Mass segmentation provides effective morphological features which are important for mass diagnosis. In this work, we propose a novel end-to-end network for mammographic mass segmentation which employs a fully convolutional network (FCN) to model a potential function, followed by a CRF to perform structured learning. Because the mass distribution varies greatly with pixel position, the FCN is combined with a position priori. Further, we employ adversarial training to eliminate over-fitting due to the small sizes of mammogram datasets. Multi-scale FCN is employed to improve the segmentation performance. Experimental results on two public datasets, INbreast and DDSM-BCRP, demonstrate that our end-to-end network achieves better performance than state-of-the-art approaches. \footnote{https://github.com/wentaozhu/adversarial-deep-structural-networks.git}
@article{arxiv.1710.09288,
title = {Adversarial Deep Structured Nets for Mass Segmentation from Mammograms},
author = {Wentao Zhu and Xiang Xiang and Trac D. Tran and Gregory D. Hager and Xiaohui Xie},
journal= {arXiv preprint arXiv:1710.09288},
year = {2017}
}
Comments
Accepted by ISBI2018. arXiv admin note: substantial text overlap with arXiv:1612.05970