Machine Learning Approaches for Myocardial Motion and Deformation Analysis

Information about myocardial motion and deformation is key to differentiate normal and abnormal conditions. With the advent of approaches relying on data rather than pre-conceived models, machine learning could either improve the robustness of motion quantification or reveal patterns of motion and deformation (rather than single parameters) that differentiate pathologies. We review machine learning strategies for extracting motion-related descriptors and analyzing such features among populations, keeping in mind constraints specific to the cardiac application.

[1]  Daniel Rueckert,et al.  Fast Spatio-temporal Free-Form Registration of Cardiac MR Image Sequences , 2004, FIMH.

[2]  Daniel Rueckert,et al.  Joint Learning of Motion Estimation and Segmentation for Cardiac MR Image Sequences , 2018, MICCAI.

[3]  Alejandro F. Frangi,et al.  Bilinear Models for Spatio-Temporal Point Distribution Analysis: Application to Extrapolation of Whole Heart Cardiac Dynamics , 2007, ICCV.

[4]  Erik Smistad,et al.  Automatic Myocardial Strain Imaging in Echocardiography Using Deep Learning , 2018, DLMIA/ML-CDS@MICCAI.

[5]  Daniel Rueckert,et al.  Temporal sparse free-form deformations , 2013, Medical Image Anal..

[6]  J. Dudley,et al.  Machine-Learning Algorithms to Automate Morphological and Functional Assessments in 2D Echocardiography. , 2016, Journal of the American College of Cardiology.

[7]  Alejandro F. Frangi,et al.  Automatic Assessment of Full Left Ventricular Coverage in Cardiac Cine Magnetic Resonance Imaging With Fisher-Discriminative 3-D CNN , 2018, IEEE Transactions on Biomedical Engineering.

[8]  Alejandro F. Frangi,et al.  Quantitative CMR population imaging on 20, 000 subjects of the UK Biobank imaging study: LV/RV quantification pipeline and its evaluation , 2019, Medical Image Anal..

[9]  Stephen Lin,et al.  Graph Embedding and Extensions: A General Framework for Dimensionality Reduction , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Maja Cikes,et al.  Velocity and deformation imaging for the assessment of myocardial dysfunction. , 2008, European journal of echocardiography : the journal of the Working Group on Echocardiography of the European Society of Cardiology.

[11]  Alejandro F. Frangi,et al.  Large Diffeomorphic FFD Registration for Motion and Strain Quantification from 3D-US Sequences , 2009, FIMH.

[12]  Wufeng Xue,et al.  Full left ventricle quantification via deep multitask relationships learning , 2018, Medical Image Anal..

[13]  Wenjia Bai,et al.  Fully Automated, Quality-Controlled Cardiac Analysis From CMR: Validation and Large-Scale Application to Characterize Cardiac Function , 2019, JACC. Cardiovascular imaging.

[14]  Nicolas Duchateau,et al.  Machine Learning Analysis of Left Ventricular Function to Characterize Heart Failure With Preserved Ejection Fraction , 2018, Circulation. Cardiovascular imaging.

[15]  Hervé Delingette,et al.  International Journal of Computer Vision Manuscript No. 10.1007/s11263-010-0405-z The final publication is available at www.springerlink.com iLogDemons: A Demons-Based Registration Algorithm for Tracking Incompressible Elastic Biological Tissues , 2022 .

[16]  Daniel Rueckert,et al.  A framework for combining a motion atlas with non‐motion information to learn clinically useful biomarkers: Application to cardiac resynchronisation therapy response prediction , 2017, Medical Image Anal..

[17]  Alistair A. Young,et al.  The Cardiac Atlas Project—an imaging database for computational modeling and statistical atlases of the heart , 2011, Bioinform..

[18]  Xavier Pennec,et al.  Intrinsic Statistics on Riemannian Manifolds: Basic Tools for Geometric Measurements , 2006, Journal of Mathematical Imaging and Vision.

[19]  Thomas Brox,et al.  FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[20]  Julia A. Schnabel,et al.  Regional Multi-View Learning for Cardiac Motion Analysis: Application to Identification of Dilated Cardiomyopathy Patients , 2019, IEEE Transactions on Biomedical Engineering.

[21]  Daniel Rueckert,et al.  Learning Interpretable Anatomical Features Through Deep Generative Models: Application to Cardiac Remodeling , 2018, MICCAI.

[22]  Maxime Sermesant,et al.  Cardiac Motion Evolution Model for Analysis of Functional Changes Using Tensor Decomposition and Cross-Sectional Data , 2018, IEEE Transactions on Biomedical Engineering.

[23]  Bruce R. Rosen,et al.  Implementation and Validation of a Three-dimensional Cardiac Motion Estimation Network. , 2019, Radiology. Artificial intelligence.

[24]  Nicolas Le Roux,et al.  Out-of-Sample Extensions for LLE, Isomap, MDS, Eigenmaps, and Spectral Clustering , 2003, NIPS.

[25]  Hervé Delingette,et al.  Myocardial Infarct Localization Using Neighbourhood Approximation Forests , 2015, STACOM@MICCAI.

[26]  Nicholas Ayache,et al.  A Log-Euclidean Framework for Statistics on Diffeomorphisms , 2006, MICCAI.

[27]  Jean-Yves Tourneret,et al.  Motion Estimation in Echocardiography Using Sparse Representation and Dictionary Learning , 2018, IEEE Transactions on Image Processing.

[28]  P Suetens,et al.  Regional strain and strain rate measurements by cardiac ultrasound: principles, implementation and limitations. , 2000, European journal of echocardiography : the journal of the Working Group on Echocardiography of the European Society of Cardiology.

[29]  Martino Alessandrini,et al.  Machine learning of the spatio-temporal characteristics of echocardiographic deformation curves for infarct classification , 2017, The International Journal of Cardiovascular Imaging.

[30]  Jan D'hooge,et al.  Diagnosis of Heart Failure With Preserved Ejection Fraction: Machine Learning of Spatiotemporal Variations in Left Ventricular Deformation , 2018, Journal of the American Society of Echocardiography : official publication of the American Society of Echocardiography.

[31]  Paolo Emilio Puddu,et al.  Morphologically normalized left ventricular motion indicators from MRI feature tracking characterize myocardial infarction , 2017, Scientific Reports.

[32]  Maxime Sermesant,et al.  Low‐dimensional representation of cardiac motion using Barycentric Subspaces: A new group‐wise paradigm for estimation, analysis, and reconstruction , 2018, Medical Image Anal..

[33]  Maja Cikes,et al.  Beyond ejection fraction: an integrative approach for assessment of cardiac structure and function in heart failure. , 2016, European heart journal.

[34]  Caroline Petitjean,et al.  A review of segmentation methods in short axis cardiac MR images , 2011, Medical Image Anal..

[35]  Nicolas Duchateau,et al.  Which Reorientation Framework for the Atlas-Based Comparison of Motion from Cardiac Image Sequences? , 2012, STIA.

[36]  Pingkun Yan,et al.  Deep learning in medical image registration: a survey , 2020, Machine Vision and Applications.

[37]  René M. Botnar,et al.  Automatic CNN-based detection of cardiac MR motion artefacts using k-space data augmentation and curriculum learning , 2018, Medical Image Anal..

[38]  Hervé Delingette,et al.  Registration of 4D Cardiac CT Sequences Under Trajectory Constraints With Multichannel Diffeomorphic Demons , 2010, IEEE Transactions on Medical Imaging.

[39]  Alejandro F. Frangi,et al.  SPM to the heart: Mapping of 4D continuous velocities for motion abnormality quantification , 2012, 2012 9th IEEE International Symposium on Biomedical Imaging (ISBI).

[40]  Maxime Sermesant,et al.  Symmetric Algorithmic Components for Shape Analysis with Diffeomorphisms , 2019, GSI.

[41]  Yongyi Yang,et al.  Numerical observer for cardiac motion assessment using machine learning , 2011, Medical Imaging.

[42]  Damien Garcia,et al.  Back to Basics in Ultrasound Velocimetry: Tracking Speckles by Using a Standard Piv Algorithm , 2018, 2018 IEEE International Ultrasonics Symposium (IUS).

[43]  Alejandro F. Frangi,et al.  Constrained manifold learning for the characterization of pathological deviations from normality , 2012, Medical Image Anal..

[44]  Alejandro F. Frangi,et al.  A spatiotemporal statistical atlas of motion for the quantification of abnormal myocardial tissue velocities , 2011, Medical Image Anal..

[45]  Daniel Rueckert,et al.  Spatial transformation of motion and deformation fields using nonrigid registration , 2004, IEEE Transactions on Medical Imaging.

[46]  Ilkay Öksüz,et al.  Global and Local Interpretability for Cardiac MRI Classification , 2019, MICCAI.

[47]  Bob D. de Vos,et al.  State-of-the-Art Deep Learning in Cardiovascular Image Analysis. , 2019, JACC. Cardiovascular imaging.

[48]  Maxime Sermesant,et al.  An Incompressible Log-Domain Demons Algorithm for Tracking Heart Tissue , 2011, STACOM.

[49]  Olivier Bernard,et al.  Cardiac MRI Segmentation with Strong Anatomical Guarantees , 2019, MICCAI.

[50]  Nicolas Duchateau,et al.  Machine learning‐based phenogrouping in heart failure to identify responders to cardiac resynchronization therapy , 2018, European journal of heart failure.

[51]  Daniel Rueckert,et al.  Assessing the Impact of Blood Pressure on Cardiac Function Using Interpretable Biomarkers and Variational Autoencoders , 2019, STACOM@MICCAI.

[52]  Milan Sonka,et al.  Automatic segmentation of echocardiographic sequences by active appearance motion models , 2002, IEEE Transactions on Medical Imaging.

[53]  Maxime Sermesant,et al.  Spatio-Temporal Tensor Decomposition of a Polyaffine Motion Model for a Better Analysis of Pathological Left Ventricular Dynamics , 2015, IEEE Transactions on Medical Imaging.

[54]  Jean-Jacques Bellanger,et al.  Machine Learning Techniques for LV Wall Motion Classification Based on Spatio-temporal Profiles from Cardiac Cine MRI , 2013, 2013 12th International Conference on Machine Learning and Applications.

[55]  Daniel Rueckert,et al.  Towards Left Ventricular Scar Localisation Using Local Motion Descriptors , 2015, STACOM@MICCAI.

[56]  Daniel Rueckert,et al.  Machine Learning of Three-dimensional Right Ventricular Motion Enables Outcome Prediction in Pulmonary Hypertension: A Cardiac MR Imaging Study , 2017, Radiology.

[57]  Alistair A. Young,et al.  Atlas-Based Quantification of Cardiac Remodeling Due to Myocardial Infarction , 2014, PloS one.

[58]  Alejandro F. Frangi,et al.  Statistical Shape Modeling of the Left Ventricle: Myocardial Infarct Classification Challenge , 2018, IEEE Journal of Biomedical and Health Informatics.

[59]  Daniel Rueckert,et al.  A bi-ventricular cardiac atlas built from 1000+ high resolution MR images of healthy subjects and an analysis of shape and motion , 2015, Medical Image Anal..

[60]  Nicolas Duchateau,et al.  Infarct localization from myocardial deformation: Prediction and uncertainty quantification by regression from a low-dimensional space. , 2016, IEEE transactions on medical imaging.

[61]  Nicolas Duchateau,et al.  Characterization of myocardial motion patterns by unsupervised multiple kernel learning , 2017, Medical Image Anal..

[62]  Nicolas Duchateau,et al.  Learning Interactions Between Cardiac Shape and Deformation: Application to Pulmonary Hypertension , 2019, STACOM@MICCAI.

[63]  Alejandro F. Frangi,et al.  Bilinear Models for Spatio-Temporal Point Distribution Analysis , 2009, 2007 IEEE 11th International Conference on Computer Vision.

[64]  Akihiro Haga,et al.  A Deep Learning Approach for Assessment of Regional Wall Motion Abnormality From Echocardiographic Images. , 2020, JACC. Cardiovascular imaging.

[65]  Alejandro F. Frangi,et al.  Temporal diffeomorphic free-form deformation: Application to motion and strain estimation from 3D echocardiography , 2012, Medical Image Anal..

[66]  P. Claus,et al.  Two-dimensional speckle tracking echocardiography: standardization efforts based on synthetic ultrasound data. , 2016, European heart journal cardiovascular Imaging.

[67]  Xiantong Zhen,et al.  Multi-scale deep networks and regression forests for direct bi-ventricular volume estimation , 2016, Medical Image Anal..

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

[69]  Nicolas Duchateau,et al.  Quantification of local changes in myocardial motion by diffeomorphic registration via currents: Application to paced hypertrophic obstructive cardiomyopathy in 2D echocardiographic sequences , 2015, Medical Image Anal..

[70]  Henggui Zhang,et al.  Multi-Views Fusion CNN for Left Ventricular Volumes Estimation on Cardiac MR Images , 2018, IEEE Transactions on Biomedical Engineering.

[71]  Mathieu De Craene,et al.  Analysis of nonstandardized stress echocardiography sequences using multiview dimensionality reduction , 2019, Medical Image Anal..

[72]  Hervé Delingette,et al.  Learning a Probabilistic Model for Diffeomorphic Registration , 2018, IEEE Transactions on Medical Imaging.

[73]  Gongning Luo,et al.  Commensal correlation network between segmentation and direct area estimation for bi-ventricle quantification , 2019, Medical Image Anal..

[74]  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.

[75]  Jean-Jacques Bellanger,et al.  Classification of LV wall motion in cardiac MRI using kernel Dictionary Learning with a parametric approach , 2015, 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[76]  Nicolas Duchateau,et al.  Parallel Transport of Surface Deformations from Pole Ladder to Symmetrical Extension , 2018, ShapeMI@MICCAI.

[77]  Daniel Rueckert,et al.  Deep learning cardiac motion analysis for human survival prediction , 2018, Nature Machine Intelligence.

[78]  Jeroen Hermans,et al.  Anatomical Image Registration Using Volume Conservation to Assess Cardiac Deformation From 3D Ultrasound Recordings , 2016, IEEE Transactions on Medical Imaging.

[79]  Paul Aljabar,et al.  A multimodal spatiotemporal cardiac motion atlas from MR and ultrasound data , 2017, Medical Image Anal..

[80]  Konstantinos Kamnitsas,et al.  Anatomically Constrained Neural Networks (ACNNs): Application to Cardiac Image Enhancement and Segmentation , 2017, IEEE Transactions on Medical Imaging.

[81]  Cathie Sudlow,et al.  UK Biobank: opportunities for cardiovascular research , 2017, European heart journal.

[82]  Hervé Delingette,et al.  Explainable cardiac pathology classification on cine MRI with motion characterization by semi-supervised learning of apparent flow , 2018, Medical Image Anal..

[83]  Françoise J. Prêteux,et al.  Building and using a statistical 3D motion atlas for analyzing myocardial contraction in MRI , 2004, SPIE Medical Imaging.

[84]  Carlos Guestrin,et al.  "Why Should I Trust You?": Explaining the Predictions of Any Classifier , 2016, ArXiv.

[85]  M. Cikes,et al.  Myocardial Motion and Deformation: What Does It Tell Us and How Does It Relate to Function? , 2012, Fetal Diagnosis and Therapy.

[86]  Mathieu De Craene,et al.  Learning associations between clinical information and motion-based descriptors using a large scale MR-derived cardiac motion atlas , 2018, STACOM@MICCAI.

[87]  Nicholas Ayache,et al.  Fine-tuned convolutional neural nets for cardiac MRI acquisition plane recognition , 2017, Comput. methods Biomech. Biomed. Eng. Imaging Vis..

[88]  Bjørn Olav Haugen,et al.  Real-Time Standard View Classification in Transthoracic Echocardiography Using Convolutional Neural Networks. , 2019, Ultrasound in medicine & biology.

[89]  Hervé Delingette,et al.  Detailed Evaluation of Five 3D Speckle Tracking Algorithms Using Synthetic Echocardiographic Recordings , 2016, IEEE Transactions on Medical Imaging.

[90]  Yuanyuan Wang,et al.  Cine MRI analysis by deep learning of optical flow: Adding the temporal dimension , 2019, Comput. Biol. Medicine.

[91]  B. Gerber,et al.  Myocardial strain imaging: review of general principles, validation, and sources of discrepancies , 2019, European heart journal cardiovascular Imaging.