Optimized Lightweight Architecture for Coronary Artery Disease Classification in Medical Imaging

Diagnostics, Год журнала: 2025, Номер 15(4), С. 446 - 446

Опубликована: Фев. 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.

Язык: Английский

---

JC-GN: multi-scene joint conditional network for remote sensing sequence imagery generation under spatio-temporal variation

Journal of King Saud University - Computer and Information Sciences, Год журнала: 2025, Номер 37(3)

Опубликована: Апрель 10, 2025

Язык: Английский

---

Telomere length as a biomarker for cerebrovascular diseases: current evidence

Molecular Biology Reports, Год журнала: 2024, Номер 51(1)

Опубликована: Ноя. 13, 2024

Язык: Английский

---