The modified YOLOv8x model achieved a precision of 0.991, recall of 0.960, F1-score of 0.980, and mAP of 0.976 for detecting coronary artery stenosis.
Does a modified YOLOv8x model improve the detection of coronary artery stenosis and risk stratification compared to baseline YOLO models?
A modified YOLOv8x deep learning framework provides highly accurate detection of coronary artery stenosis and integrates troponin levels for cardiovascular risk stratification.
Abstract Detection of coronary artery stenosis and risk stratification of troponin plays a pivotal role in offering early diagnosis and treatment of cardiovascular diseases. In this paper, an improved deep learning framework that allows using both spatial and frequency-based attention mechanisms will be proposed using a modified YOLOv8x framework. Upon benchmarking YOLOv8, YOLOv9 and YOLOv10 models, YOLOv8x was chosen due to its excellent baseline and the enhancement was done to make it more clinical relevant. The proposed model was found to have a precision of 0.991, a recall value of 0.960, F1-score of 0.980, and a mAP of 0.976. These findings show significant possibilities of real world applications. The effectiveness of the improvements is in addition validated by large-scale ablation studies, and the results overcome the problem of detecting fine lesions and disparate clinical information. The work has added value in the form of a reliable end-to-end diagnostic cardiovascular imaging and biomarker-based risk analysis.
Albasrawi et al. (2026) studied Coronary artery stenosis (n=2,250). Modified YOLOv8x model vs. Baseline YOLOv8, YOLOv9, and YOLOv10 models was evaluated on Detection of coronary artery stenosis (Precision, Recall, F1-score, mAP). The modified YOLOv8x model achieved a precision of 0.991, recall of 0.960, F1-score of 0.980, and mAP of 0.976 for detecting coronary artery stenosis.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: