MyoPS: A benchmark of myocardial pathology segmentation combining three-sequence cardiac magnetic resonance images

Lei Li; Fuping Wu; Sihan Wang; Xinzhe Luo; Carlos Martín-Isla; Shuwei Zhai; Jianpeng Zhang; Yanfei Liu; Zhen Zhang; Markus J Ankenbrand; Haochuan Jiang; Xiaoran Zhang; Linhong Wang; Tewodros Weldebirhan Arega; Elif Altunok; Zhou Zhao; Feiyan Li; Jun Ma; Xiaoping Yang; Elodie Puybareau; Ilkay Oksuz; Stephanie Bricq; Weisheng Li; Kumaradevan Punithakumar; Sotirios A Tsaftaris; Laura M Schreiber; Mingjing Yang; Guocai Liu; Yong Xia; Guotai Wang; Sergio Escalera; Xiahai Zhuang

doi:10.1016/j.media.2023.102808

MyoPS: A benchmark of myocardial pathology segmentation combining three-sequence cardiac magnetic resonance images

Med Image Anal. 2023 Jul:87:102808. doi: 10.1016/j.media.2023.102808. Epub 2023 Apr 4.

Authors

Lei Li¹, Fuping Wu², Sihan Wang³, Xinzhe Luo⁴, Carlos Martín-Isla⁵, Shuwei Zhai⁶, Jianpeng Zhang⁷, Yanfei Liu⁸, Zhen Zhang⁹, Markus J Ankenbrand¹⁰, Haochuan Jiang¹¹, Xiaoran Zhang¹², Linhong Wang¹³, Tewodros Weldebirhan Arega¹⁴, Elif Altunok¹⁵, Zhou Zhao¹⁶, Feiyan Li¹³, Jun Ma¹⁷, Xiaoping Yang¹⁸, Elodie Puybareau¹⁶, Ilkay Oksuz¹⁵, Stephanie Bricq¹⁴, Weisheng Li¹³, Kumaradevan Punithakumar¹⁹, Sotirios A Tsaftaris²⁰, Laura M Schreiber¹⁰, Mingjing Yang⁹, Guocai Liu²¹, Yong Xia⁷, Guotai Wang⁶, Sergio Escalera²², Xiahai Zhuang²³

Affiliations

¹ School of Data Science, Fudan University, Shanghai, China; School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, China. Electronic address: lilei.sky@sjtu.edu.cn.
² School of Data Science, Fudan University, Shanghai, China. Electronic address: 17110690006@fudan.edu.cn.
³ School of Data Science, Fudan University, Shanghai, China. Electronic address: shwang21@m.fudan.edu.cn.
⁴ School of Data Science, Fudan University, Shanghai, China.
⁵ Departament de Matemàtiques & Informàtica, Universitat de Barcelona, Barcelona, Spain.
⁶ School of Mechanical and Electrical Engineering, University of Electronic Science and Technology of China, Chengdu, China.
⁷ School of Computer Science and Engineering, Northwestern Polytechnical University, Xi'an, China.
⁸ College of Electrical and Information Engineering, Hunan University, Changsha, China.
⁹ College of Physics and Information Engineering, Fuzhou University, Fuzhou, China.
¹⁰ Chair of Molecular and Cellular Imaging, Comprehensive Heart Failure Center, Wuerzburg University Hospitals, Wuerzburg, Germany.
¹¹ School of Engineering, University of Edinburgh, Edinburgh, UK; School of Robotics, Xi'an Jiaotong-Liverpool University, Suzhou, China.
¹² Department of Electrical and Computer Engineering, University of California, LA, USA.
¹³ Chongqing Key Laboratory of Image Cognition, Chongqing University of Posts and Telecommunications, Chongqing, China.
¹⁴ ImViA Laboratory, Université Bourgogne Franche-Comté, Dijon, France.
¹⁵ Computer Engineering Department, Istanbul Technical University, Istanbul, Turkey.
¹⁶ EPITA Research and Development Laboratory (LRDE), Le Kremlin-Bicêtre, France.
¹⁷ Department of Mathematics, Nanjing University of Science and Technology, Nanjing, China.
¹⁸ Department of Mathematics, Nanjing University, Nanjing, China.
¹⁹ Department of Radiology and Diagnostic Imaging, University of Alberta, Edmonton, Canada.
²⁰ School of Engineering, University of Edinburgh, Edinburgh, UK.
²¹ College of Electrical and Information Engineering, Hunan University, Changsha, China; National Engineering Laboratory for Robot Visual Perception and Control Technology, Changsha, China.
²² Departament de Matemàtiques & Informàtica, Universitat de Barcelona, Barcelona, Spain; Computer Vision Center, Universitat Autònoma de Barcelona, Spain.
²³ School of Data Science, Fudan University, Shanghai, China. Electronic address: zxh@fudan.edu.cn.

PMID: 37087838
DOI: 10.1016/j.media.2023.102808

Abstract

Assessment of myocardial viability is essential in diagnosis and treatment management of patients suffering from myocardial infarction, and classification of pathology on the myocardium is the key to this assessment. This work defines a new task of medical image analysis, i.e., to perform myocardial pathology segmentation (MyoPS) combining three-sequence cardiac magnetic resonance (CMR) images, which was first proposed in the MyoPS challenge, in conjunction with MICCAI 2020. Note that MyoPS refers to both myocardial pathology segmentation and the challenge in this paper. The challenge provided 45 paired and pre-aligned CMR images, allowing algorithms to combine the complementary information from the three CMR sequences for pathology segmentation. In this article, we provide details of the challenge, survey the works from fifteen participants and interpret their methods according to five aspects, i.e., preprocessing, data augmentation, learning strategy, model architecture and post-processing. In addition, we analyze the results with respect to different factors, in order to examine the key obstacles and explore the potential of solutions, as well as to provide a benchmark for future research. The average Dice scores of submitted algorithms were 0.614±0.231 and 0.644±0.153 for myocardial scars and edema, respectively. We conclude that while promising results have been reported, the research is still in the early stage, and more in-depth exploration is needed before a successful application to the clinics. MyoPS data and evaluation tool continue to be publicly available upon registration via its homepage (www.sdspeople.fudan.edu.cn/zhuangxiahai/0/myops20/).

Keywords: Benchmark; Cardiac magnetic resonance; Multi-sequence MRI; Multi-source images; Myocardial pathology segmentation.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Benchmarking*
Heart / diagnostic imaging
Humans
Image Processing, Computer-Assisted* / methods
Magnetic Resonance Imaging / methods
Myocardium / pathology