Abstract
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.
| Original language | English |
|---|---|
| Article number | 8451958 |
| Pages (from-to) | 585-595 |
| Number of pages | 11 |
| Journal | IEEE Transactions on Medical Imaging |
| Volume | 38 |
| Issue number | 2 |
| DOIs | |
| Publication status | Published - 2019 Feb 1 |
Fingerprint
Keywords
- computed tomography
- Image segmentation
- multitasking
- neural networks
- pelvic organ
- prostate cancer
ASJC Scopus subject areas
- Software
- Radiological and Ultrasound Technology
- Computer Science Applications
- Electrical and Electronic Engineering
Cite this
Pelvic Organ Segmentation Using Distinctive Curve Guided Fully Convolutional Networks. / He, Kelei; Cao, Xiaohuan; Shi, Yinghuan; Nie, Dong; Gao, Yang; Shen, Dinggang.
In: IEEE Transactions on Medical Imaging, Vol. 38, No. 2, 8451958, 01.02.2019, p. 585-595.Research output: Contribution to journal › Article
}
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
PY - 2019/2/1
Y1 - 2019/2/1
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 - computed tomography
KW - Image segmentation
KW - multitasking
KW - neural networks
KW - pelvic organ
KW - prostate cancer
UR - http://www.scopus.com/inward/record.url?scp=85061034978&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.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 -