Multi-Centre, Multi-Vendor and Multi-Disease Cardiac Segmentation: The M&Ms Challenge

doi:10.1109/TMI.2021.3090082

	Multi-Centre, Multi-Vendor and Multi-Disease Cardiac Segmentation: The M&Ms Challenge
	Campello, Victor M.1; Gkontra, Polyxeni 1; Izquierdo, Cristian 1; Martin-Isla, Carlos 1; Sojoudi, Alireza 2; Full, Peter M.3; Maier-Hein, Klaus 3; Zhang, Yao 4; He, Zhiqiang 5; Ma, Jun 6; Parreno, Mario 7; Albiol, Alberto 8; Kong, Fanwei 9; Shadden, Shawn C.9; Acero, Jorge Corral 10; Sundaresan, Vaanathi 11; Saber, Mina 12; Elattar, Mustafa 12,13; Li, Hongwei 14,15; Menze, Bjoern 14; Khader, Firas 16; Haarburger, Christoph 16; Scannell, Cian M.17; Veta, Mitko 18; Carscadden, Adam 19,20; Punithakumar, Kumaradevan 19,20; Liu, Xiao 21; Tsaftaris, Sotirios A.21,22; Huang, Xiaoqiong 23,24; Yang, Xin 23,24; Li, Lei 25; Zhuang, Xiahai 26; Vilades, David 27; Descalzo, Martin L.27; Guala, Andrea 28; La Mura, Lucia 29; Friedrich, Matthias G.30; Garg, Ria 30; Lebel, Julie 30; Henriques, Filipe 30; Karakas, Mahir 31,32; Cavus, Ersin 31,32; Petersen, Steffen E.33,34; Escalera, Sergio 35,36; Segui, Santi 35; Rodriguez-Palomares, Jose F.28; Lekadir, Karim 1
	2021-12-01
发表期刊	IEEE TRANSACTIONS ON MEDICAL IMAGING
ISSN	0278-0062
卷号	40 期号:12 页码:3543-3554
摘要	The emergence of deep learning has considerably advanced the state-of-the-art in cardiac magnetic resonance (CMR) segmentation. Many techniques have been proposed over the last few years, bringing the accuracy of automated segmentation close to human performance. However, these models have been all too often trained and validated using cardiac imaging samples from single clinical centres or homogeneous imaging protocols. This has prevented the development and validation of models that are generalizable across different clinical centres, imaging conditions or scanner vendors. To promote further research and scientific benchmarking in the field of generalizable deep learning for cardiac segmentation, this paper presents the results of the Multi-Centre, Multi-Vendor and Multi-Disease Cardiac Segmentation (M&Ms) Challenge, which was recently organized as part of the MICCAI 2020 Conference. A total of 14 teams submitted different solutions to the problem, combining various baseline models, data augmentation strategies, and domain adaptation techniques. The obtained results indicate the importance of intensity-driven data augmentation, as well as the need for further research to improve generalizability towards unseen scanner vendors or new imaging protocols. Furthermore, we present a new resource of 375 heterogeneous CMR datasets acquired by using four different scanner vendors in six hospitals and three different countries (Spain, Canada and Germany), which we provide as open-access for the community to enable future research in the field.
关键词	Image segmentation Heart Training Hospitals Deep learning Biomedical engineering Protocols Cardiovascular magnetic resonance image segmentation deep learning generalizability data augmentation domain adaption public dataset
DOI	10.1109/TMI.2021.3090082
收录类别	SCI
语种	英语
资助项目	European Union[825903]
WOS研究方向	Computer Science ; Engineering ; Imaging Science & Photographic Technology ; Radiology, Nuclear Medicine & Medical Imaging
WOS类目	Computer Science, Interdisciplinary Applications ; Engineering, Biomedical ; Engineering, Electrical & Electronic ; Imaging Science & Photographic Technology ; Radiology, Nuclear Medicine & Medical Imaging
WOS记录号	WOS:000724511900026
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：191[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/2XEOYT63/18063
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Campello, Victor M.
作者单位	1.Univ Barcelona, Artificial Intelligence Med Lab BCN AIM, Dept Matemat & Informat, Barcelona 08007, Spain 2.Circle Cardiovasc Imaging Pvt Ltd, Calgary, AB T2P 3T6, Canada 3.German Canc Res Ctr, Div Med Image Comp, D-69120 Heidelberg, Germany 4.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China 5.Lenovo Ltd, Beijing 100085, Peoples R China 6.Nanjing Univ Sci & Technol, Dept Math, Nanjing 210094, Peoples R China 7.Univ Politecn Valencia, PRHLT Res Ctr, Valencia 46022, Spain 8.Univ Politecn Valencia, iTeam Res Inst, Valencia 46022, Spain 9.Univ Calif Berkeley, Dept Mech Engn, Berkeley, CA 94720 USA 10.Univ Oxford, Dept Engn Sci, Inst Biomed Engn, Oxford OX3 7DQ, England 11.Univ Oxford, Ctr Funct MRI Brain, Nuffield Dept Clin Neurosci, Oxford OX3 9DU, England 12.Intixel Co SAE, Res & Dev Div, Cairo 11585, Egypt 13.Nile Univ, Med Imaging & Image Proc Grp, Giza 16453, Egypt 14.Tech Univ Munich, Dept Comp Sci, D-80333 Munich, Germany 15.Orbem GmbH, D-85748 Garching, Germany 16.ARISTRA GmbH, D-10439 Berlin, Germany 17.Kings Coll London, Sch Biomed Engn & Imaging Sci, London WC2R 2LS, England 18.Eindhoven Univ Technol, Dept Biomed Engn, NL-5612 Eindhoven, Netherlands 19.Univ Alberta, Dept Radiol & Diagnost Imaging, Edmonton, AB T6G 2R3, Canada 20.Mazankowski Alberta Heart Inst, Servier Virtual Cardiac Ctr, Edmonton, AB T6G 2B7, Canada 21.Univ Edinburgh, Sch Engn, Edinburgh EH9 3FB, Midlothian, Scotland 22.Alan Turing Inst, London NW1 2DB, England 23.Shenzhen Univ, Sch Biomed Engn, Shenzhen 518037, Peoples R China 24.Shenzhen Univ, Med UltraSound Image Comp MUSIC Lab, Shenzhen 518037, Peoples R China 25.Shanghai Jiao Tong Univ, Sch Biomed Engn, Shanghai 200240, Peoples R China 26.Fudan Univ, Sch Data Sci, Shanghai 200433, Peoples R China 27.Univ Autonoma Barcelona, Cardiol Serv, Cardiac Imaging Unit, Hosp Santa Creu & St Pau, Barcelona, Spain 28.Univ Autonoma Barcelona, Hosp Univ Vall dHebron, Vall dHebron Inst Recerca, CIBERCV,Dept Cardiol, Barcelona 08193, Spain 29.Univ Naples Federico II, Dept Adv Biomed Sci, I-80138 Naples, Italy 30.McGill Univ, Dept Med & Diagnost Radiol, Montreal, PQ H3A 0G4, Canada 31.Univ Heart & Vasc Ctr Hamburg, Dept Cardiol, D-20251 Hamburg, Germany 32.German Ctr Cardiovasc Res DZHK, D-10785 Berlin, Germany 33.Barts Hlth NHS Trust, Barts Heart Ctr, London E1 1BB, England 34.Queen Mary Univ London, NIHR Barts Biomed Res Ctr, William Harvey Res Inst, London E1 4NS, England 35.Univ Barcelona, Dept Matemat & Informat, Barcelona 08007, Spain 36.Univ Autonoma Barcelona, Comp Vis Ctr, Barcelona 08193, Spain
推荐引用方式 GB/T 7714	Campello, Victor M.,Gkontra, Polyxeni,Izquierdo, Cristian,et al. Multi-Centre, Multi-Vendor and Multi-Disease Cardiac Segmentation: The M&Ms Challenge[J]. IEEE TRANSACTIONS ON MEDICAL IMAGING,2021,40(12):3543-3554.
APA	Campello, Victor M..,Gkontra, Polyxeni.,Izquierdo, Cristian.,Martin-Isla, Carlos.,Sojoudi, Alireza.,...&Lekadir, Karim.(2021).Multi-Centre, Multi-Vendor and Multi-Disease Cardiac Segmentation: The M&Ms Challenge.IEEE TRANSACTIONS ON MEDICAL IMAGING,40(12),3543-3554.
MLA	Campello, Victor M.,et al."Multi-Centre, Multi-Vendor and Multi-Disease Cardiac Segmentation: The M&Ms Challenge".IEEE TRANSACTIONS ON MEDICAL IMAGING 40.12(2021):3543-3554.