1
|
Chen WW, Kuo L, Lin YX, Yu WC, Tseng CC, Lin YJ, Huang CC, Chang SL, Wu JCH, Chen CK, Weng CY, Chan S, Lin WW, Hsieh YC, Lin MC, Fu YC, Chen T, Chen SA, Lu HHS. A Deep Learning Approach to Classify Fabry Cardiomyopathy from Hypertrophic Cardiomyopathy Using Cine Imaging on Cardiac Magnetic Resonance. Int J Biomed Imaging 2024; 2024:6114826. [PMID: 38706878 PMCID: PMC11068448 DOI: 10.1155/2024/6114826] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/01/2023] [Revised: 03/20/2024] [Accepted: 03/23/2024] [Indexed: 05/07/2024] Open
Abstract
A challenge in accurately identifying and classifying left ventricular hypertrophy (LVH) is distinguishing it from hypertrophic cardiomyopathy (HCM) and Fabry disease. The reliance on imaging techniques often requires the expertise of multiple specialists, including cardiologists, radiologists, and geneticists. This variability in the interpretation and classification of LVH leads to inconsistent diagnoses. LVH, HCM, and Fabry cardiomyopathy can be differentiated using T1 mapping on cardiac magnetic resonance imaging (MRI). However, differentiation between HCM and Fabry cardiomyopathy using echocardiography or MRI cine images is challenging for cardiologists. Our proposed system named the MRI short-axis view left ventricular hypertrophy classifier (MSLVHC) is a high-accuracy standardized imaging classification model developed using AI and trained on MRI short-axis (SAX) view cine images to distinguish between HCM and Fabry disease. The model achieved impressive performance, with an F1-score of 0.846, an accuracy of 0.909, and an AUC of 0.914 when tested on the Taipei Veterans General Hospital (TVGH) dataset. Additionally, a single-blinding study and external testing using data from the Taichung Veterans General Hospital (TCVGH) demonstrated the reliability and effectiveness of the model, achieving an F1-score of 0.727, an accuracy of 0.806, and an AUC of 0.918, demonstrating the model's reliability and usefulness. This AI model holds promise as a valuable tool for assisting specialists in diagnosing LVH diseases.
Collapse
Affiliation(s)
- Wei-Wen Chen
- Institute of Computer Science and Engineering, National Yang-Ming University, Hsinchu, Taiwan
| | - Ling Kuo
- Faculty of Medicine and Institute of Clinical Medicine, National Yang Ming Chiao Tung University, Taipei, Taiwan
- Division of Cardiology, Department of Medicine, Taipei Veterans General Hospital, Taipei, Taiwan
- Department of Biomedical Imaging and Radiological Sciences, National Yang-Ming University, Taipei, Taiwan
| | - Yi-Xun Lin
- Institute of Statistics, National Yang Ming Chiao Tung University, Hsinchu, Taiwan
| | - Wen-Chung Yu
- Faculty of Medicine and Institute of Clinical Medicine, National Yang Ming Chiao Tung University, Taipei, Taiwan
- Division of Cardiology, Department of Medicine, Taipei Veterans General Hospital, Taipei, Taiwan
| | - Chien-Chao Tseng
- Institute of Computer Science and Engineering, National Yang-Ming University, Hsinchu, Taiwan
| | - Yenn-Jiang Lin
- Faculty of Medicine and Institute of Clinical Medicine, National Yang Ming Chiao Tung University, Taipei, Taiwan
- Division of Cardiology, Department of Medicine, Taipei Veterans General Hospital, Taipei, Taiwan
| | - Ching-Chun Huang
- Institute of Computer Science and Engineering, National Yang-Ming University, Hsinchu, Taiwan
| | - Shih-Lin Chang
- Faculty of Medicine and Institute of Clinical Medicine, National Yang Ming Chiao Tung University, Taipei, Taiwan
- Division of Cardiology, Department of Medicine, Taipei Veterans General Hospital, Taipei, Taiwan
| | - Jacky Chung-Hao Wu
- Institute of Statistics, National Yang Ming Chiao Tung University, Hsinchu, Taiwan
| | - Chun-Ku Chen
- Department of Radiology, Taipei Veterans General Hospital, Taipei, Taiwan
| | - Ching-Yao Weng
- Department of Radiology, Taipei Veterans General Hospital, Taipei, Taiwan
| | - Siwa Chan
- Department of Radiology, Taichung Veterans General Hospital, Taichung, Taiwan
- Department of Post-Baccalaureate Medicine, National Chung Hsing University, Taichung, Taiwan
| | - Wei-Wen Lin
- Cardiovascular Center, Taichung Veterans General Hospital, Taichung, Taiwan
| | - Yu-Cheng Hsieh
- Cardiovascular Center, Taichung Veterans General Hospital, Taichung, Taiwan
| | - Ming-Chih Lin
- Department of Post-Baccalaureate Medicine, National Chung Hsing University, Taichung, Taiwan
- Department of Pediatric Cardiology, Taichung Veterans General Hospital, Taichung, Taiwan
- Children's Medical Center, Taichung Veterans General Hospital, Taichung, Taiwan
| | - Yun-Ching Fu
- Department of Pediatric Cardiology, Taichung Veterans General Hospital, Taichung, Taiwan
- Children's Medical Center, Taichung Veterans General Hospital, Taichung, Taiwan
- Department of Pediatrics, School of Medicine, National Chung-Hsing University, Taichung, Taiwan
| | - Tsung Chen
- Institute of Statistics, National Yang Ming Chiao Tung University, Hsinchu, Taiwan
| | - Shih-Ann Chen
- Faculty of Medicine and Institute of Clinical Medicine, National Yang Ming Chiao Tung University, Taipei, Taiwan
- Division of Cardiology, Department of Medicine, Taipei Veterans General Hospital, Taipei, Taiwan
- Cardiovascular Center, Taichung Veterans General Hospital, Taichung, Taiwan
- College of Medicine, National Chung Hsing University, Taichung, Taiwan
| | - Henry Horng-Shing Lu
- Institute of Statistics, National Yang Ming Chiao Tung University, Hsinchu, Taiwan
- Department of Statistics and Data Science, Cornell University, Ithaca, New York, USA
| |
Collapse
|
2
|
Lin CY, Wu JCH, Kuan YM, Liu YC, Chang PY, Chen JP, Lu HHS, Lee OKS. Precision Identification of Locally Advanced Rectal Cancer in Denoised CT Scans Using EfficientNet and Voting System Algorithms. Bioengineering (Basel) 2024; 11:399. [PMID: 38671820 PMCID: PMC11048699 DOI: 10.3390/bioengineering11040399] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/04/2024] [Revised: 04/11/2024] [Accepted: 04/16/2024] [Indexed: 04/28/2024] Open
Abstract
BACKGROUND AND OBJECTIVE Local advanced rectal cancer (LARC) poses significant treatment challenges due to its location and high recurrence rates. Accurate early detection is vital for treatment planning. With magnetic resonance imaging (MRI) being resource-intensive, this study explores using artificial intelligence (AI) to interpret computed tomography (CT) scans as an alternative, providing a quicker, more accessible diagnostic tool for LARC. METHODS In this retrospective study, CT images of 1070 T3-4 rectal cancer patients from 2010 to 2022 were analyzed. AI models, trained on 739 cases, were validated using two test sets of 134 and 197 cases. By utilizing techniques such as nonlocal mean filtering, dynamic histogram equalization, and the EfficientNetB0 algorithm, we identified images featuring characteristics of a positive circumferential resection margin (CRM) for the diagnosis of locally advanced rectal cancer (LARC). Importantly, this study employs an innovative approach by using both hard and soft voting systems in the second stage to ascertain the LARC status of cases, thus emphasizing the novelty of the soft voting system for improved case identification accuracy. The local recurrence rates and overall survival of the cases predicted by our model were assessed to underscore its clinical value. RESULTS The AI model exhibited high accuracy in identifying CRM-positive images, achieving an area under the curve (AUC) of 0.89 in the first test set and 0.86 in the second. In a patient-based analysis, the model reached AUCs of 0.84 and 0.79 using a hard voting system. Employing a soft voting system, the model attained AUCs of 0.93 and 0.88, respectively. Notably, AI-identified LARC cases exhibited a significantly higher five-year local recurrence rate and displayed a trend towards increased mortality across various thresholds. Furthermore, the model's capability to predict adverse clinical outcomes was superior to those of traditional assessments. CONCLUSION AI can precisely identify CRM-positive LARC cases from CT images, signaling an increased local recurrence and mortality rate. Our study presents a swifter and more reliable method for detecting LARC compared to traditional CT or MRI techniques.
Collapse
Affiliation(s)
- Chun-Yu Lin
- Institute of Clinical Medicine, National Yang Ming Chiao Tung University, Taipei 11221, Taiwan;
- Division of Colorectal Surgery, Department of Surgery, Taichung Veterans General Hospital, Taichung 40705, Taiwan
- School of Medicine, National Defense Medical Center, Taipei 11490, Taiwan
| | - Jacky Chung-Hao Wu
- Institute of Statistics, National Yang Ming Chiao Tung University, Hsinchu 300093, Taiwan;
| | - Yen-Ming Kuan
- Institute of Multimedia Engineering, National Yang Ming Chiao Tung University, Hsinchu 300093, Taiwan;
| | - Yi-Chun Liu
- Department of Post-Baccalaureate Medicine, College of Medicine, National Chung Hsing University, Taichung 402202, Taiwan;
- Department of Radiation Oncology, Taichung Veterans General Hospital, Taichung 40705, Taiwan
| | - Pi-Yi Chang
- Department of Radiology, Taichung Veterans General Hospital, Taichung 40705, Taiwan;
| | - Jun-Peng Chen
- Biostatistics Task Force, Taichung Veterans General Hospital, Taichung 40705, Taiwan;
| | - Henry Horng-Shing Lu
- Institute of Statistics, National Yang Ming Chiao Tung University, Hsinchu 300093, Taiwan;
- Department of Statistics and Data Science, Cornell University, Ithaca, NY 14853, USA
| | - Oscar Kuang-Sheng Lee
- Institute of Clinical Medicine, National Yang Ming Chiao Tung University, Taipei 11221, Taiwan;
- Stem Cell Research Center, National Yang Ming Chiao Tung University, Taipei 11221, Taiwan
- Department of Medical Research, Taipei Veterans General Hospital, Taipei 112201, Taiwan
- Department of Orthopedics, China Medical University Hospital, Taichung 40402, Taiwan
- Center for Translational Genomics & Regenerative Medicine Research, China Medical University Hospital, Taichung 40402, Taiwan
| |
Collapse
|
3
|
Wu JCH, Yu HW, Tsai TH, Lu HHS. Dynamically Synthetic Images for Federated Learning of medical images. Comput Methods Programs Biomed 2023; 242:107845. [PMID: 37852147 DOI: 10.1016/j.cmpb.2023.107845] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 03/01/2023] [Revised: 09/28/2023] [Accepted: 10/03/2023] [Indexed: 10/20/2023]
Abstract
BACKGROUND To develop deep learning models for medical diagnosis, it is important to collect more medical data from several medical institutions. Due to the regulations for privacy concerns, it is infeasible to collect data from various medical institutions to one institution for centralized learning. Federated Learning (FL) provides a feasible approach to jointly train the deep learning model with data stored in various medical institutions instead of collected together. However, the resulting FL models could be biased towards institutions with larger training datasets. METHODOLOGY In this study, we propose the applicable method of Dynamically Synthetic Images for Federated Learning (DSIFL) that aims to integrate the information of local institutions with heterogeneous types of data. The main technique of DSIFL is to develop a synthetic method that can dynamically adjust the number of synthetic images similar to local data that are misclassified by the current model. The resulting global model can handle the diversity in heterogeneous types of data collected in local medical institutions by including the training of synthetic images similar to misclassified cases in local collections. RESULTS In model performance evaluation metrics, we focus on the accuracy of each client's dataset. Finally, the accuracy of the model of DSIFL in the experiments can achieve the higher accuracy of the FL approach. CONCLUSION In this study, we propose the framework of DSIFL that achieves improvements over the conventional FL approach. We conduct empirical studies with two kinds of medical images. We compare the performance by variants of FL vs. DSIFL approaches. The performance by individual training is used as the baseline, whereas the performance by centralized learning is used as the target for the comparison studies. The empirical findings suggest that the DSIFL has improved performance over the FL via the technique of dynamically synthetic images in training.
Collapse
Affiliation(s)
- Jacky Chung-Hao Wu
- Institute of Statistics, National Yang Ming Chiao Tung University, Hsinchu, Taiwan, ROC
| | - Hsuan-Wen Yu
- Institute of Statistics, National Yang Ming Chiao Tung University, Hsinchu, Taiwan, ROC
| | - Tsung-Hung Tsai
- Institute of Statistics, National Yang Ming Chiao Tung University, Hsinchu, Taiwan, ROC
| | - Henry Horng-Shing Lu
- Institute of Statistics, National Yang Ming Chiao Tung University, Hsinchu, Taiwan, ROC; Department of Statistics and Data Science, Cornell University, New York, USA.
| |
Collapse
|