8 February 2017 Deep learning and non-negative matrix factorization in recognition of mammograms
Author Affiliations +
Proceedings Volume 10225, Eighth International Conference on Graphic and Image Processing (ICGIP 2016); 102250B (2017) https://doi.org/10.1117/12.2266335
Event: Eighth International Conference on Graphic and Image Processing, 2016, Tokyo, Japan
Abstract
This paper presents novel approach to the recognition of mammograms. The analyzed mammograms represent the normal and breast cancer (benign and malignant) cases. The solution applies the deep learning technique in image recognition. To obtain increased accuracy of classification the nonnegative matrix factorization and statistical self-similarity of images are applied. The images reconstructed by using these two approaches enrich the data base and thanks to this improve of quality measures of mammogram recognition (increase of accuracy, sensitivity and specificity). The results of numerical experiments performed on large DDSM data base containing more than 10000 mammograms have confirmed good accuracy of class recognition, exceeding the best results reported in the actual publications for this data base.
© (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Bartosz Swiderski, Bartosz Swiderski, Jaroslaw Kurek, Jaroslaw Kurek, Stanislaw Osowski, Stanislaw Osowski, Michal Kruk, Michal Kruk, Walid Barhoumi, Walid Barhoumi, } "Deep learning and non-negative matrix factorization in recognition of mammograms", Proc. SPIE 10225, Eighth International Conference on Graphic and Image Processing (ICGIP 2016), 102250B (8 February 2017); doi: 10.1117/12.2266335; https://doi.org/10.1117/12.2266335
PROCEEDINGS
7 PAGES


SHARE
Back to Top