Functional Imaging and Modeling of the Heart 11th International Conference, FIMH 2021, Stanford, CA, USA, June 21-25, 2021, Proceedings

• Main Authors: Ennis, Daniel B, Perotti, Luigi E, Wang, Vicky Y
• Format: eBook
• Language: English
• Published: Netherlands Springer Nature 2021; Springer International Publishing AG; Springer International Publishing
• Edition: 1
• Series: Lecture Notes in Computer Science
• Subjects: Computer programming, programs, data; Machine learning; Optical data processing
• ISBN: 3030787109; 9783030787103; 9783030787097; 3030787095

This book constitutes the refereed proceedings of the 11th International Conference on Functional Imaging and Modeling of the Heart, which took place online during June 21-24, 2021, organized by the University of Stanford. The 65 revised full papers were carefully reviewed and selected from 68 submi...

Table of Contents:

• 3.2 The Sheetlet Angle Measured Using the Fourier-Based Method -- 3.3 Angle : Comparison Between the Skeleton and Fourier-Based Methods -- 4 Results -- 5 Discussion -- 6 Conclusion -- References -- A High-Fidelity 3D Micromechanical Model of Ventricular Myocardium -- 1 Introduction -- 2 Methods -- 2.1 Finite Element Mesh Construction -- 2.2 Constitutive Modeling -- 2.3 FE Simulations -- 3 Results -- 4 Discussion -- References -- Quantitative Interpretation of Myocardial Fiber Structure in the Left and Right Ventricle of an Equine Heart Using Diffusion Tensor Cardiovascular Magnetic Resonance Imaging -- 1 Introduction -- 2 Method -- 2.1 MRI Protocol -- 2.2 Processing -- 2.3 Helix Angle Calculation -- 2.4 Analysis -- 3 Results -- 4 Discussion -- References -- Analysis of Location-Dependent Cardiomyocyte Branching -- 1 Introduction -- 1.1 Definition of Terms -- 2 Methods -- 2.1 Extended Volume Confocal Microscopy -- 2.2 Cardiomyocyte Network Analysis -- 3 Results -- 4 Discussion -- 4.1 Physiological Significance -- 4.2 Cardiomyocyte Branching and Myocardial Deformation -- 4.3 Growth and Remodeling -- 4.4 Limitations -- 5 Conclusion -- References -- Systematic Study of Joint Influence of Angular Resolution and Noise in Cardiac Diffusion Tensor Imaging -- 1 Introduction -- 2 Materials and Methods -- 2.1 Simulated Datasets -- 2.2 Real Datasets -- 2.3 Gradient Direction Sampling -- 2.4 Evaluation -- 3 Results -- 3.1 Results on Simulated Data -- 3.2 Results on Real Data -- 4 Conclusions and Discussions -- References -- Novel Approaches to Measuring Heart Deformation -- Arbitrary Point Tracking with Machine Learning to Measure Cardiac Strains in Tagged MRI -- 1 Introduction -- 2 Methods -- 2.1 Tag Tracking -- 2.2 Strain Calculation -- 2.3 Computational Deforming Cardiac Phantom -- 2.4 In Vivo Data -- 3 Results -- 4 Discussion -- References
• 2.3 Multiscale Spatio-Temporal Graph Convolutional Neural Network
• 2.3 Accuracy Estimation -- 3 Results -- 4 Discussion and Conclusions -- References -- Efficient Model Monitoring for Quality Control in Cardiac Image Segmentation -- 1 Introduction -- 2 Method -- 3 Experiments and Results -- 3.1 Experimental Setup -- 3.2 Results -- 4 Discussion and Conclusions -- References -- Domain Adaptation for Automatic Aorta Segmentation of 4D Flow Magnetic Resonance Imaging Data from Multiple Vendor Scanners -- 1 Introduction -- 2 Materials and Methods -- 2.1 Population Datasets -- 2.2 nn-Unet Architecture and Experimental Setup -- 2.3 Domain Adaptation -- 2.4 Post-processing -- 2.5 Experiments -- 3 Results -- 4 Discussion -- 5 Conclusions -- References -- A Multi-step Machine Learning Approach for Short Axis MR Images Segmentation -- 1 Introduction -- 2 Method -- 2.1 Imaging Data -- 2.2 Image Preprocessing -- 2.3 Convolutional Neural Networks -- 2.4 Training -- 2.5 Weighted Average and Image Correction -- 2.6 Spline Interpolation and LV Surface Generation -- 3 Results -- 4 Discussion -- References -- Cardiac Microstructure: Measures and Models -- Diffusion Biomarkers in Chronic Myocardial Infarction -- 1 Introduction -- 2 Methods -- 2.1 Experimental and Imaging Procedures -- 2.2 Diffusion Tensor Reconstruction and Image Labeling -- 2.3 Data Analysis -- 3 Results -- 4 Discussion -- References -- Spatially Constrained Deep Learning Approach for Myocardial T1 Mapping -- 1 Introduction -- 2 Methods -- 2.1 Dataset -- 2.2 Identification of Myocardial Tissue for Training -- 2.3 Spatially Constrained Deep Learning T1 Mapping -- 3 Results -- 4 Discussion -- 5 Conclusions -- References -- A Methodology for Accessing the Local Arrangement of the Sheetlets that Make up the Extracellular Heart Tissue -- 1 Introduction -- 2 Material -- 3 Data Processing Strategy -- 3.1 The Sheetlet Angle Measured Using the Skeleton Method
• Investigation of the Impact of Normalization on the Study of Interactions Between Myocardial Shape and Deformation -- 1 Introduction -- 2 Methods -- 2.1 Data and Descriptors -- 2.2 Manifold Learning -- 3 Experiments and Results -- 3.1 Shape Descriptors -- 3.2 Deformation Descriptors -- 4 Discussion and Conclusion -- References -- Reproducibility of Left Ventricular CINE DENSE Strain in Pediatric Subjects with Duchenne Muscular Dystrophy -- 1 Introduction -- 2 Methods -- 2.1 Study Enrollment -- 2.2 MR Imaging and Post-processing -- 2.3 Reproducibility and Statistics -- 3 Results -- 3.1 Global and Regional Ecc -- 3.2 Intra-observer Repeatability -- 3.3 Intra-exam Reproducibility -- 3.4 Inter-observer Reproducibility -- 4 Discussion -- 5 Conclusion -- References -- M-SiSSR: Regional Endocardial Function Using Multilabel Simultaneous Subdivision Surface Registration -- 1 Introduction -- 2 Methods -- 2.1 Dataset and Annotation -- 2.2 Left Heart Segmentation -- 2.3 Boundary Candidate Selection -- 2.4 Mesh Model Generation -- 2.5 Subdivision Surface Evaluation -- 2.6 Multilabel SiSSR (M-SiSSR) -- 2.7 Implementation -- 3 Results -- 3.1 CNN Segmentation -- 3.2 Template Mesh Generation -- 3.3 Determining Scaling Factors -- 3.4 Comparison to Label-Agnostic Approach: M-SiSSR vs SiSSR -- 4 Discussion -- References -- CNN-Based Cardiac Motion Extraction to Generate Deformable Geometric Left Ventricle Myocardial Models from Cine MRI -- 1 Introduction -- 2 Methodology -- 2.1 Cardiac MRI Data -- 2.2 Image Preprocessing -- 2.3 Deformable Image Registration -- 2.4 Mesh Generation and Propagation -- 3 Results and Discussion -- 4 Conclusion -- References -- Multiscale Graph Convolutional Networks for Cardiac Motion Analysis -- 1 Introduction -- 2 Method -- 2.1 Multiscale Cardiac Graph Construction -- 2.2 Multiscale Graph Computation Unit (MGCU)
• Intro -- Preface -- Organization -- Contents -- Advanced Cardiac and Cardiovascular Image Processing -- Population-Based Personalization of Geometric Models of Myocardial Infarction -- 1 Introduction -- 2 Methods -- 2.1 Data and Pre-processing -- 2.2 Geometric Models of Myocardial Infarction -- 2.3 Personalization of the Models -- 3 Experiments and Results -- 3.1 CMA-ES Parameters and Convergence -- 3.2 Distribution of the Synthetic and Real Populations -- 4 Discussion -- References -- Impact of Image Resolution and Resampling on Motion Tracking of the Left Chambers from Cardiac Scans -- 1 Introduction -- 2 Methods -- 2.1 Clinical Data -- 2.2 Preprocessing Data -- 2.3 Resampling Data -- 2.4 Endocardium Motion Estimation -- 2.5 Calculation of Strain on Endocardium -- 2.6 Analysis of Motion Tracking Error -- 3 Results -- 3.1 Impact of Spatial Resolution on Short Axis Reconstruction -- 3.2 Impact of Spatial Resolution on Long Axis Reconstruction -- 3.3 Discussion -- 3.4 Limitations -- 4 Conclusion -- References -- Shape Constraints in Deep Learning for Robust 2D Echocardiography Analysis -- 1 Introduction -- 2 Methods -- 2.1 SEG-LM: Parallel Segmentation and Landmark Detection -- 2.2 SEG-AFFINE: Poly-affine Regulariser for Myocardium -- 2.3 SEG-CONTOUR: Multi-class Contour-Loss -- 3 Experiments and Results -- 3.1 Datasets -- 3.2 Experiments -- 3.3 Evaluation Metrics -- 3.4 Results -- 4 Conclusion -- References -- Image-Derived Geometric Characteristics Predict Abdominal Aortic Aneurysm Growth in a Machine Learning Model -- 1 Introduction -- 2 Methods -- 2.1 Data Generation and Pre-processing -- 2.2 Image-Derived Geometric Parameter Calculations -- 2.3 Image-Derived Predictors and Outcome Calculations -- 2.4 Machine Learning Model Selection -- 2.5 Tuning of the Machine Learning Model -- 2.6 Assessment of Machine Learning Model Performance
• 3 Results -- 4 Discussion and Future Direction -- References -- Cardiac MRI Left Ventricular Segmentation and Function Quantification Using Pre-trained Neural Networks -- 1 Introduction -- 2 Materials and Methods -- 2.1 Cardiac MRI Datasets -- 2.2 Algorithm Pipeline -- 2.3 Evaluation Methods -- 2.4 Statistical Analysis -- 3 Results -- 4 Discussion -- References -- Three-Dimensional Embedded Attentive RNN (3D-EAR) Segmentor for Left Ventricle Delineation from Myocardial Velocity Mapping -- 1 Introduction -- 2 Method -- 2.1 Data Acquisition, Preprocessing and Augmentation -- 2.2 Network Architectures -- 2.3 Loss Functions -- 2.4 Implementation Details -- 3 Results -- 3.1 Experiments and Evaluation Metrics -- 3.2 Quantitative Results -- 4 Discussion and Conclusion -- References -- Whole Heart Anatomical Refinement from CCTA Using Extrapolation and Parcellation -- 1 Introduction -- 2 Methods -- 2.1 Data -- 2.2 Image-to-Label Initial Segmentation -- 2.3 Label Processing -- 2.4 Label to Label Networks -- 2.5 Image to Label Refinement -- 3 Results -- 3.1 Image to Label Initial Segmentation -- 3.2 Label to Label Refinement -- 3.3 Image to Label Final Segmentation -- 4 Conclusions and Limitations -- References -- Optimisation of Left Atrial Feature Tracking Using Retrospective Gated Computed Tomography Images -- 1 Introduction -- 2 Methods -- 3 Results -- 4 Discussion -- 5 Limitations and Future Work -- 6 Conclusion -- References -- Assessment of Geometric Models for the Approximation of Aorta Cross-Sections -- 1 Introduction -- 2 Materials and Methods -- 2.1 Clinical Data -- 2.2 Cross-Section Models -- 2.3 Error Measurement -- 3 Results -- 3.1 Slice Fitting Error Distribution -- 4 Conclusion -- References -- Improved High Frame Rate Speckle Tracking for Echocardiography -- 1 Introduction -- 2 Methods -- 2.1 Simulation Setup -- 2.2 2-D Motion Estimator