Identification of Key Features in Breast Cancer Diagnosis Using Vision Transformer

Accurate image-based prediction is critical for diagnosing breast cancer. Current diagnostic practices depend on interpreting a variety of data types, such as pathology reports, MRI, and ultrasound images, making the accurate interpretation of these images by physicians essential. This study aims to enhance diagnostic accuracy by developing a high-performance tool using a novel deep learning model, the Vision Transformer (ViT_B_16). Five distinct breast cancer image datasets were selected for model training, optimizing the ViT_B_16 Transformer model's parameters. The results demonstrated that the Transformer model achieved an impressive accuracy of 0.99 and a minimal loss score of 0.01. Additionally, for mixed-type datasets, the Transformer model exhibited significant potential in breast cancer diagnosis, outperforming the FasterRCNN model.