Ensemble learning of myocardial displacements for myocardial infarction detection in echocardiography

Frontiers in Cardiovascular Medicine

Cardiovascular Medicine

Dai Tran¹  Vinh Le²  Thuy Nguyen²  Phi Nguyen³  Long Tran³  Hung Pham⁴  Phuong Tran⁴  Hanh Van⁴  Quang Nguyen⁴  Thanh Le⁴  Bach Do⁴  Tuan Nguyen⁵  Hieu Pham⁵ 

[1] Cardiovascular Center, E Hospital, Hanoi, Vietnam;Faculty of Information Technology, VNU University of Engineering and Technology, Hanoi, Vietnam;Institute for Artificial Intelligence, VNU University of Engineering and Technology, Hanoi, Vietnam;Vietnam National Heart Institute, Bach Mai Hospital, Hanoi, Vietnam;VinUni-Illinois Smart Health Center, VinUniversity, Hanoi, Vietnam;College of Engineering and Computer Science, VinUniversity, Hanoi, Vietnam;

关键词: echocardiography;    image segmentation;    deep learning;    machine learning;    myocardial infarction;    motion estimation;    regional wall motion abnormality;    diagnostic ability;   

DOI  :  10.3389/fcvm.2023.1185172

 received in 2023-03-13, accepted in 2023-09-18,  发布年份 2023

来源: Frontiers

【 摘 要 】

BackgroundEarly detection and localization of myocardial infarction (MI) can reduce the severity of cardiac damage through timely treatment interventions. In recent years, deep learning techniques have shown promise for detecting MI in echocardiographic images. Existing attempts typically formulate this task as classification and rely on a single segmentation model to estimate myocardial segment displacements. However, there has been no examination of how segmentation accuracy affects MI classification performance or the potential benefits of using ensemble learning approaches. Our study investigates this relationship and introduces a robust method that combines features from multiple segmentation models to improve MI classification performance by leveraging ensemble learning.Materials and MethodsOur method combines myocardial segment displacement features from multiple segmentation models, which are then input into a typical classifier to estimate the risk of MI. We validated the proposed approach on two datasets: the public HMC-QU dataset (109 echocardiograms) for training and validation, and an E-Hospital dataset (60 echocardiograms) from a local clinical site in Vietnam for independent testing. Model performance was evaluated based on accuracy, sensitivity, and specificity.ResultsThe proposed approach demonstrated excellent performance in detecting MI. It achieved an F1 score of 0.942, corresponding to an accuracy of 91.4%, a sensitivity of 94.1%, and a specificity of 88.3%. The results showed that the proposed approach outperformed the state-of-the-art feature-based method, which had a precision of 85.2%, a specificity of 70.1%, a sensitivity of 85.9%, an accuracy of 85.5%, and an accuracy of 80.2% on the HMC-QU dataset. On the external validation set, the proposed model still performed well, with an F1 score of 0.8, an accuracy of 76.7%, a sensitivity of 77.8%, and a specificity of 75.0%.ConclusionsOur study demonstrated the ability to accurately predict MI in echocardiograms by combining information from several segmentation models. Further research is necessary to determine its potential use in clinical settings as a tool to assist cardiologists and technicians with objective assessments and reduce dependence on operator subjectivity. Our research codes are available on GitHub at https://github.com/vinuni-vishc/mi-detection-echo.

【 授权许可】

Unknown   
© 2023 Nguyen, Nguyen, Tran, Pham, Nguyen, Le, Van, Do, Tran, Le, Nguyen, Tran and Pham.