A deep learning approach for the analysis of masses in mammograms with minimal user intervention

Abstract

We present an integrated methodology for detecting, segmenting and classifying breast masses from mammograms with minimal user intervention. This is a long standing problem due to low signal-to-noise ratio in the visualisation of breast masses, combined with their large variability in terms of shape, size, appearance and location. We break the problem down… (More)
DOI: 10.1016/j.media.2017.01.009

16 Figures and Tables

Topics

  • Presentations referencing similar topics