A closer look onto breast density with weakly supervised dense-tissue masks

Mickael Tardy, Bruno Scheffer, Diana Mateus

Keywords: Deep Learning, Weakly supervised segmentation, Regression, Breast density

TL;DR: U-Net based network using image-wise ground truth for segmentation of breast dense tissues.

Abstract: This work focuses on the automatic quantification of the breast density from digital mam- mography imaging. Using only categorical image-wise labels we train a model capable of predicting continuous density percentage as well as providing a pixel wise support frit for the dense region. In particular we propose a weakly supervised loss linking the density percentage to the mask size.

Code Of Conduct: I have read and accept the code of conduct.