Weakly-Supervised Self-Training for Breast Cancer Localization. Conference Paper uri icon

abstract

  • The use of deep learning methods has dramatically increased the state-of-the-art performance in image object localization. However, commonly used supervised learning methods require large training datasets with pixel-level or bounding box annotations. Obtaining such fine-grained annotations is extremely costly, especially in the medical imaging domain. In this work, we propose a novel weakly supervised method for breast cancer localization. The essential advantage of our approach is that the model only requires image-level labels and uses a self-training strategy to refine the predicted localization in a step-wise manner. We evaluated our approach on a large, clinically relevant mammogram dataset. The results show that our model significantly improves performance compared to other methods trained similarly.

name of conference

  • 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)

published proceedings

  • Annu Int Conf IEEE Eng Med Biol Soc

author list (cited authors)

  • Liang, G., Wang, X., Zhang, Y. u., & Jacobs, N.

citation count

  • 15

complete list of authors

  • Liang, Gongbo||Wang, Xiaoqin||Zhang, Yu||Jacobs, Nathan

publication date

  • July 2020