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

2019/07/27 by Mickael Tardy, Tardy, Mickael, Bruno Scheffer +3
Medicine · Computer Science · #Digital Radiography and Breast Imaging #AI in cancer detection #Optical Imaging and Spectroscopy Techniques

paper · pdf · doi:10.48550/arxiv.1907.11860

Abstract

This work focuses on the automatic quantification of the breast density from digital mammography 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.

Related

• A multi-reconstruction study of breast density estimation using Deep Learning
• Photometric Transformer Networks and Label Adjustment for Breast Density Prediction
• Attention-Enhanced Deep Learning Ensemble for Breast Density Classification in Mammography
• MammoFL: Mammographic Breast Density Estimation using Federated Learning
• Breast density classification with deep convolutional neural networks