Skip to content
DraconiticResearch
Search Sources API
194,220 studies31 sourcesUpdated 7 min ago
Peer-reviewedCC BY 4.0Current Medical Imaging

Deep Learning-based Classification of Apical Hypertrophic Cardiomyopathy using Left Ventricular Opacification and Enhanced LV Apex Imaging

  • P. Venkatesan1
  • A. Rajeswari2
  • N.R. Shanker3
  1. 1Department of Computer Science and Engineering, Vel Tech Multi Tech Dr. Rangarajan Dr. Sakunthala Engineering College, Chennai, India
  2. 2Department of Computer Science and Engineering, Velammal Engineering College, Chennai, India
  3. 3Department of Computer Science and Engineering, Sriram Engineering College, Chennai, India
Read full textDOICite

Abstract

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 (P-ApHCM), 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.

Related

  1. Transatrial air-assisted epicardial ventricular tachycardia ablation for hypertrophic cardiomyopathy and management of postprocedural right atrial thrombus.
    İbrahim Etem Dural, Mehmet Özgeyik, Ramazan Anıl Eşki +1
    HeartRhythm case reportsPeer-reviewedCC BY-NC-NDFull textCardiovascular medicineEurope PMC
  2. Atrial and ventricular mechanical dysfunction and myocardial injury predict long-term outcomes in hypertrophic cardiomyopathy: a retrospective cohort study
    Sheng-Liang Liu, Xue-Dong Wang, Ye Li +7
    Quantitative imaging in medicine and surgeryPeer-reviewedCC BY-NC-NDFull textMedical imaging & radiologyEurope PMC
  3. Left Ventricular Wall Thickness in Hypertrophic Cardiomyopathy and Cardiac Amyloidosis: A Multimodality Imaging Comparison
    Zubair Bashir, Syed Bukhari, Michelle Yang +4
    Journal of Clinical MedicinePeer-reviewedCC BY 4.0Full textCardiovascular medicineCrossrefEurope PMC
  4. Unmasking Latent Left Ventricular Outflow Tract Obstruction in Hypertrophic Cardiomyopathy
    Hyunseok Cho, Jihoon Kim, Sang-Chol Lee +2
    JACC Case ReportsPeer-reviewedCC BY-NC-ND 4.0Full textCardiovascular medicinePMCDOAJ
  5. Left Ventricular Structural, Physiological, and Transcriptomic Abnormalities in a Novel Porcine Hypertrophic Cardiomyopathy Model.
    Eric M Green, Carlos Del Rio, Kamel Shibbani +18
    JACC. Basic to translational sciencePeer-reviewedCC BY-NC-NDFull text1 citedCardiovascular medicineEurope PMC

Cite

BibTeXRIS
BibTeX
@article{venkatesan2026deep,
  title = {{Deep Learning-based Classification of Apical Hypertrophic Cardiomyopathy using Left Ventricular Opacification and Enhanced LV Apex Imaging}},
  author = {P. Venkatesan and A. Rajeswari and N.R. Shanker},
  journal = {Current Medical Imaging},
  year = {2026},
  month = aug,
  doi = {10.2174/0115734056450679260721035709},
  url = {https://doi.org/10.2174/0115734056450679260721035709},
  note = {CC BY 4.0},
}
RIS
TY  - JOUR
TI  - Deep Learning-based Classification of Apical Hypertrophic Cardiomyopathy using Left Ventricular Opacification and Enhanced LV Apex Imaging
AU  - P. Venkatesan
AU  - A. Rajeswari
AU  - N.R. Shanker
PY  - 2026
DA  - 2026/08/05
JO  - Current Medical Imaging
DO  - 10.2174/0115734056450679260721035709
UR  - https://doi.org/10.2174/0115734056450679260721035709
AB  - 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 (P-ApHCM), 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.
SN  - 1573-4056
ER  -