pp. 1951-1957
S&M3646 Research Paper of Special Issue https://doi.org/10.18494/SAM4826 Published: May 24, 2024 Mammographic Breast Composition Classification Using Swin Transformer Network [PDF] Kuen-Jang Tsai, Wei-Cheng Yeh, Cheng-Yi Kao, Ming-Wei Lin, Chao-Ming Hung, Hung-Ying Chi, Cheng-Yu Yeh, and Shaw-Hwa Hwang (Received December 15, 2023; Accepted May 10, 2024) Keywords: screening mammography, breast imaging reporting and data system (BI-RADS), breast composition, image classification, Swin Transformer, deep learning
Breast cancer is a prevalent global health concern and the most commonly diagnosed cancer in women. Mammography, a well-established and widely used screening tool, has greatly contributed to early breast cancer detection. However, understanding mammographic breast composition is also crucial for refining the risk assessment of breast cancer beyond identifying lesions. In contrast to previous studies, we adopt an exploratory approach by using the Swin Transformer, a foundation model for image classification, to classify the four-category breast density. Leveraging this foundation, we fine-tune the model with a small set of mammograms for the purpose of making advancements in breast density classification. This study is experimentally validated to achieve an overall accuracy of 74.96% in the four-category breast density classification, which is a comparable performance to recent counterparts.
Corresponding author: Cheng-Yu YehThis work is licensed under a Creative Commons Attribution 4.0 International License. Cite this article Kuen-Jang Tsai, Wei-Cheng Yeh, Cheng-Yi Kao, Ming-Wei Lin, Chao-Ming Hung, Hung-Ying Chi, Cheng-Yu Yeh, and Shaw-Hwa Hwang, Mammographic Breast Composition Classification Using Swin Transformer Network, Sens. Mater., Vol. 36, No. 5, 2024, p. 1951-1957. |