The state of the art in kidney and kidney tumor segmentation in contrast-enhanced CT imaging: Results of the KiTS19 challenge

doi:10.1016/j.media.2020.101821

	The state of the art in kidney and kidney tumor segmentation in contrast-enhanced CT imaging: Results of the KiTS19 challenge
	Heller, Nicholas 1; Isensee, Fabian 2,3; Maier-Hein, Klaus H.2; Hou, Xiaoshuai 4; Xie, Chunmei 4; Li, Fengyi 4; Nan, Yang 4; Mu, Guangrui 5,6; Lin, Zhiyong 7; Han, Miofei 5; Yao, Guang 5; Gao, Yaozong 5; Zhang, Yao 8,9; Wang, Yixin 8,9; Hou, Feng 8,9; Yang, Jiawei 10; Xiong, Guangwei 10; Tian, Jiang 11; Zhong, Cheng 11; Ma, Jun 12; Rickman, Jack 1; Dean, Joshua 1; Stai, Bethany 1; Tejpaul, Resha 1; Oestreich, Makinna 1; Blake, Paul 1; Kaluzniak, Heather 15; Raza, Shaneabbas 15; Rosenberg, Joel 1; Moore, Keenan 16; Walczak, Edward 1; Rengel, Zachary 1; Edgerton, Zach 1; Vasdev, Ranveer 1; Peterson, Matthew 1; McSweeney, Sean 1; Peterson, Sarah 14; Kalapara, Arveen 13; Sathianathen, Niranjan 13; Papanikolopoulos, Nikolaos 1; Weight, Christopher 1
	2021
发表期刊	MEDICAL IMAGE ANALYSIS
ISSN	1361-8415
卷号	67 页码:16
摘要	There is a large body of literature linking anatomic and geometric characteristics of kidney tumors to perioperative and oncologic outcomes. Semantic segmentation of these tumors and their host kidneys is a promising tool for quantitatively characterizing these lesions, but its adoption is limited due to the manual effort required to produce high-quality 3D segmentations of these structures. Recently, methods based on deep learning have shown excellent results in automatic 3D segmentation, but they require large datasets for training, and there remains little consensus on which methods perform best. The 2019 Kidney and Kidney Tumor Segmentation challenge (KiTS19) was a competition held in conjunction with the 2019 International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) which sought to address these issues and stimulate progress on this automatic segmentation problem. A training set of 210 cross sectional CT images with kidney tumors was publicly released with corresponding semantic segmentation masks. 106 teams from five continents used this data to develop automated systems to predict the true segmentation masks on a test set of 90 CT images for which the corresponding ground truth segmentations were kept private. These predictions were scored and ranked according to their average Sorensen-Dice coefficient between the kidney and tumor across all 90 cases. The winning team achieved a Dice of 0.974 for kidney and 0.851 for tumor, approaching the inter-annotator performance on kidney (0.983) but falling short on tumor (0.923). This challenge has now entered an "open leaderboard" phase where it serves as a challenging benchmark in 3D semantic segmentation. (C) 2020 Elsevier B.V. All rights reserved.
关键词	Semantic segmentation Computed tomography Kidney tumor
DOI	10.1016/j.media.2020.101821
收录类别	SCI
语种	英语
资助项目	National Cancer Institute of the National Institutes of Health[R01CA225435]
WOS研究方向	Computer Science ; Engineering ; Radiology, Nuclear Medicine & Medical Imaging
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Interdisciplinary Applications ; Engineering, Biomedical ; Radiology, Nuclear Medicine & Medical Imaging
WOS记录号	WOS:000598891600009
出版者	ELSEVIER
引用统计	被引频次：296[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/16610
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Heller, Nicholas
作者单位	1.Univ Minnesota, Minneapolis, MN 55455 USA 2.German Canc Res Ctr, Heidelberg, Germany 3.Heidelberg Univ, Heidelberg, Germany 4.PingAn Technol Co Ltd, Shanghai, Peoples R China 5.Shanghai United Imaging Intelligence Inc, Shanghai, Peoples R China 6.Southern Med Univ, Guangzhou, Peoples R China 7.Peking Univ First Hosp, Beijing, Peoples R China 8.Chinese Acad Sci, Inst Comp Technol, Beijing, Peoples R China 9.Univ Chinese Acad Sci, Beijing, Peoples R China 10.Southeast Univ, Nanjing, Peoples R China 11.Lenovo Res, AI Lab, Beijing, Peoples R China 12.Nanjing Univ Sci & Technol, Sch Sci, Nanjing, Peoples R China 13.Univ Melbourne, Melbourne, Vic, Australia 14.Brigham Young Univ, Provo, UT 84602 USA 15.Univ North Dakota, Grand Forks, ND 58201 USA 16.Carleton Coll, Northfield, MN 55057 USA
推荐引用方式 GB/T 7714	Heller, Nicholas,Isensee, Fabian,Maier-Hein, Klaus H.,et al. The state of the art in kidney and kidney tumor segmentation in contrast-enhanced CT imaging: Results of the KiTS19 challenge[J]. MEDICAL IMAGE ANALYSIS,2021,67:16.
APA	Heller, Nicholas.,Isensee, Fabian.,Maier-Hein, Klaus H..,Hou, Xiaoshuai.,Xie, Chunmei.,...&Weight, Christopher.(2021).The state of the art in kidney and kidney tumor segmentation in contrast-enhanced CT imaging: Results of the KiTS19 challenge.MEDICAL IMAGE ANALYSIS,67,16.
MLA	Heller, Nicholas,et al."The state of the art in kidney and kidney tumor segmentation in contrast-enhanced CT imaging: Results of the KiTS19 challenge".MEDICAL IMAGE ANALYSIS 67(2021):16.