S137 - Improving Mammography Malignancy Segmentation by Designing the Training Process
Mickael Tardy, Diana Mateus
We work on the breast imaging malignancy segmentation task while focusing on the train- ing process instead of network complexity. We designed a training process based on a modified U-Net, increasing the overall segmentation performances by using both, benign and malignant data for training. Our approach makes use of only a small amount of anno- tated data and relies on transfer learning from a self-supervised reconstruction task, and favors explainability.
Poster Session #5 - 9:30 - 11:00 UTC-4 (Wednesday)