TY - JOUR
T1 - CT Male Pelvic Organ Segmentation via Hybrid Loss Network with Incomplete Annotation
AU - Wang, Shuai
AU - Nie, Dong
AU - Qu, Liangqiong
AU - Shao, Yeqin
AU - Lian, Jun
AU - Wang, Qian
AU - Shen, DInggang
N1 - Funding Information:
Manuscript received November 13, 2019; revised December 31, 2019; accepted January 8, 2020. Date of publication January 13, 2020; date of current version June 1, 2020. This work was supported in part by the NIH under Grant 5R01CA206100. (Corresponding authors: Qian Wang; Dinggang Shen.) Shuai Wang, Dong Nie, and Liangqiong Qu are with the Department of Radiology and the Biomedical Research Imaging Center, The University of North Carolina at Chapel Hill, Chapel Hill, NC 27599 USA (e-mail: shuaiwang.tai@gmail.com; dongnie@cs.unc.edu; liangqiqu2-c@my.cityu.edu.hk).
PY - 2020/6
Y1 - 2020/6
N2 - Sufficient data with complete annotation is essential for training deep models to perform automatic and accurate segmentation of CT male pelvic organs, especially when such data is with great challenges such as low contrast and large shape variation. However, manual annotation is expensive in terms of both finance and human effort, which usually results in insufficient completely annotated data in real applications. To this end, we propose a novel deep framework to segment male pelvic organs in CT images with incomplete annotation delineated in a very user-friendly manner. Specifically, we design a hybrid loss network derived from both voxel classification and boundary regression, to jointly improve the organ segmentation performance in an iterative way. Moreover, we introduce a label completion strategy to complete the labels of the rich unannotated voxels and then embed them into the training data to enhance the model capability. To reduce the computation complexity and improve segmentation performance, we locate the pelvic region based on salient bone structures to focus on the candidate segmentation organs. Experimental results on a large planning CT pelvic organ dataset show that our proposed method with incomplete annotation achieves comparable segmentation performance to the state-of-the-art methods with complete annotation. Moreover, our proposed method requires much less effort of manual contouring from medical professionals such that an institutional specific model can be more easily established.
AB - Sufficient data with complete annotation is essential for training deep models to perform automatic and accurate segmentation of CT male pelvic organs, especially when such data is with great challenges such as low contrast and large shape variation. However, manual annotation is expensive in terms of both finance and human effort, which usually results in insufficient completely annotated data in real applications. To this end, we propose a novel deep framework to segment male pelvic organs in CT images with incomplete annotation delineated in a very user-friendly manner. Specifically, we design a hybrid loss network derived from both voxel classification and boundary regression, to jointly improve the organ segmentation performance in an iterative way. Moreover, we introduce a label completion strategy to complete the labels of the rich unannotated voxels and then embed them into the training data to enhance the model capability. To reduce the computation complexity and improve segmentation performance, we locate the pelvic region based on salient bone structures to focus on the candidate segmentation organs. Experimental results on a large planning CT pelvic organ dataset show that our proposed method with incomplete annotation achieves comparable segmentation performance to the state-of-the-art methods with complete annotation. Moreover, our proposed method requires much less effort of manual contouring from medical professionals such that an institutional specific model can be more easily established.
KW - CT
KW - Image segmentation
KW - deep learning
KW - incomplete annotation
KW - male pelvic organ
UR - http://www.scopus.com/inward/record.url?scp=85085904736&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85085904736&partnerID=8YFLogxK
U2 - 10.1109/TMI.2020.2966389
DO - 10.1109/TMI.2020.2966389
M3 - Article
C2 - 31940526
AN - SCOPUS:85085904736
VL - 39
SP - 2151
EP - 2162
JO - IEEE Transactions on Medical Imaging
JF - IEEE Transactions on Medical Imaging
SN - 0278-0062
IS - 6
M1 - 8957549
ER -