%0 Journal Article
%T Deep learning networks find unique mammographic differences in previous negative mammograms between interval and screen-detected cancers: a case-case study
%A Amir Pasha Mahmoudzadeh
%A Benjamin Hinton
%A Bo Fan
%A Bonnie Joe
%A Heather Greenwood
%A John Shepherd
%A Karla Kerlikowske
%A Lin Ma
%A Serghei Malkov
%A Vivian Lee
%J Archive of "Cancer Imaging".
%D 2019
%R 10.1186/s40644-019-0227-3
%X Schematic of the architecture of the deep learning network used in this study. YxY conv, M/N£¿=£¿M kernels of YxYx3 size and stride length of N (N£¿=£¿1 if only M is listed). Fully Connected (FC) Layer£¿=£¿Dense (256), Dropout, Dense (1
%K Breast Cancer
%K Masking
%K Mammography
%K Interval Cancer
%K Deep learning
%K Transfer learning
%K Neural network
%K Breast density
%U https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6589178/