Fully convolutional network-based multi-output model for automatic segmentation of organs at risk in thorax

doi:10.1177/00368504211020161

HFCAS OpenIR

	Fully convolutional network-based multi-output model for automatic segmentation of organs at risk in thorax
	Zhang, Jie 1,2,3; Yang, Yiwei 1,2,3; Shao, Kainan 1,2,3; Bai, Xue 1,2,3; Fang, Min 1,4,5; Shan, Guoping 1,2,3; Chen, Ming 1,4,5
	2021-04-01
发表期刊	SCIENCE PROGRESS
ISSN	0036-8504
通讯作者	Chen, Ming(chenming@zjcc.org.cn)
摘要	Purpose: To propose a multi-output fully convolutional network (MOFCN) to segment bilateral lung, heart and spinal cord in the planning thoracic computed tomography (CT) slices automatically and simultaneously. Methods: The MOFCN includes two components: one main backbone and three branches. The main backbone extracts the features about lung, heart and spinal cord. The extracted features are transferred to three branches which correspond to three organs respectively. The longest branch to segment spinal cord is nine layers, including input and output layers. The MOFCN was evaluated on 19,277 CT slices from 966 patients with cancer in the thorax. In these slices, the organs at risk (OARs) were delineated and validated by experienced radiation oncologists, and served as ground truth for training and evaluation. The data from 61 randomly chosen patients were used for training and validation. The remaining 905 patients' slices were used for testing. The metric used to evaluate the similarity between the auto-segmented organs and their ground truth was Dice. Besides, we compared the MOFCN with other published models. To assess the distinct output design and the impact of layer number and dilated convolution, we compared MOFCN with a multi-label learning model and its variants. By analyzing the not good performances, we suggested possible solutions. Results: MOFCN achieved Dice of 0.950.02 for lung, 0.91 +/- 0.03 for heart and 0.87 +/- 0.06 for spinal cord. Compared to other models, MOFCN could achieve a comparable accuracy with the least time cost. Conclusion: The results demonstrated the MOFCN's effectiveness. It uses less parameters to delineate three OARs simultaneously and automatically, and thus shows a relatively low requirement for hardware and has potential for broad application.
关键词	Fully convolutional network multi-output architecture organ at risk automatic segmentation thoracic radiotherapy
DOI	10.1177/00368504211020161
关键词[WOS]	ATLAS-BASED SEGMENTATION ; CLINICAL TARGET VOLUME ; INTEROBSERVER VARIATION ; PLANNING CT ; SPINAL-CORD ; DELINEATION ; RADIOTHERAPY ; TUMOR ; HEAD ; PROSTATE
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Program[2017YFC0113201] ; Zhejiang Provincial Natural Science Foundation of China[LQ20H180016] ; Zhejiang Provincial Natural Science Foundation of China[LQ17H180003] ; Zhejiang Key Research and Development Program[2019C03003] ; Youth Talent Foundation of Zhejiang Medical and Health Project[2019RC023] ; Appropriate Technology Cultivation and Promotion of Zhejiang Medical and Health Project[2019ZH018] ; Postdoctoral Program of Zhejiang Province ; National Natural Science Foundation of China[81230031/H18] ; National Natural Science Foundation of China[82001928] ; Chinese Postdoctoral Fund[520000-X91601]
项目资助者	National Key Research and Development Program ; Zhejiang Provincial Natural Science Foundation of China ; Zhejiang Key Research and Development Program ; Youth Talent Foundation of Zhejiang Medical and Health Project ; Appropriate Technology Cultivation and Promotion of Zhejiang Medical and Health Project ; Postdoctoral Program of Zhejiang Province ; National Natural Science Foundation of China ; Chinese Postdoctoral Fund
WOS研究方向	Education & Educational Research ; Science & Technology - Other Topics
WOS类目	Education, Scientific Disciplines ; Multidisciplinary Sciences
WOS记录号	WOS:000729763400001
出版者	SAGE PUBLICATIONS LTD
引用统计	被引频次：6[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.hfcas.ac.cn:8080/handle/334002/126449
专题	中国科学院合肥物质科学研究院
通讯作者	Chen, Ming
作者单位	1.Chinese Acad Sci, Inst Canc & Med, Hangzhou, Peoples R China 2.Univ Chinese Acad Sci, Dept Radiat Phys, Canc Hosp, Hangzhou, Peoples R China 3.Zhejiang Canc Hosp, Dept Radiat Phys, Hangzhou, Peoples R China 4.Univ Chinese Acad Sci, Dept Radiat Oncol, Canc Hosp, Hangzhou, Peoples R China 5.Zhejiang Canc Hosp, Dept Radiat Oncol, Hangzhou, Peoples R China
推荐引用方式 GB/T 7714	Zhang, Jie,Yang, Yiwei,Shao, Kainan,et al. Fully convolutional network-based multi-output model for automatic segmentation of organs at risk in thorax[J]. SCIENCE PROGRESS,2021,104.
APA	Zhang, Jie.,Yang, Yiwei.,Shao, Kainan.,Bai, Xue.,Fang, Min.,...&Chen, Ming.(2021).Fully convolutional network-based multi-output model for automatic segmentation of organs at risk in thorax.SCIENCE PROGRESS,104.
MLA	Zhang, Jie,et al."Fully convolutional network-based multi-output model for automatic segmentation of organs at risk in thorax".SCIENCE PROGRESS 104(2021).