Enhancing Breast Cancer Detection Using Dual-View Cross Attention with Swin Transformer

Breast cancer remains a significant global health issue, particularly impacting women. Early detection and accurate diagnosis are essential for improving patient outcomes. In this study, we explore a deep learning-based approach utilizing Swin Transformer with Dual-View Cross Attention to enhance breast cancer detection. Leveraging mammography images from the RSNA dataset, our method achieved an accuracy of 0.81 and an AUC of 0.87. These results underscore the potential of advanced deep learning techniques in improving breast cancer detection through medical imaging.