Registration is open - make plans to attend
Get pricing and details
Conference 12033 > Paper 12033-88
Paper 12033-88

Intrinsic subtype classification of breast lesions on mammograms by contrastive learning

In person: 23 February 2022 • 5:30 PM - 7:00 PM PST


When breast cancer is found, the best treatment is selected based on the cancer characteristics. We investigated a method to classify lesions into four molecular subtypes to assist diagnosis and treatment planning. Because of a limited number of samples and imbalanced types, the lesions were classified based on the similarities of samples using contrastive learning. The network takes two images and provides the same-class and different-class probabilities. The proposed model was tested using 189 cases by a 4-fold cross validation. The result indicates the potential usefulness of the proposed method. The computerized subtype classification may support a prompt treatment planning.


Shiga Univ. (Japan)
Shiga Univ. (Japan)
Mikinao Oiwa
Nagoya Medical Ctr. (Japan)
International Medical Ctr.., Saitama Medical Univ. (Japan)
Gifu Univ. (Japan)