Cardiac segmentation on late gadolinium enhancement MRI: A benchmark study from multi-sequence cardiac MR segmentation challenge

Zhuang，Xiahai1; Xu，Jiahang1; Luo，Xinzhe1; Chen，Chen3; Ouyang，Cheng3; Rueckert，Daniel3; Campello，Victor M.4; Lekadir，Karim4; Vesal，Sulaiman5; RaviKumar，Nishant5; Liu，Yashu6; Luo，Gongning6; Chen，Jingkun7; Li，Hongwei8; Ly，Buntheng9; Sermesant，Maxime9; Roth，Holger10; Zhu，Wentao10; Wang，Jiexiang11; Ding，Xinghao11; Wang，Xinyue12; Yang，Sen12,13; Li，Lei1,2

2022-10-01

10.1016/j.media.2022.102528

MEDICAL IMAGE ANALYSIS   Impact Factor & Quartile

1361-8415

1361-8423

Accurate computing, analysis and modeling of the ventricles and myocardium from medical images are important, especially in the diagnosis and treatment management for patients suffering from myocardial infarction (MI). Late gadolinium enhancement (LGE) cardiac magnetic resonance (CMR) provides an important protocol to visualize MI. However, compared with the other sequences LGE CMR images with gold standard labels are particularly limited. This paper presents the selective results from the Multi-Sequence Cardiac MR (MS-CMR) Segmentation challenge, in conjunction with MICCAI 2019. The challenge offered a data set of paired MS-CMR images, including auxiliary CMR sequences as well as LGE CMR, from 45 patients who underwent cardiomyopathy. It was aimed to develop new algorithms, as well as benchmark existing ones for LGE CMR segmentation focusing on myocardial wall of the left ventricle and blood cavity of the two ventricles. In addition, the paired MS-CMR images could enable algorithms to combine the complementary information from the other sequences for the ventricle segmentation of LGE CMR. Nine representative works were selected for evaluation and comparisons, among which three methods are unsupervised domain adaptation (UDA) methods and the other six are supervised. The results showed that the average performance of the nine methods was comparable to the inter-observer variations. Particularly, the top-ranking algorithms from both the supervised and UDA methods could generate reliable and robust segmentation results. The success of these methods was mainly attributed to the inclusion of the auxiliary sequences from the MS-CMR images, which provide important label information for the training of deep neural networks. The challenge continues as an ongoing resource, and the gold standard segmentation as well as the MS-CMR images of both the training and test data are available upon registration via its homepage (www.sdspeople.fudan.edu.cn/zhuangxiahai/0/mscmrseg/).

Benchmark Cardiac MRI segmentation Challenge Multi-sequence

SCI ; EI

English

Others

National Natural Science Foundation of China[61971142];National Natural Science Foundation of China[62011540404];National Natural Science Foundation of China[62111530195];

Computer Science ; Engineering ; Radiology, Nuclear Medicine & Medical Imaging

Computer Science, Artificial Intelligence ; Computer Science, Interdisciplinary Applications ; Engineering, Biomedical ; Radiology, Nuclear Medicine & Medical Imaging

WOS:000861027600002

ELSEVIER

20223012406366

Deep neural networks ; Gadolinium ; Heart ; Image segmentation ; Magnetic resonance ; Medical imaging ; Patient treatment

Biomedical Engineering:461.1 ; Biological Materials and Tissue Engineering:461.2 ; Ergonomics and Human Factors Engineering:461.4 ; Medicine and Pharmacology:461.6 ; Rare Earth Metals:547.2 ; Magnetism: Basic Concepts and Phenomena:701.2 ; Imaging Techniques:746

COMPUTER SCIENCE

2-s2.0-85134615635

Scopus

1.School of Data Science,Fudan University,Shanghai,China
2.School of Biomedical Engineering,Shanghai Jiao Tong University,Shanghai,China
3.Biomedical Image Analysis Group,Imperial College London,London,United Kingdom
4.Department Mathematics & Computer Science,Universitat de Barcelona,Barcelona,Spain
5.Friedrich-Alexander-Universität Erlangen-Nürnberg,Germany
6.School of Computer Science and Technology,Harbin Institute of Technology,Harbin,China
7.Department of Computer Science and Engineering,Southern University of Science and Technology,Shenzhen,China
8.Department of Informatics,Technical University of Munich,Germany
9.INRIA,Université Côte d'Azur,Sophia Antipolis,France
10.NVIDIA,Bethesda,United States
11.School of Informatics,Xiamen University,Xiamen,China
12.College of Electrical Engineering,Sichuan University,Chengdu,China
13.Tencent AI Lab,Shenzhen,China

Zhuang，Xiahai,Xu，Jiahang,Luo，Xinzhe,et al. Cardiac segmentation on late gadolinium enhancement MRI: A benchmark study from multi-sequence cardiac MR segmentation challenge[J]. MEDICAL IMAGE ANALYSIS,2022,81.

Zhuang，Xiahai.,Xu，Jiahang.,Luo，Xinzhe.,Chen，Chen.,Ouyang，Cheng.,...&Li，Lei.(2022).Cardiac segmentation on late gadolinium enhancement MRI: A benchmark study from multi-sequence cardiac MR segmentation challenge.MEDICAL IMAGE ANALYSIS,81.

Zhuang，Xiahai,et al."Cardiac segmentation on late gadolinium enhancement MRI: A benchmark study from multi-sequence cardiac MR segmentation challenge".MEDICAL IMAGE ANALYSIS 81(2022).