Breast Cancer Detection And Localization Using Region-Based Convolutional Neural Networks (RCNN): A Deep Learning Approach
Sandhya C · International Journal of Intelligent Systems and Applications in Engineering · 2024
Breast cancer remains a major global health challenge, where timely and accurate detection is crucial for effective treatment. Conventional interpretation of ultrasound or MRI scans often suffers from diagnostic variability and human error. This study presents a Region-based Convolutional Neural Network (RCNN) model for the automated detection and localization of breast tumors using ultrasound and MRI imaging data. The model is trained and validated on benchmark medical datasets and evaluated through key metrics including accuracy, precision, recall, and Intersection over Union (IoU). Results indicate that the proposed RCNN framework significantly improves tumor detection accuracy and spatial localization effectiveness. DOI: https://doi.org/10.17762/ijisae.v12i8s.7645