Identifying Hypertrophic or Dilated Cardiomyopathy: Development and Validation of a Fine-Tuned ResNet50 Model Based on Electrocardiogram Image

There is no established detecting tool for hypertrophic cardiomyopathy (HCM) and dilated cardiomyopathy (DCM). This study aimed to develop a deep-learning-based model for identifying HCM and DCM using standard 12-lead electrocardiogram (ECG) images. We obtained a cohort of patients with HCM (171 ECG...

Full description

Saved in:
Bibliographic Details
Main Authors: Jiayu Xu, Bo Chen, Weiyang Liu, Wei Dong, Yan Zhuang, Peifang Zhang, Kunlun He
Format: Article
Language:English
Published: MDPI AG 2025-02-01
Series:Bioengineering
Subjects:
Online Access:https://www.mdpi.com/2306-5354/12/3/250
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850204094114824192
author Jiayu Xu
Bo Chen
Weiyang Liu
Wei Dong
Yan Zhuang
Peifang Zhang
Kunlun He
author_facet Jiayu Xu
Bo Chen
Weiyang Liu
Wei Dong
Yan Zhuang
Peifang Zhang
Kunlun He
author_sort Jiayu Xu
collection DOAJ
description There is no established detecting tool for hypertrophic cardiomyopathy (HCM) and dilated cardiomyopathy (DCM). This study aimed to develop a deep-learning-based model for identifying HCM and DCM using standard 12-lead electrocardiogram (ECG) images. We obtained a cohort of patients with HCM (171 ECG images) or DCM (364 ECG images), confirmed by cardiovascular magnetic resonance (CMR) examinations, who underwent both ECG and CMR within 30 days at our institution. Age- and sex-matched healthy controls (2314 ECG images) were selected from our Health Check Center. A total of 2849 ECG images were processed via a fine-tuned ResNet50 architecture, with stratified five-fold cross-validation for model training, validation, and testing. The proposed model demonstrated strong performance in distinguishing DCM, achieving an area under the receiver operating curve (AUROC) of 0.996 and an area under the precision–recall curve (AUPRC) of 0.940. For the detection of HCM, the model also achieved an AUROC of 0.980 and an AUPRC of 0.953, respectively. The model prospectively exhibited stability in temporal validation. Furthermore, representative images of the Gradient-weighted Class Activation Mapping (Grad-CAM) technique analysis showed the regions corresponding to the anterior and anteroseptal leads were the most important areas for the prediction of HCM or DCM. This temporally validated fine-tuned ResNet50 model shows promise to inexpensively detect individuals with HCM or DCM.
format Article
id doaj-art-b5ad8cfa96e44e7cacd30c4726b77ccf
institution OA Journals
issn 2306-5354
language English
publishDate 2025-02-01
publisher MDPI AG
record_format Article
series Bioengineering
spelling doaj-art-b5ad8cfa96e44e7cacd30c4726b77ccf2025-08-20T02:11:21ZengMDPI AGBioengineering2306-53542025-02-0112325010.3390/bioengineering12030250Identifying Hypertrophic or Dilated Cardiomyopathy: Development and Validation of a Fine-Tuned ResNet50 Model Based on Electrocardiogram ImageJiayu Xu0Bo Chen1Weiyang Liu2Wei Dong3Yan Zhuang4Peifang Zhang5Kunlun He6Graduate School, Chinese People’s Liberation Army General Hospital, Beijing 100853, ChinaMedical Innovation Research Division, Chinese People’s Liberation Army General Hospital, Beijing 100853, ChinaGraduate School, Chinese People’s Liberation Army General Hospital, Beijing 100853, ChinaCardiology Department, Sixth Medical Center of Chinese People’s Liberation Army General Hospital, Beijing 100853, ChinaMedical Innovation Research Division, Chinese People’s Liberation Army General Hospital, Beijing 100853, ChinaBiomind Technology Inc., Beijing 101300, ChinaMedical Innovation Research Division, Chinese People’s Liberation Army General Hospital, Beijing 100853, ChinaThere is no established detecting tool for hypertrophic cardiomyopathy (HCM) and dilated cardiomyopathy (DCM). This study aimed to develop a deep-learning-based model for identifying HCM and DCM using standard 12-lead electrocardiogram (ECG) images. We obtained a cohort of patients with HCM (171 ECG images) or DCM (364 ECG images), confirmed by cardiovascular magnetic resonance (CMR) examinations, who underwent both ECG and CMR within 30 days at our institution. Age- and sex-matched healthy controls (2314 ECG images) were selected from our Health Check Center. A total of 2849 ECG images were processed via a fine-tuned ResNet50 architecture, with stratified five-fold cross-validation for model training, validation, and testing. The proposed model demonstrated strong performance in distinguishing DCM, achieving an area under the receiver operating curve (AUROC) of 0.996 and an area under the precision–recall curve (AUPRC) of 0.940. For the detection of HCM, the model also achieved an AUROC of 0.980 and an AUPRC of 0.953, respectively. The model prospectively exhibited stability in temporal validation. Furthermore, representative images of the Gradient-weighted Class Activation Mapping (Grad-CAM) technique analysis showed the regions corresponding to the anterior and anteroseptal leads were the most important areas for the prediction of HCM or DCM. This temporally validated fine-tuned ResNet50 model shows promise to inexpensively detect individuals with HCM or DCM.https://www.mdpi.com/2306-5354/12/3/250artificial intelligenceelectrocardiogram imagehypertrophic cardiomyopathydilated cardiomyopathydiagnosis
spellingShingle Jiayu Xu
Bo Chen
Weiyang Liu
Wei Dong
Yan Zhuang
Peifang Zhang
Kunlun He
Identifying Hypertrophic or Dilated Cardiomyopathy: Development and Validation of a Fine-Tuned ResNet50 Model Based on Electrocardiogram Image
Bioengineering
artificial intelligence
electrocardiogram image
hypertrophic cardiomyopathy
dilated cardiomyopathy
diagnosis
title Identifying Hypertrophic or Dilated Cardiomyopathy: Development and Validation of a Fine-Tuned ResNet50 Model Based on Electrocardiogram Image
title_full Identifying Hypertrophic or Dilated Cardiomyopathy: Development and Validation of a Fine-Tuned ResNet50 Model Based on Electrocardiogram Image
title_fullStr Identifying Hypertrophic or Dilated Cardiomyopathy: Development and Validation of a Fine-Tuned ResNet50 Model Based on Electrocardiogram Image
title_full_unstemmed Identifying Hypertrophic or Dilated Cardiomyopathy: Development and Validation of a Fine-Tuned ResNet50 Model Based on Electrocardiogram Image
title_short Identifying Hypertrophic or Dilated Cardiomyopathy: Development and Validation of a Fine-Tuned ResNet50 Model Based on Electrocardiogram Image
title_sort identifying hypertrophic or dilated cardiomyopathy development and validation of a fine tuned resnet50 model based on electrocardiogram image
topic artificial intelligence
electrocardiogram image
hypertrophic cardiomyopathy
dilated cardiomyopathy
diagnosis
url https://www.mdpi.com/2306-5354/12/3/250
work_keys_str_mv AT jiayuxu identifyinghypertrophicordilatedcardiomyopathydevelopmentandvalidationofafinetunedresnet50modelbasedonelectrocardiogramimage
AT bochen identifyinghypertrophicordilatedcardiomyopathydevelopmentandvalidationofafinetunedresnet50modelbasedonelectrocardiogramimage
AT weiyangliu identifyinghypertrophicordilatedcardiomyopathydevelopmentandvalidationofafinetunedresnet50modelbasedonelectrocardiogramimage
AT weidong identifyinghypertrophicordilatedcardiomyopathydevelopmentandvalidationofafinetunedresnet50modelbasedonelectrocardiogramimage
AT yanzhuang identifyinghypertrophicordilatedcardiomyopathydevelopmentandvalidationofafinetunedresnet50modelbasedonelectrocardiogramimage
AT peifangzhang identifyinghypertrophicordilatedcardiomyopathydevelopmentandvalidationofafinetunedresnet50modelbasedonelectrocardiogramimage
AT kunlunhe identifyinghypertrophicordilatedcardiomyopathydevelopmentandvalidationofafinetunedresnet50modelbasedonelectrocardiogramimage