TY - JOUR
T1 - STRAINet
T2 - Spatially Varying sTochastic Residual AdversarIal Networks for MRI Pelvic Organ Segmentation
AU - Nie, Dong
AU - Wang, Li
AU - Gao, Yaozong
AU - Lian, Jun
AU - Shen, Dinggang
N1 - Funding Information:
Manuscript received August 10, 2017; revised February 18, 2018 and May 19, 2018; accepted August 31, 2018. Date of publication October 9, 2018; date of current version April 16, 2019. This work was supported by the National Institutes of Health under Grant R01 CA206100. (Corresponding author: Dinggang Shen.) D. Nie is with the Department of Computer Science, The University of North Carolina at Chapel Hill, Chapel Hill, NC 27599 USA, and also with the Department of Radiology, BRIC, The University of North Carolina at Chapel Hill, Chapel Hill, NC 27599 USA.
Publisher Copyright:
© 2012 IEEE.
PY - 2019/5
Y1 - 2019/5
N2 - Accurate segmentation of pelvic organs is important for prostate radiation therapy. Modern radiation therapy starts to use a magnetic resonance image (MRI) as an alternative to computed tomography image because of its superior soft tissue contrast and also free of risk from radiation exposure. However, segmentation of pelvic organs from MRI is a challenging problem due to inconsistent organ appearance across patients and also large intrapatient anatomical variations across treatment days. To address such challenges, we propose a novel deep network architecture, called 'Spatially varying sTochastic Residual AdversarIal Network' (STRAINet), to delineate pelvic organs from MRI in an end-to-end fashion. Compared to the traditional fully convolutional networks (FCN), the proposed architecture has two main contributions: 1) inspired by the recent success of residual learning, we propose an evolutionary version of the residual unit, i.e., stochastic residual unit, and use it to the plain convolutional layers in the FCN. We further propose long-range stochastic residual connections to pass features from shallow layers to deep layers; and 2) we propose to integrate three previously proposed network strategies to form a new network for better medical image segmentation: a) we apply dilated convolution in the smallest resolution feature maps, so that we can gain a larger receptive field without overly losing spatial information; b) we propose a spatially varying convolutional layer that adapts convolutional filters to different regions of interest; and c) an adversarial network is proposed to further correct the segmented organ structures. Finally, STRAINet is used to iteratively refine the segmentation probability maps in an autocontext manner. Experimental results show that our STRAINet achieved the state-of-the-art segmentation accuracy. Further analysis also indicates that our proposed network components contribute most to the performance.
AB - Accurate segmentation of pelvic organs is important for prostate radiation therapy. Modern radiation therapy starts to use a magnetic resonance image (MRI) as an alternative to computed tomography image because of its superior soft tissue contrast and also free of risk from radiation exposure. However, segmentation of pelvic organs from MRI is a challenging problem due to inconsistent organ appearance across patients and also large intrapatient anatomical variations across treatment days. To address such challenges, we propose a novel deep network architecture, called 'Spatially varying sTochastic Residual AdversarIal Network' (STRAINet), to delineate pelvic organs from MRI in an end-to-end fashion. Compared to the traditional fully convolutional networks (FCN), the proposed architecture has two main contributions: 1) inspired by the recent success of residual learning, we propose an evolutionary version of the residual unit, i.e., stochastic residual unit, and use it to the plain convolutional layers in the FCN. We further propose long-range stochastic residual connections to pass features from shallow layers to deep layers; and 2) we propose to integrate three previously proposed network strategies to form a new network for better medical image segmentation: a) we apply dilated convolution in the smallest resolution feature maps, so that we can gain a larger receptive field without overly losing spatial information; b) we propose a spatially varying convolutional layer that adapts convolutional filters to different regions of interest; and c) an adversarial network is proposed to further correct the segmented organ structures. Finally, STRAINet is used to iteratively refine the segmentation probability maps in an autocontext manner. Experimental results show that our STRAINet achieved the state-of-the-art segmentation accuracy. Further analysis also indicates that our proposed network components contribute most to the performance.
KW - Adversarial learning
KW - dilation
KW - pelvic organ segmentation
KW - stochastic residual learning
UR - http://www.scopus.com/inward/record.url?scp=85054636735&partnerID=8YFLogxK
U2 - 10.1109/TNNLS.2018.2870182
DO - 10.1109/TNNLS.2018.2870182
M3 - Article
C2 - 30307879
AN - SCOPUS:85054636735
SN - 2162-237X
VL - 30
SP - 1552
EP - 1564
JO - IEEE Transactions on Neural Networks and Learning Systems
JF - IEEE Transactions on Neural Networks and Learning Systems
IS - 5
M1 - 08486982
ER -