TY - JOUR
T1 - Pelvic Organ Segmentation Using Distinctive Curve Guided Fully Convolutional Networks
AU - He, Kelei
AU - Cao, Xiaohuan
AU - Shi, Yinghuan
AU - Nie, Dong
AU - Gao, Yang
AU - Shen, Dinggang
N1 - Funding Information:
Manuscript received August 15, 2018; accepted August 23, 2018. Date of publication August 30, 2018; date of current version February 1, 2019. This work was supported in part by the National Natural Science Foundation of China under Grant 61432008, Grant 61673203, and Grant U1435214, in part by the Young Elite Scientists Sponsorship Program through CAST under Grant 2016QNRC001, in part by NIH under Grant CA206100, and in part by the Collaborative Innovation Center of Novel Software Technology and Industrialization. (Corresponding authors: Dinggang Shen; Yang Gao.) K. He is with the State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing 210008, China, and also with the Biomedical Research Imaging Center, University of North Carolina, Chapel Hill, NC 27599 USA.
Funding Information:
This work was supported in part by the National Natural Science Foundation of China under Grant 61432008, Grant 61673203, and Grant U1435214, in part by the Young Elite Scientists Sponsorship Program through CAST under Grant 2016QNRC001, in part by NIH under Grant CA206100, and in part by the Collaborative Innovation Center of Novel Software Technology and Industrialization.
Publisher Copyright:
© 2018 IEEE.
PY - 2019/2
Y1 - 2019/2
N2 - Accurate segmentation of pelvic organs (i.e., prostate, bladder, and rectum) from CT image is crucial for effective prostate cancer radiotherapy. However, it is a challenging task due to: 1) low soft tissue contrast in CT images and 2) large shape and appearance variations of pelvic organs. In this paper, we employ a two-stage deep learning-based method, with a novel distinctive curve-guided fully convolutional network (FCN), to solve the aforementioned challenges. Specifically, the first stage is for fast and robust organ detection in the raw CT images. It is designed as a coarse segmentation network to provide region proposals for three pelvic organs. The second stage is for fine segmentation of each organ, based on the region proposal results. To better identify those indistinguishable pelvic organ boundaries, a novel morphological representation, namely, distinctive curve, is also introduced to help better conduct the precise segmentation. To implement this, in this second stage, a multi-task FCN is initially utilized to learn the distinctive curve and the segmentation map separately and then combine these two tasks to produce accurate segmentation map. The final segmentation results of all three pelvic organs are generated by a weighted max-voting strategy. We have conducted exhaustive experiments on a large and diverse pelvic CT data set for evaluating our proposed method. The experimental results demonstrate that our proposed method is accurate and robust for this challenging segmentation task, by also outperforming the state-of-the-art segmentation methods.
AB - Accurate segmentation of pelvic organs (i.e., prostate, bladder, and rectum) from CT image is crucial for effective prostate cancer radiotherapy. However, it is a challenging task due to: 1) low soft tissue contrast in CT images and 2) large shape and appearance variations of pelvic organs. In this paper, we employ a two-stage deep learning-based method, with a novel distinctive curve-guided fully convolutional network (FCN), to solve the aforementioned challenges. Specifically, the first stage is for fast and robust organ detection in the raw CT images. It is designed as a coarse segmentation network to provide region proposals for three pelvic organs. The second stage is for fine segmentation of each organ, based on the region proposal results. To better identify those indistinguishable pelvic organ boundaries, a novel morphological representation, namely, distinctive curve, is also introduced to help better conduct the precise segmentation. To implement this, in this second stage, a multi-task FCN is initially utilized to learn the distinctive curve and the segmentation map separately and then combine these two tasks to produce accurate segmentation map. The final segmentation results of all three pelvic organs are generated by a weighted max-voting strategy. We have conducted exhaustive experiments on a large and diverse pelvic CT data set for evaluating our proposed method. The experimental results demonstrate that our proposed method is accurate and robust for this challenging segmentation task, by also outperforming the state-of-the-art segmentation methods.
KW - Image segmentation
KW - computed tomography
KW - multitasking
KW - neural networks
KW - pelvic organ
KW - prostate cancer
UR - http://www.scopus.com/inward/record.url?scp=85061034978&partnerID=8YFLogxK
U2 - 10.1109/TMI.2018.2867837
DO - 10.1109/TMI.2018.2867837
M3 - Article
C2 - 30176583
AN - SCOPUS:85061034978
VL - 38
SP - 585
EP - 595
JO - IEEE Transactions on Medical Imaging
JF - IEEE Transactions on Medical Imaging
SN - 0278-0062
IS - 2
M1 - 8451958
ER -