. 65.4%). Experts correctly predicted the origins of AI segmentations in an average of 26.0% of cases. Conclusions Stepwise transfer learning enabled expert-level, automated pediatric brain tumor auto-segmentation and volumetric measurement with a high level of clinical acceptability. This approach may enable development and translation of AI imaging segmentation algorithms in limited data scenarios.
Collapse
Affiliation(s)
- Aidan Boyd
- Artificial Intelligence in Medicine (AIM) Program, Mass General Brigham, Harvard Medical School, Boston, MA
- Department of Radiation Oncology, Dana-Farber Cancer Institute and Brigham and Women’s Hospital, Harvard Medical School, Boston, MA
| | - Zezhong Ye
- Artificial Intelligence in Medicine (AIM) Program, Mass General Brigham, Harvard Medical School, Boston, MA
- Department of Radiation Oncology, Dana-Farber Cancer Institute and Brigham and Women’s Hospital, Harvard Medical School, Boston, MA
| | - Sanjay Prabhu
- Department of Radiology, Boston Children’s Hospital, Harvard Medical School, Boston, MA
| | - Michael C. Tjong
- Department of Radiation Oncology, Dana-Farber Cancer Institute and Brigham and Women’s Hospital, Harvard Medical School, Boston, MA
| | - Yining Zha
- Artificial Intelligence in Medicine (AIM) Program, Mass General Brigham, Harvard Medical School, Boston, MA
- Department of Radiation Oncology, Dana-Farber Cancer Institute and Brigham and Women’s Hospital, Harvard Medical School, Boston, MA
| | - Anna Zapaishchykova
- Artificial Intelligence in Medicine (AIM) Program, Mass General Brigham, Harvard Medical School, Boston, MA
- Department of Radiation Oncology, Dana-Farber Cancer Institute and Brigham and Women’s Hospital, Harvard Medical School, Boston, MA
| | - Sridhar Vajapeyam
- Department of Radiology, Boston Children’s Hospital, Harvard Medical School, Boston, MA
| | - Hasaan Hayat
- Artificial Intelligence in Medicine (AIM) Program, Mass General Brigham, Harvard Medical School, Boston, MA
- Department of Radiation Oncology, Dana-Farber Cancer Institute and Brigham and Women’s Hospital, Harvard Medical School, Boston, MA
| | - Rishi Chopra
- Artificial Intelligence in Medicine (AIM) Program, Mass General Brigham, Harvard Medical School, Boston, MA
- Department of Radiation Oncology, Dana-Farber Cancer Institute and Brigham and Women’s Hospital, Harvard Medical School, Boston, MA
| | - Kevin X. Liu
- Department of Radiation Oncology, Dana-Farber Cancer Institute and Brigham and Women’s Hospital, Harvard Medical School, Boston, MA
| | - Ali Nabavidazeh
- Center for Data-Driven Discovery in Biomedicine (D3b), Children’s Hospital of Philadelphia, Philadelphia, PA
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA
| | - Adam Resnick
- Center for Data-Driven Discovery in Biomedicine (D3b), Children’s Hospital of Philadelphia, Philadelphia, PA
- Department of Neurosurgery, Children’s Hospital of Philadelphia, Philadelphia, PA
| | - Sabine Mueller
- Department of Neurology, University of California San Francisco, San Francisco, California
- Department of Pediatrics, University of California San Francisco, San Francisco, California
- Department of Neurological Surgery, University of California San Francisco, San Francisco, California
| | - Daphne Haas-Kogan
- Department of Radiation Oncology, Dana-Farber Cancer Institute and Brigham and Women’s Hospital, Harvard Medical School, Boston, MA
| | - Hugo J.W.L. Aerts
- Artificial Intelligence in Medicine (AIM) Program, Mass General Brigham, Harvard Medical School, Boston, MA
- Department of Radiation Oncology, Dana-Farber Cancer Institute and Brigham and Women’s Hospital, Harvard Medical School, Boston, MA
- Department of Radiology, Brigham and Women’s Hospital, Dana-Farber Cancer Institute, Harvard Medical School, Boston, MA, USA
- Radiology and Nuclear Medicine, CARIM & GROW, Maastricht University, Maastricht, the Netherlands
| | - Tina Poussaint
- Department of Radiology, Boston Children’s Hospital, Harvard Medical School, Boston, MA
| | - Benjamin H. Kann
- Artificial Intelligence in Medicine (AIM) Program, Mass General Brigham, Harvard Medical School, Boston, MA
- Department of Radiation Oncology, Dana-Farber Cancer Institute and Brigham and Women’s Hospital, Harvard Medical School, Boston, MA
| |
Collapse
|
46
|
Yuan T, Edelmann D, Fan Z, Alwers E, Kather JN, Brenner H, Hoffmeister M. Machine learning in the identification of prognostic DNA methylation biomarkers among patients with cancer: A systematic review of epigenome-wide studies. Artif Intell Med 2023; 143:102589. [PMID: 37673571 DOI: 10.1016/j.artmed.2023.102589] [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: 07/21/2022] [Revised: 04/19/2023] [Accepted: 04/30/2023] [Indexed: 09/08/2023]
Abstract
BACKGROUND DNA methylation biomarkers have great potential in improving prognostic classification systems for patients with cancer. Machine learning (ML)-based analytic techniques might help overcome the challenges of analyzing high-dimensional data in relatively small sample sizes. This systematic review summarizes the current use of ML-based methods in epigenome-wide studies for the identification of DNA methylation signatures associated with cancer prognosis. METHODS We searched three electronic databases including PubMed, EMBASE, and Web of Science for articles published until 2 January 2023. ML-based methods and workflows used to identify DNA methylation signatures associated with cancer prognosis were extracted and summarized. Two authors independently assessed the methodological quality of included studies by a seven-item checklist adapted from 'A Tool to Assess Risk of Bias and Applicability of Prediction Model Studies (PROBAST)' and from the 'Reporting Recommendations for Tumor Marker Prognostic Studies (REMARK). Different ML methods and workflows used in included studies were summarized and visualized by a sunburst chart, a bubble chart, and Sankey diagrams, respectively. RESULTS Eighty-three studies were included in this review. Three major types of ML-based workflows were identified. 1) unsupervised clustering, 2) supervised feature selection, and 3) deep learning-based feature transformation. For the three workflows, the most frequently used ML techniques were consensus clustering, least absolute shrinkage and selection operator (LASSO), and autoencoder, respectively. The systematic review revealed that the performance of these approaches has not been adequately evaluated yet and that methodological and reporting flaws were common in the identified studies using ML techniques. CONCLUSIONS There is great heterogeneity in ML-based methodological strategies used by epigenome-wide studies to identify DNA methylation markers associated with cancer prognosis. In theory, most existing workflows could not handle the high multi-collinearity and potentially non-linearity interactions in epigenome-wide DNA methylation data. Benchmarking studies are needed to compare the relative performance of various approaches for specific cancer types. Adherence to relevant methodological and reporting guidelines are urgently needed.
Collapse
Affiliation(s)
- Tanwei Yuan
- Division of Clinical Epidemiology and Aging Research, German Cancer Research Center (DKFZ), Heidelberg, Germany; Medical Faculty Heidelberg, Heidelberg University, Heidelberg, Germany
| | - Dominic Edelmann
- Division of Biostatistics, German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Ziwen Fan
- Division of Clinical Epidemiology and Aging Research, German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Elizabeth Alwers
- Division of Clinical Epidemiology and Aging Research, German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Jakob Nikolas Kather
- Else Kroener Fresenius Center for Digital Health, Technical University Dresden, Dresden, Germany; Medical Oncology, National Center of Tumour Diseases (NCT), University Hospital Heidelberg, Heidelberg, Germany
| | - Hermann Brenner
- Division of Clinical Epidemiology and Aging Research, German Cancer Research Center (DKFZ), Heidelberg, Germany; Division of Preventive Oncology, German Cancer Research Center (DKFZ) and National Center for Tumor Diseases (NCT), Heidelberg, Germany; German Cancer Consortium (DKTK), German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Michael Hoffmeister
- Division of Clinical Epidemiology and Aging Research, German Cancer Research Center (DKFZ), Heidelberg, Germany.
| |
Collapse
|
47
|
Lee J, Warner E, Shaikhouni S, Bitzer M, Kretzler M, Gipson D, Pennathur S, Bellovich K, Bhat Z, Gadegbeku C, Massengill S, Perumal K, Saha J, Yang Y, Luo J, Zhang X, Mariani L, Hodgin JB, Rao A. Clustering-based spatial analysis (CluSA) framework through graph neural network for chronic kidney disease prediction using histopathology images. Sci Rep 2023; 13:12701. [PMID: 37543648 PMCID: PMC10404289 DOI: 10.1038/s41598-023-39591-8] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/21/2023] [Accepted: 07/27/2023] [Indexed: 08/07/2023] Open
Abstract
Machine learning applied to digital pathology has been increasingly used to assess kidney function and diagnose the underlying cause of chronic kidney disease (CKD). We developed a novel computational framework, clustering-based spatial analysis (CluSA), that leverages unsupervised learning to learn spatial relationships between local visual patterns in kidney tissue. This framework minimizes the need for time-consuming and impractical expert annotations. 107,471 histopathology images obtained from 172 biopsy cores were used in the clustering and in the deep learning model. To incorporate spatial information over the clustered image patterns on the biopsy sample, we spatially encoded clustered patterns with colors and performed spatial analysis through graph neural network. A random forest classifier with various groups of features were used to predict CKD. For predicting eGFR at the biopsy, we achieved a sensitivity of 0.97, specificity of 0.90, and accuracy of 0.95. AUC was 0.96. For predicting eGFR changes in one-year, we achieved a sensitivity of 0.83, specificity of 0.85, and accuracy of 0.84. AUC was 0.85. This study presents the first spatial analysis based on unsupervised machine learning algorithms. Without expert annotation, CluSA framework can not only accurately classify and predict the degree of kidney function at the biopsy and in one year, but also identify novel predictors of kidney function and renal prognosis.
Collapse
Affiliation(s)
- Joonsang Lee
- Department of Computational Medicine and Bioinformatics, University of Michigan, Ann Arbor, MI, USA.
| | - Elisa Warner
- Department of Computational Medicine and Bioinformatics, University of Michigan, Ann Arbor, MI, USA
| | - Salma Shaikhouni
- Department of Internal Medicine, Nephrology, University of Michigan, Ann Arbor, MI, USA
| | - Markus Bitzer
- Department of Internal Medicine, Nephrology, University of Michigan, Ann Arbor, MI, USA
| | - Matthias Kretzler
- Department of Internal Medicine, Nephrology, University of Michigan, Ann Arbor, MI, USA
| | - Debbie Gipson
- Department of Pediatrics, Pediatric Nephrology, University of Michigan, Ann Arbor, MI, USA
| | - Subramaniam Pennathur
- Department of Internal Medicine, Nephrology, University of Michigan, Ann Arbor, MI, USA
| | - Keith Bellovich
- Department of Internal Medicine, Nephrology, St. Clair Nephrology Research, Detroit, MI, USA
| | - Zeenat Bhat
- Department of Internal Medicine, Nephrology, Wayne State University, Detroit, MI, USA
| | - Crystal Gadegbeku
- Department of Internal Medicine, Nephrology, Cleveland Clinic, , Cleveland, OH, USA
| | - Susan Massengill
- Department of Pediatrics, Pediatric Nephrology, Levine Children's Hospital, Charlotte, NC, USA
| | - Kalyani Perumal
- Department of Internal Medicine, Nephrology, Department of JH Stroger Hospital, Chicago, IL, USA
| | - Jharna Saha
- Department of Pathology, University of Michigan, Ann Arbor, MI, USA
| | - Yingbao Yang
- Department of Pathology, University of Michigan, Ann Arbor, MI, USA
| | - Jinghui Luo
- Department of Pathology, University of Michigan, Ann Arbor, MI, USA
| | - Xin Zhang
- Department of Computational Medicine and Bioinformatics, University of Michigan, Ann Arbor, MI, USA
| | - Laura Mariani
- Department of Internal Medicine, Nephrology, University of Michigan, Ann Arbor, MI, USA
| | - Jeffrey B Hodgin
- Department of Pathology, University of Michigan, Ann Arbor, MI, USA.
| | - Arvind Rao
- Department of Computational Medicine and Bioinformatics, University of Michigan, Ann Arbor, MI, USA.
- Department of Biostatistics, University of Michigan, Ann Arbor, MI, USA.
- Department of Radiation Oncology, University of Michigan, Ann Arbor, MI, USA.
- Department of Biomedical Engineering, University of Michigan, Ann Arbor, MI, USA.
| |
Collapse
|
48
|
Hagiwara A, Fujita S, Kurokawa R, Andica C, Kamagata K, Aoki S. Multiparametric MRI: From Simultaneous Rapid Acquisition Methods and Analysis Techniques Using Scoring, Machine Learning, Radiomics, and Deep Learning to the Generation of Novel Metrics. Invest Radiol 2023; 58:548-560. [PMID: 36822661 PMCID: PMC10332659 DOI: 10.1097/rli.0000000000000962] [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: 12/01/2022] [Revised: 01/10/2023] [Indexed: 02/25/2023]
Abstract
ABSTRACT With the recent advancements in rapid imaging methods, higher numbers of contrasts and quantitative parameters can be acquired in less and less time. Some acquisition models simultaneously obtain multiparametric images and quantitative maps to reduce scan times and avoid potential issues associated with the registration of different images. Multiparametric magnetic resonance imaging (MRI) has the potential to provide complementary information on a target lesion and thus overcome the limitations of individual techniques. In this review, we introduce methods to acquire multiparametric MRI data in a clinically feasible scan time with a particular focus on simultaneous acquisition techniques, and we discuss how multiparametric MRI data can be analyzed as a whole rather than each parameter separately. Such data analysis approaches include clinical scoring systems, machine learning, radiomics, and deep learning. Other techniques combine multiple images to create new quantitative maps associated with meaningful aspects of human biology. They include the magnetic resonance g-ratio, the inner to the outer diameter of a nerve fiber, and the aerobic glycolytic index, which captures the metabolic status of tumor tissues.
Collapse
Affiliation(s)
- Akifumi Hagiwara
- From theDepartment of Radiology, Juntendo University School of Medicine, Tokyo, Japan
| | - Shohei Fujita
- From theDepartment of Radiology, Juntendo University School of Medicine, Tokyo, Japan
- Department of Radiology, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan
| | - Ryo Kurokawa
- Department of Radiology, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan
- Division of Neuroradiology, Department of Radiology, University of Michigan, Ann Arbor, Michigan
| | - Christina Andica
- From theDepartment of Radiology, Juntendo University School of Medicine, Tokyo, Japan
| | - Koji Kamagata
- From theDepartment of Radiology, Juntendo University School of Medicine, Tokyo, Japan
| | - Shigeki Aoki
- From theDepartment of Radiology, Juntendo University School of Medicine, Tokyo, Japan
| |
Collapse
|
49
|
Kalapos A, Szabó L, Dohy Z, Kiss M, Merkely B, Gyires-Tóth B, Vágó H. Automated T1 and T2 mapping segmentation on cardiovascular magnetic resonance imaging using deep learning. Front Cardiovasc Med 2023; 10:1147581. [PMID: 37522085 PMCID: PMC10374405 DOI: 10.3389/fcvm.2023.1147581] [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: 01/18/2023] [Accepted: 06/19/2023] [Indexed: 08/01/2023] Open
Abstract
Introduction Structural and functional heart abnormalities can be examined non-invasively with cardiac magnetic resonance imaging (CMR). Thanks to the development of MR devices, diagnostic scans can capture more and more relevant information about possible heart diseases. T1 and T2 mapping are such novel technology, providing tissue specific information even without the administration of contrast material. Artificial intelligence solutions based on deep learning have demonstrated state-of-the-art results in many application areas, including medical imaging. More specifically, automated tools applied at cine sequences have revolutionized volumetric CMR reporting in the past five years. Applying deep learning models to T1 and T2 mapping images can similarly improve the efficiency of post-processing pipelines and consequently facilitate diagnostic processes. Methods In this paper, we introduce a deep learning model for myocardium segmentation trained on over 7,000 raw CMR images from 262 subjects of heterogeneous disease etiology. The data were labeled by three experts. As part of the evaluation, Dice score and Hausdorff distance among experts is calculated, and the expert consensus is compared with the model's predictions. Results Our deep learning method achieves 86% mean Dice score, while contours provided by three experts on the same data show 90% mean Dice score. The method's accuracy is consistent across epicardial and endocardial contours, and on basal, midventricular slices, with only 5% lower results on apical slices, which are often challenging even for experts. Conclusions We trained and evaluated a deep learning based segmentation model on 262 heterogeneous CMR cases. Applying deep neural networks to T1 and T2 mapping could similarly improve diagnostic practices. Using the fine details of T1 and T2 mapping images and high-quality labels, the objective of this research is to approach human segmentation accuracy with deep learning.
Collapse
Affiliation(s)
- András Kalapos
- Department of Telecommunications and Media Informatics, Faculty of Electrical Engineering and Informatics, Budapest University of Technology and Economics, Budapest, Hungary
| | - Liliána Szabó
- Semmelweis University, Heart and Vascular Centre, Budapest, Hungary
| | - Zsófia Dohy
- Semmelweis University, Heart and Vascular Centre, Budapest, Hungary
| | - Máté Kiss
- Siemens Healthcare, Budapest, Hungary
| | - Béla Merkely
- Semmelweis University, Heart and Vascular Centre, Budapest, Hungary
- Department of Sports Medicine, Semmelweis University, Budapest, Hungary
| | - Bálint Gyires-Tóth
- Department of Telecommunications and Media Informatics, Faculty of Electrical Engineering and Informatics, Budapest University of Technology and Economics, Budapest, Hungary
| | - Hajnalka Vágó
- Semmelweis University, Heart and Vascular Centre, Budapest, Hungary
- Department of Sports Medicine, Semmelweis University, Budapest, Hungary
| |
Collapse
|
50
|
Hansun S, Argha A, Alinejad-Rokny H, Liaw ST, Celler BG, Marks GB. Revisiting Transfer Learning Method for Tuberculosis Diagnosis. ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. ANNUAL INTERNATIONAL CONFERENCE 2023; 2023:1-4. [PMID: 38083096 DOI: 10.1109/embc40787.2023.10340441] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/18/2023]
Abstract
Transfer learning (TL) has been proven to be a good strategy for solving domain-specific problems in many deep learning (DL) applications. Typically, in TL, a pre-trained DL model is used as a feature extractor and the extracted features are then fed to a newly trained classifier as the model head. In this study, we propose a new ensemble approach of transfer learning that uses multiple neural network classifiers at once in the model head. We compared the classification results of the proposed ensemble approach with the direct approach of several popular models, namely VGG-16, ResNet-50, and MobileNet, on two publicly available tuberculosis datasets, i.e., Montgomery County (MC) and Shenzhen (SZ) datasets. Moreover, we also compared the results when a fully pre-trained DL model was used for feature extraction versus the cases in which the features were obtained from a middle layer of the pre-trained DL model. Several metrics derived from confusion matrix results were used, namely the accuracy (ACC), sensitivity (SNS), specificity (SPC), precision (PRC), and F1-score. We concluded that the proposed ensemble approach outperformed the direct approach. Best result was achieved by ResNet-50 when the features were extracted from a middle layer with an accuracy of 91.2698% on MC dataset.Clinical Relevance- The proposed ensemble approach could increase the detection accuracy of 7-8% for Montgomery County dataset and 4-5% for Shenzhen dataset.
Collapse
|