Enhancing Cardiovascular Diagnostics with YOLOv8: A Deep Learning Approach to Focal Anomaly Detection in Angiogram Imaging

Fast and precise diagnosis techniques are required since cardiovascular illnesses are one of the main causes of death globally. For the purpose of improve the rate of detection and diagnosis even further, this paper applies an advanced deep learning technique by employing the YOLOv8 algorithm, with a particular focus on the “focal” class of the “Cardiovascular-Angiogram-dataset.” Using the most recent object detection model, YOLOv8, the Angiogram images were examined and achieved precision is 0.99, recall is 0.99, and F1 score is 0.98. With a score of 0.99, the Precision-Recall Curve likewise showed excellent performance. These findings demonstrate how well the system detects focused cardiovascular problems, greatly improving diagnostic precisison. The results of this study imply that deep learning models, such as YOLOv8, can play a critical role in clinical settings by providing accurate, real-time diagnosis. Subsequent research endeavours will investigate the assimilation of this model into more comprehensive diagnostic frameworks and its possible utilisation in a range of cardiovascular ailments to enhance patient outcomes.