Aug 2026· Current medical imaging· Vol 22· 0 citations
Medicine
TL;DR
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.
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, relative ApHCM, mixed 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.
The proposed anatomically guided BackMix augmentation combined with semi-supervised ensemble learning can improve classification accuracy, robustness, and interpretability in echocardiographic analysis under limited annotation conditions, offering a promising approach for automated AS assessment across independent clinical datasets.
Fatima Ezzahra Elkouahy, Badreddine Labakoum, H. Ouahid et al.· Journal of Electronics Elect...· 0 citations
Combining GLCM texture analysis with ML provides a potential way of improving the precision and reliability of MV disease diagnosis, ultimately supporting efforts to enhance public health and early disease diagnosis, in alignment with global healthcare initiatives.
Hani Attar, Jafar Ababneh, Omar A. Sarhan et al.· International Journal of Com...· 0 citations
A fully automated ML model identifies area-derived LACI at end-diastole at end-diastole as a robust feature associated with disease progression, providing improved risk stratification for pre-symptomatic HCM.
Antoine Olivier, Auriane Riou, T. D'humières et al.· Frontiers in Cardiovascular...· 0 citations
This study implemented strict subject-disjoint partitioning to eliminate data leakage, and simultaneously introduced cross-frame case aggregation to emulate the multi-frame visual synthesis process of expert echocardiographers, suggesting that the proposed workflow has the potential to serve as an adjunctive tool for septal defect screening.
Tao Zhang, Peipei Zhang, Qing-Yuan Zhang et al.· IEEE Access· 0 citations
Background: Right ventricular (RV) function predicts survival in pulmonary hypertension (PH) and other cardiovascular diseases, yet echocardiographic AI has largely focused on the left ventricle (LV). Objectives: To develop and evaluate PH-ECHO-AI, a unified deep learning model performing four-chamber segmentation, landmark localisation, biventricular ejection fraction (EF) estimation, deformation analysis, and PH prediction from a single apical four-chamber (A4C) clip. Methods: We developed the model using 8,416 clips from four public datasets and no institutional data: EchoNet-Dynamic, CAMUS, RVENet (apical four-chamber clips paired with 3D-echocardiographic right ventricular ejection fraction, RVEF), and MIMIC-IV-ECHO. Evaluation used held-out, training-excluded data with expert-reviewed reference standards and a per-cohort audit of patient-level separation: 1,416 clips for segmentation; 600 clips for function and deformation (350 referenced to 3D-echocardiographic RVEF, 250 to the EchoNet LVEF); and 1,076 MIMIC-IV patients for PH prediction, with five-fold cross-validation. Performance measures were Dice, correlation, mean absolute error (MAE), Bland-Altman agreement, and area under the receiver operating characteristic curve (AUC). Results: Four-chamber segmentation generalised robustly across all datasets (pooled Dice: LV 0.925, RV 0.836, LA 0.910, RA 0.904). Left ventricular ejection fraction (LVEF) was estimated with r=0.845 (95% CI 0.786 to 0.886) and MAE 4.67%. RVEF, regressed directly from the clip by a supervised head trained on 3D-echocardiographic labels with no geometric assumption, reached r=0.754 (95% CI 0.690 to 0.806) and MAE 4.98%, matching published single-view RVEF ceilings and exceeding geometric RV fractional area change (RVFAC; r=0.278). Deformation and excursion metrics, namely RV free-wall and LV A4C longitudinal strain and tricuspid and mitral annular plane systolic excursion (TAPSE, MAPSE), proved physiologically coherent. Segmentation generalised to the external MIMIC-IV cohort, and PH prediction was developed and evaluated entirely within it; RVEF evaluation was clip-disjoint and same-source, so cross-centre RVEF validation remains outstanding. Using echocardiographic geometry alone, confirmed PH was detected with an AUC of 0.697 and strong calibration (Brier 0.061). Conclusions: A single, reproducible model provides comprehensive right-heart-focused interpretation from one A4C view. It achieves RVEF accuracy competitive with dedicated RV models while simultaneously delivering segmentation, deformation, annular excursion (TAPSE and MAPSE), and PH prediction. Registration: This retrospective study used existing datasets. Code is openly released, and trained model weights are available to credentialed investigators, for independent evaluation.
T. Pitre, L. Marques, J. Weatherald et al.· medRxiv· 0 citations
Accurate standard-view classification is essential for pediatric echocardiographic image analysis and downstream automated interpretation. This task remains challenging because discriminative view information is often encoded in subtle chamber configurations, outflow-tract morphology, and weak anatomical boundaries, whereas conventional classifiers may underuse shallow and intermediate representations that preserve spatial structure. We propose PVTv2-ASEF, a structure-aware framework for 4-class pediatric echocardiographic standard-view classification. The framework introduces an Adaptive Structural Enhancement Module that performs residual input-side conditioning through channel recalibration, local convolutional mixing, multi-scale structural modeling, and input-dependent branch weighting. It further employs a Dual Auxiliary Fusion Head to transform Stage 2 and Stage 3 representations into class-level evidence and fuse them with the final-stage logits during inference. PVTv2-ASEF was evaluated on a private pediatric ventricular septal defect echocardiography dataset comprising 4 standard views under repeated patient-disjoint evaluation, with macro-F1 used as the primary class-balanced metric. Compared with PVTv2-B2, the proposed framework improved macro-F1 by 0.093 on the private dataset and by 0.023 in cross-task evaluation on FETAL_PLANES_DB. These results support the utility of coordinated input-side structural enhancement and intermediate logit fusion for ultrasound view and plane classification.
