Related Experiment Video
Updated: Jul 17, 2026
Patient-specific Modeling of the Heart: Estimation of Ventricular Fiber Orientations
Published on: January 8, 2013
Identifying Hypertrophic or Dilated Cardiomyopathy: Development and Validation of a Fine-Tuned ResNet50 Model Based
Jiayu Xu1, Bo Chen2, Weiyang Liu1
1Graduate School, Chinese People's Liberation Army General Hospital, Beijing 100853, China.
Insights
A novel deep learning model can identify hypertrophic cardiomyopathy (HCM) and dilated cardiomyopathy (DCM) using standard electrocardiogram (ECG) images. This AI tool shows promise for inexpensive and early detection of these heart conditions.
Area of Science:
- Cardiology
- Artificial Intelligence
- Medical Imaging
Background:
- Hypertrophic cardiomyopathy (HCM) and dilated cardiomyopathy (DCM) lack established non-invasive diagnostic tools.
- Early and accurate detection of HCM and DCM is crucial for patient management and outcomes.
Purpose of the Study:
- To develop and validate a deep learning model for identifying HCM and DCM using 12-lead electrocardiogram (ECG) images.
- To assess the model's performance and identify key ECG regions contributing to predictions.
Main Methods:
- A ResNet50 deep learning architecture was fine-tuned using 2849 ECG images (171 HCM, 364 DCM, 2314 controls).
- Stratified five-fold cross-validation was employed for robust model training and testing.
- Gradient-weighted Class Activation Mapping (Grad-CAM) was used for model interpretability.
Main Results:
- The model achieved high accuracy in distinguishing DCM (AUROC 0.996, AUPRC 0.940) and HCM (AUROC 0.980, AUPRC 0.953).
- Temporal validation confirmed the model's prospective stability.
- Grad-CAM analysis highlighted anterior and anteroseptal leads as critical for predictions.
Conclusions:
- A fine-tuned ResNet50 model effectively identifies HCM and DCM from standard ECGs.
- This AI-driven approach offers a promising, cost-effective method for early detection of these cardiomyopathies.
- The model's interpretability provides insights into ECG markers for HCM and DCM.
Abstract:
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.
