Optimized Lightweight Architecture for Coronary Artery Disease Classification in Medical Imaging

Diagnostics, Journal Year: 2025, Volume and Issue: 15(4), P. 446 - 446

Published: Feb. 12, 2025

Background/Objectives: The early and accurate detection of Coronary Artery Disease (CAD) is crucial for preventing life-threatening complications, particularly among athletes engaged in high-intensity endurance sports. This demographic faces unique cardiovascular risks, as prolonged intense physical exertion can exacerbate underlying CAD conditions. Studies indicate that while typically exhibit enhanced health, this not immune to risks. Research has shown approximately 1-2% competitive suffer from CAD-related with sudden cardiac arrest being the leading cause mortality over 35 years old. High-intensity sports conditions due stress placed on system, making crucial. study aimed develop evaluate a lightweight deep learning model tailored challenges diagnosing athletes. Methods: introduces specifically designed By integrating ResNet-inspired residual connections into VGG16 architecture, achieves balance high diagnostic accuracy computational efficiency. incorporating enhances gradient flow, mitigates vanishing issues, improves feature extraction subtle morphological variations coronary lesions. Its design, only 1.2 million parameters 3.5 GFLOPs, ensures suitability real-time deployment resource-constrained clinical environments, such clinics mobile systems, where rapid efficient diagnostics are essential high-risk populations. Results: proposed achieved superior performance compared state-of-the-art architectures, an 90.3%, recall 89%, precision 90%, AUC-ROC 0.912. These metrics highlight its robustness detecting classifying efficiency applications, settings. Conclusions: demonstrates potential lightweight, learning-based tool athletes, achieving Future work should focus broader dataset validations enhancing explainability improve adoption real-world scenarios.

Language: Английский

A proximal policy optimisation algorithm-based algorithm for cardiovascular disorders detection

Journal of Medical Engineering & Technology, Journal Year: 2025, Volume and Issue: unknown, P. 1 - 20

Published: March 11, 2025

Cardiovascular diseases (CVDs) significantly impact athletes, impacting the heart and blood vessels. This article introduces a novel method to assess CVD in athletes through an artificial neural network (ANN). The model utilises mutual learning-based bee colony (ML-ABC) algorithm set initial weights proximal policy optimisation (PPO) address imbalanced classification. ML-ABC uses learning enhance process by updating positions of food sources with respect best fitness outcomes two randomly selected individuals. PPO makes updates ANN stable efficient improve model's reliability. Our approach formulates classification problem as series decision-making processes, rewarding every act higher rewards for correctly identifying instances minority class, hence handling class imbalance. We evaluated performance on diversified medical dataset including 26,002 who were examined within Polyclinic Occupational Health Sports Zagreb, further validated NCAA NHANES datasets verify generalisability. findings indicate that our outperforms existing models accuracies 0.88, 0.86 0.82 respective datasets. These results clinical application advance cardiovascular disorder detection methodologies.

Language: Английский