Key result
Novel deep learning framework classifies apical hypertrophic cardiomyopathy subtypes with ~96% accuracy.
Why the study?
Accurate classification of apical hypertrophic cardiomyopathy subtypes is challenging due to morphological variability, overlapping phenotypes, and limited apex visualization with conventional echocardiography.
Does a deep learning framework integrating MG-APSO-DnCNN and GIN improve the accurate classification of apical hypertrophic cardiomyopathy subtypes from echocardiograms?
Does a deep learning framework integrating MG-APSO-DnCNN and GIN improve the accurate classification of apical hypertrophic cardiomyopathy subtypes from echocardiograms?
p-value: p=<0.001
A novel deep learning framework integrating denoising, segmentation, and graph-based learning can accurately classify apical hypertrophic cardiomyopathy subtypes from echocardiograms with 96.2% accuracy.
Deep learning may aid apical hypertrophic cardiomyopathy subtyping on limited echocardiography; leaves open prospective validation before clinical adoption.
INTRODUCTION: Accurate classification of apical hypertrophic cardiomyopathy (ApHCM) subtypes is challenging due to morphological variability and overlapping phenotypes. Conventional echocardiography provides limited visualization of the apex. Artifacts induced during left ventricular opacification (LVO) complicate diagnostic interpretation. A deep learning-based framework enhances image quality and improves subtype classification. MATERIALS AND METHODS: In this work, a deep learning-based framework is used for ApHCM subtype classification. Apical four-chamber end-diastolic frames from 3,200 individual patients were extracted from the EchoNet-Dynamic Dataset. Two cardiology experts manually annotated images into pure ApHCM (PApHCM), relative ApHCM (R-ApHCM), mixed ApHCM (M-ApHCM), and normal classes, based on apical wall thickness and morphological characteristics, using a computer vision annotation tool. A deep learning pipeline integrated multilevel graph-based adaptive particle swarm optimization with a deep denoised convolutional neural network (MG-APSO-DnCNN) to suppress reverberation and clutter artifacts from LVO echocardiograms. Enhanced images were then segmented using a U-Net-based levelset model to delineate the left ventricular (LV) apex. Morphological and LV wall features were extracted from the segmented region, and a graph isomorphism network (GIN) was trained to capture both local hypertrophic patterns and global ventricular morphology for subtype classification. The framework was designed to distinguish among pure ApHCM, relative ApHCM, and mixed ApHCM. RESULTS: The framework achieved a classification accuracy of 96.2%, with a precision, recall, and F1-score of approximately 95%. Cross-validation results indicate stable performance (95.8% ± 0.4%, p < 0.001), and ablation experiments confirmed the contribution of each pipeline component. DISCUSSION: By combining denoising, segmentation, and graph-based learning, the framework addressed limitations caused by LVO artifacts and improved the recognition of subtle ApHCM subtypes. These results demonstrate the clinical potential of integrating morphological feature extraction with deep learning in echocardiography. CONCLUSION: The framework integrating MG-APSO-DnCNN and GIN enables accurate and robust ApHCM subtype classification, supporting cardiologists in early diagnosis, patient risk stratification, and treatment planning.
No takes yet. Share an insight, caveat, or question.
Venkatesan et al. (2026) studied Apical hypertrophic cardiomyopathy (n=3,200). Deep learning framework (MG-APSO-DnCNN and GIN) was evaluated on Classification accuracy among pure, relative, and mixed ApHCM, and normal classes (p=<0.001). A deep learning framework integrating MG-APSO-DnCNN and GIN classified apical hypertrophic cardiomyopathy subtypes with 96.2% accuracy.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: