MyoPS: A Benchmark of Myocardial Pathology Segmentation Combining Three-Sequence Cardiac Magnetic Resonance Images

Assessment of myocardial viability is essential in diagnosis and treatment management of patients suffering from myocardial infarction, and classification of pathology on 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 threesequence cardiac magnetic resonance (CMR) images, which was first proposed in the MyoPS challenge, in conjunction with MICCAI 2020. 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 potential of solutions, as well as to provide a benchmark for future research. 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. Note that MyoPS data and evaluation tool continue to be publicly available upon registration via its homepage (www.sdspeople.fudan.edu.cn/zhuangxiahai/0/myops20/).

[1]  Colin Berry,et al.  Highly automatic quantification of myocardial oedema in patients with acute myocardial infarction using bright blood T2-weighted CMR , 2013, Journal of Cardiovascular Magnetic Resonance.

[2]  A. Herment,et al.  Quantification of myocardial edema and necrosis during acute myocardial infarction , 2008, 2008 Computers in Cardiology.

[3]  Fatemeh Zabihollahy,et al.  Convolutional neural network‐based approach for segmentation of left ventricle myocardial scar from 3D late gadolinium enhancement MR images , 2019, Medical physics.

[4]  R. Rieben,et al.  Edema is a sign of early acute myocardial infarction on post-mortem magnetic resonance imaging , 2013, Forensic Science, Medicine, and Pathology.

[5]  et al.,et al.  ISLES 2015 ‐ A public evaluation benchmark for ischemic stroke lesion segmentation from multispectral MRI , 2017, Medical Image Anal..

[6]  Xiahai Zhuang,et al.  Multivariate Mixture Model for Cardiac Segmentation from Multi-Sequence MRI , 2016, MICCAI.

[7]  Yubing Tong,et al.  LinSEM: Linearizing segmentation evaluation metrics for medical images , 2019, Medical Image Anal..

[8]  Jonathan Chan,et al.  Differentiation of subendocardial and transmural infarction using two-dimensional strain rate imaging to assess short-axis and long-axis myocardial function. , 2006, Journal of the American College of Cardiology.

[9]  A. Culyer.  Spearman’s rank correlation coefficient , 2014, BMJ : British Medical Journal.

[10]  Colin Berry,et al.  Automatic quantification and 3D visualisation of edema in cardiac MRI , 2011, 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[11]  Richard James Housden,et al.  Algorithms for left atrial wall segmentation and thickness – Evaluation on an open-source CT and MRI image database , 2018, Medical Image Anal..

[12]  Yanfei Liu,et al.  Two-Stage Method for Segmentation of the Myocardial Scars and Edema on Multi-sequence Cardiac Magnetic Resonance , 2020, MyoPS@MICCAI.

[13]  Markus J. Ankenbrand,et al.  Exploring Ensemble Applications for Multi-sequence Myocardial Pathology Segmentation , 2020, MyoPS@MICCAI.

[14]  Sotirios A. Tsaftaris,et al.  Max-Fusion U-Net for Multi-Modal Pathology Segmentation with Attention and Dynamic Resampling , 2020, MyoPS@MICCAI.

[15]  Brian B. Avants,et al.  The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS) , 2015, IEEE Transactions on Medical Imaging.

[16]  Stefan L. Zimmerman,et al.  Automatic high-resolution infarct detection using volumetric multiphase dual-energy CT. , 2017, Journal of cardiovascular computed tomography.

[17]  Víctor M. Campello,et al.  Cardiac Segmentation on Late Gadolinium Enhancement MRI: A Benchmark Study from Multi-Sequence Cardiac MR Segmentation Challenge , 2020, Medical Image Anal..

[18]  F. Weidemann,et al.  Longitudinal strain bull’s eye plot patterns in patients with cardiomyopathy and concentric left ventricular hypertrophy , 2016, European Journal of Medical Research.

[19]  Tewodros Weldebirhan Arega,et al.  Automatic Myocardial Scar Segmentation from Multi-sequence Cardiac MRI Using Fully Convolutional Densenet with Inception and Squeeze-Excitation Module , 2020, MyoPS@MICCAI.

[20]  Huafeng Liu,et al.  Direct delineation of myocardial infarction without contrast agents using a joint motion feature learning architecture , 2018, Medical Image Anal..

[21]  Zhen Zhang,et al.  Multi-Modality Pathology Segmentation Framework: Application to Cardiac Magnetic Resonance Images , 2020, MyoPS@MICCAI.

[22]  Daniel Rueckert,et al.  Right ventricle segmentation from cardiac MRI: A collation study , 2015, Medical Image Anal..

[23]  Guang Yang,et al.  Evaluation of algorithms for Multi-Modality Whole Heart Segmentation: An open-access grand challenge , 2019, Medical Image Anal..

[24]  Takashi Matsubara,et al.  Data Augmentation Using Random Image Cropping and Patching for Deep CNNs , 2018, IEEE Transactions on Circuits and Systems for Video Technology.

[25]  Ke Lu,et al.  An overview of multi-modal medical image fusion , 2016, Neurocomputing.

[26]  Xiahai Zhuang,et al.  Multivariate Mixture Model for Myocardial Segmentation Combining Multi-Source Images , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[27]  Simon K. Warfield,et al.  Left Ventricular Segmentation Challenge from Cardiac MRI: A Collation Study , 2011, STACOM.

[28]  Andreas Nürnberger,et al.  CHAOS Challenge - Combined (CT-MR) Healthy Abdominal Organ Segmentation , 2020, Medical Image Anal..

[29]  Mahmood Fathy,et al.  Bi-Directional ConvLSTM U-Net with Densley Connected Convolutions , 2019, 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW).

[30]  Ilkay Öksüz,et al.  Accurate Myocardial Pathology Segmentation with Residual U-Net , 2020, MyoPS@MICCAI.

[31]  M. Cerqueira,et al.  Standardized myocardial segmentation and nomenclature for tomographic imaging of the heart: A statement for healthcare professionals from the Cardiac Imaging Committee of the Council on Clinical Cardiology of the American Heart Association , 2002, The international journal of cardiovascular imaging.

[32]  Xin Yang,et al.  Deep Learning Techniques for Automatic MRI Cardiac Multi-Structures Segmentation and Diagnosis: Is the Problem Solved? , 2018, IEEE Transactions on Medical Imaging.

[33]  Jürgen Weese,et al.  Benchmark for Algorithms Segmenting the Left Atrium From 3D CT and MRI Datasets , 2015, IEEE Transactions on Medical Imaging.

[34]  Andreas K. Maier,et al.  Myocardial Scar Segmentation in LGE-MRI using Fractal Analysis and Random Forest Classification , 2018, 2018 24th International Conference on Pattern Recognition (ICPR).

[35]  Hong Yu,et al.  Dual Attention U-Net for Multi-sequence Cardiac MR Images Segmentation , 2020, MyoPS@MICCAI.

[36]  et al.,et al.  Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation, Progression Assessment, and Overall Survival Prediction in the BRATS Challenge , 2018, ArXiv.

[37]  John D. Austin,et al.  Adaptive histogram equalization and its variations , 1987 .

[38]  Weisheng Li,et al.  Dual-Path Feature Aggregation Network Combined Multi-layer Fusion for Myocardial Pathology Segmentation with Multi-sequence Cardiac MR , 2020, MyoPS@MICCAI.

[39]  J. Milles,et al.  Automated segmentation of myocardial scar in late enhancement MRI using combined intensity and spatial information , 2010, Magnetic resonance in medicine.

[40]  Sergio Escalera,et al.  Multi-Centre, Multi-Vendor and Multi-Disease Cardiac Segmentation: The M&Ms Challenge , 2021, IEEE Transactions on Medical Imaging.

[41]  Guotai Wang,et al.  Myocardial Edema and Scar Segmentation Using a Coarse-to-Fine Framework with Weighted Ensemble , 2020, MyoPS@MICCAI.

[42]  Zhibin Liao,et al.  EfficientSeg: A Simple But Efficient Solution to Myocardial Pathology Segmentation Challenge , 2020, MyoPS@MICCAI.

[43]  M. Motwani,et al.  Relationship between myocardial edema and regional myocardial function after reperfused acute myocardial infarction: an MR imaging study. , 2013, Radiology.

[44]  Alejandro F. Frangi,et al.  Evaluation of state-of-the-art segmentation algorithms for left ventricle infarct from late Gadolinium enhancement MR images , 2016, Medical Image Anal..

[45]  Fred S Apple,et al.  Universal definition of myocardial infarction. , 2007, Journal of the American College of Cardiology.

[46]  Guido Gerig,et al.  User-guided 3D active contour segmentation of anatomical structures: Significantly improved efficiency and reliability , 2006, NeuroImage.

[47]  Xiahai Zhuang,et al.  Medical Image Analysis on Left Atrial LGE MRI for Atrial Fibrillation Studies: A Review , 2021, Medical Image Anal..

[48]  G. Wright,et al.  Evaluation Framework for Algorithms Segmenting Short Axis Cardiac MRI. , 2009, The MIDAS Journal.

[49]  Sara Moccia,et al.  Development and testing of a deep learning-based strategy for scar segmentation on CMR-LGE images , 2018, Magnetic Resonance Materials in Physics, Biology and Medicine.

[50]  Sébastien Ourselin,et al.  A Framework Combining Multi-sequence MRI for Fully Automated Quantitative Analysis of Cardiac Global And Regional Functions , 2011, FIMH.

[51]  Kumaradevan Punithakumar,et al.  Fully automated deep learning based segmentation of normal, infarcted and edema regions from multiple cardiac MRI sequences , 2020, MyoPS@MICCAI.

[52]  Yuanyuan Wang,et al.  A global benchmark of algorithms for segmenting the left atrium from late gadolinium-enhanced cardiac magnetic resonance imaging , 2020, Medical Image Anal..

[53]  M. Cerqueira,et al.  Standardized myocardial segmentation and nomenclature for tomographic imaging of the heart. A statement for healthcare professionals from the Cardiac Imaging Committee of the Council on Clinical Cardiology of the American Heart Association. , 2002, Journal of nuclear cardiology : official publication of the American Society of Nuclear Cardiology.

[54]  Taesung Park,et al.  Semantic Image Synthesis With Spatially-Adaptive Normalization , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[55]  Quoc V. Le,et al.  EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks , 2019, ICML.

[56]  Jun Ma,et al.  Cascaded Framework with Complementary CMR Information for Myocardial Pathology Segmentation , 2020, MyoPS@MICCAI.

[57]  Ronald Rousseau,et al.  Alternative area-perimeter ratios for measurement of 2D shape compactness of habitats , 2000, Appl. Math. Comput..

[58]  Daniel J. Perry,et al.  Evaluation of current algorithms for segmentation of scar tissue from late Gadolinium enhancement cardiovascular magnetic resonance of the left atrium: an open-access grand challenge , 2013, Journal of Cardiovascular Magnetic Resonance.

[59]  Sergio Escalera,et al.  Stacked BCDU-Net with Semantic CMR Synthesis: Application to Myocardial Pathology Segmentation Challenge , 2020, MyoPS@MICCAI.

[60]  Yuesong Yang,et al.  Automated quantification of myocardial infarction using graph cuts on contrast delayed enhanced magnetic resonance images. , 2012, Quantitative imaging in medicine and surgery.

[61]  Alain Lalande,et al.  Emidec: A Database Usable for the Automatic Evaluation of Myocardial Infarction from Delayed-Enhancement Cardiac MRI , 2020, Data.

[62]  Nicolas Boutry,et al.  Stacked and Parallel U-Nets with Multi-output for Myocardial Pathology Segmentation , 2020, MyoPS@MICCAI.

[63]  Weisheng Li,et al.  CMS-UNet: Cardiac Multi-task Segmentation in MRI with a U-Shaped Network , 2020, MyoPS@MICCAI.