Graph-convolutional-network-based interactive prostate segmentation in MR images

doi:10.1002/mp.14327

	Graph-convolutional-network-based interactive prostate segmentation in MR images
	Tian, Zhiqiang 8; Li, Xiaojian 8; Zheng, Yaoyue 8; Chen, Zhang 8; Shi, Zhong 6,7; Liu, Lizhi 4,5; Fei, Baowei 1,2,3
刊名	MEDICAL PHYSICS
	2020-07-13
关键词	graph convolutional network interactive segmentation prostate MR image
ISSN号	0094-2405
DOI	10.1002/mp.14327
通讯作者	Tian, Zhiqiang(tianzq@gmail.com)
英文摘要	Purpose Accurate and robust segmentation of the prostate from magnetic resonance (MR) images is extensively applied in many clinical applications in prostate cancer diagnosis and treatment. The purpose of this study is the development of a robust interactive segmentation method for accurate segmentation of the prostate from MR images. Methods We propose an interactive segmentation method based on a graph convolutional network (GCN) to refine the automatically segmented results. An atrous multiscale convolutional neural network (CNN) encoder is proposed to learn representative features to obtain accurate segmentations. Based on the multiscale feature, a GCN block is presented to predict the prostate contour in both automatic and interactive manners. To preserve the prostate boundary details and effectively train the GCN, a contour matching loss is proposed. The performance of the proposed algorithm was evaluated on 41 in-house MR subjects and 30 PROMISE12 test subjects. Result The proposed method yields mean Dice similarity coefficients of 93.8 +/- 1.2% and 94.4 +/- 1.0% on our in-house and PROMISE12 datasets, respectively. The experimental results show that the proposed method outperforms several state-of-the-art segmentation methods. Conclusion The proposed interactive segmentation method based on the GCN can accurately segment the prostate from MR images. Our method has a variety of applications in prostate cancer imaging.
资助项目	NSFC[61876148] ; NSFC[81602583] ; Fundamental Research Funds for the Central Universities[XJJ2018254] ; China Postdoctoral Science Foundation[2018M631164]
WOS研究方向	Radiology, Nuclear Medicine & Medical Imaging
语种	英语
出版者	WILEY
WOS记录号	WOS:000547741300001
资助机构	NSFC ; Fundamental Research Funds for the Central Universities ; China Postdoctoral Science Foundation
内容类型	期刊论文
源URL	[http://ir.hfcas.ac.cn:8080/handle/334002/71085]
专题	中国科学院合肥物质科学研究院
通讯作者	Tian, Zhiqiang
作者单位	1.Univ Texas Southwestern Med Ctr Dallas, Dept Radiol, Dallas, TX 75080 USA 2.Univ Texas Southwestern Med Ctr Dallas, Adv Imaging Res Ctr, Dallas, TX 75080 USA 3.Univ Texas Dallas, Dept Bioengn, Richardson, TX 75035 USA 4.State Key Lab Oncol South China, Guangzhou 510060, Peoples R China 5.Sun Yat Sen Univ, Canc Ctr, Ctr Med Imaging & Imageguided Therapy, Guangzhou 510060, Peoples R China 6.Univ Chinese Acad Sci, Canc Hosp, Hangzhou 310022, Peoples R China 7.Chinese Acad Sci, Inst Canc & Basic Med, Hangzhou 310022, Peoples R China 8.Xi An Jiao Tong Univ, Sch Software Engn, Xian 710049, Peoples R China
推荐引用方式 GB/T 7714	Tian, Zhiqiang,Li, Xiaojian,Zheng, Yaoyue,et al. Graph-convolutional-network-based interactive prostate segmentation in MR images[J]. MEDICAL PHYSICS,2020.
APA	Tian, Zhiqiang.,Li, Xiaojian.,Zheng, Yaoyue.,Chen, Zhang.,Shi, Zhong.,...&Fei, Baowei.(2020).Graph-convolutional-network-based interactive prostate segmentation in MR images.MEDICAL PHYSICS.
MLA	Tian, Zhiqiang,et al."Graph-convolutional-network-based interactive prostate segmentation in MR images".MEDICAL PHYSICS (2020).