Enhancing Microcalcification Detection in Mammography with YOLO-v8 Performance and Clinical Implications

Background: Microcalcifications in the breast are often an early warning sign of breast cancer, and their accurate detection is crucial for the early discovery and management of the disease. In recent years, deep learning technology, particularly models based on object detection, has significantly improved the ability to detect microcalcifications. This study aims to use the advanced YOLO-v8 object detection algorithm to identify breast microcalcifications and explore its advantages in terms of performance and clinical application. Methods: This study collected mammograms from 7615 female participants, with a dataset including 10,323 breast images containing microcalcifications. We used the YOLO-v8 model for microcalcification detection and trained and validated the model using five-fold cross-validation. The model's performance was evaluated through metrics such as accuracy, recall, F1 score, mAP50, and mAP50-95. Additionally, this study explored the potential applications of this technology in clinical practice. Results: The YOLO-v8 model achieved an mAP50 of 0.921, an mAP50-95 of 0.709, an F1 score of 0.82, a detection accuracy of 0.842, and a recall rate of 0.796 in breast microcalcification detection. Compared to previous similar deep learning object detection techniques like Mask R-CNN, YOLO-v8 has shown improvements in both speed and accuracy. Conclusions: YOLO-v8 outperforms traditional detection methods in detecting breast microcalcifications. Its multi-scale detection capability significantly enhances both speed and accuracy, making it more clinically practical for large-scale screenings. Future research should further explore the model's potential in benign and malignant classification to promote its application in clinical settings, assisting radiologists in diagnosing breast cancer more efficiently.