Annotation-Free Breast Cancer Prediction (CBM)

Most AI models for breast cancer detection assume that each mammogram image, or even each region within an image, has been manually labeled. However, in real hospitals, clinicians only provide a final, case-level diagnosis, and the number of images per exam varies.

We introduce a two-level multi-instance learning (MIL) framework that learns directly from case-level labels without requiring manual image annotation. This method can handle a variable number of images per patient and includes a breast-specific MIL pooling strategy that reflects how mammography is performed.

Our approach achieved performance comparable to models trained using detailed image labels. It also identified which breast, view, and region were most suspicious despite using only weak supervision. These results demonstrate that accurate and scalable breast cancer prediction is possible using the labels already available in routine clinical practice.

Reference

(Pathak et al., 2025)

1. Shreyasi Pathak, Jörg Schlötterer, Jeroen Geerdink, Jeroen Veltman, Maurice van Keulen, Nicola Strisciuglio, and Christin Seifert. Breast cancer prediction using mammography exams for real hospital settings. Computers in Biology and Medicine. 2025.
   BibTeX

   @article{Pathatk2025_cbmj_breast-cancer-mammography,
     author = {Pathak, Shreyasi and Schlötterer, Jörg and Geerdink, Jeroen and Veltman, Jeroen and {van Keulen}, Maurice and Strisciuglio, Nicola and Seifert, Christin},
     journal = {Computers in Biology and Medicine},
     title = {Breast cancer prediction using mammography exams for real hospital settings},
     year = {2025},
     issn = {0010-4825},
     pages = {111136},
     volume = {198},
     code = {https://github.com/ShreyasiPathak/multiinstance-learning-mammography},
     doi = {https://doi.org/10.1016/j.compbiomed.2025.111136},
     file = {:own-pdf/Pathatk2025_cbmj_breast-cancer-mammography-realistic-settings_preprint.pdf:PDF},
     keywords = {Deep learning, Mammography images, Weakly supervised learning, Breast cancer prediction in real hospital settings},
     url = {https://www.sciencedirect.com/science/article/pii/S0010482525014891}
   }