TY - GEN
T1 - Adversarial deep structured nets for mass segmentation from mammograms
AU - Zhu, Wentao
AU - Xiang, Xiang
AU - Tran, Trac D.
AU - Hager, Gregory D.
AU - Xie, Xiaohui
N1 - Publisher Copyright:
© 2018 IEEE.
PY - 2018/5/23
Y1 - 2018/5/23
N2 - 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 conditional random field (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, IN breast and DDSM-BCRP, demonstrate that our end-to-end network achieves better performance than state-of-the-art approaches.1
AB - 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 conditional random field (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, IN breast and DDSM-BCRP, demonstrate that our end-to-end network achieves better performance than state-of-the-art approaches.1
KW - Adversarial deep structured networks
KW - Adversarial fully convolutional networks
KW - Segmentation
UR - http://www.scopus.com/inward/record.url?scp=85048081629&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85048081629&partnerID=8YFLogxK
U2 - 10.1109/ISBI.2018.8363704
DO - 10.1109/ISBI.2018.8363704
M3 - Conference contribution
AN - SCOPUS:85048081629
T3 - Proceedings - International Symposium on Biomedical Imaging
SP - 847
EP - 850
BT - 2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018
PB - IEEE Computer Society
T2 - 15th IEEE International Symposium on Biomedical Imaging, ISBI 2018
Y2 - 4 April 2018 through 7 April 2018
ER -