Machine Learning-Based Automating Breast Cancer Detection and Classification using DWI

Motivation: Breast MRI's subotimal specificity and labor-intensive DWI interpretation call for automated diagnostic solutions. Goal(s): Investigate effectiveness of AI integration for breast tumor detection and characterization in DWI. Approach: Retrospective analysis of 601 patients. Fine-tuned YOLO v5 for tumor identification and 2D CNN for malignancy assessment, utilizing whole-slice and bounding box techniques. Results: Strong diagnostic performance observed. Whole-slice method: AUC 0.90, sensitivity 84.4%, specificity 84.0%. Bounding box method: AUC 0.87, sensitivity 87.5%, specificity 80.0%. Impact: Potential to boost screening efficiency, minimize false positives, and improve patient care via more precise, swift diagnoses.