Statistical Atlases and Computational Models of the Heart. ACDC and MMWHS Challenges

Name: Statistical Atlases and Computational Models of the Heart. ACDC and MMWHS Challenges | 8th International Workshop, STACOM 2017, Held in Conjunction with MICCAI 2017, Quebec City, Canada, September 10-14, 2017, Revised Selected Papers
Brand: Springer
Price: 53.49 EUR
Availability: OnlineOnly

8th International Workshop, STACOM 2017, Held in Conjunction with MICCAI 2017, Quebec City, Canada, September 10-14, 2017, Revised Selected Papers

Mihaela Pop Maxime Sermesant Pierre-Marc Jodoin Alain Lalande Xiahai Zhuang Guang Yang Alistair Young Olivier Bernard(Herausgeber*in)

Springer (Verlag)

Erschienen am 14. März 2018

XIII, 260 Seiten

E-Book

PDF mit Wasserzeichen-DRM

Systemvoraussetzungen

978-3-319-75541-0 (ISBN)

53,49 €inkl. 7% MwSt.

Systemvoraussetzungen

für PDF mit Wasserzeichen-DRM

E-Book Einzellizenz

Als Download verfügbar

Beschreibung

Weitere Details

Weitere Ausgaben

Inhalt

Intro
Preface
Organization
Contents
Regular Papers
Multiview Machine Learning Using an Atlas of Cardiac Cycle Motion
1 Introduction
2 Materials
3 Methods
3.1 Motion Atlas Formation
3.2 Multiview Classification
4 Experiments and Results
5 Discussion
References
Joint Myocardial Registration and Segmentation of Cardiac BOLD MRI
1 Introduction
2 Background
3 Methods
3.1 Dictionary Learning Based Image Segmentation
3.2 Graph-Based Joint Optimization
3.3 Dictionary Update
4 Experimental Results
4.1 Data Preparation and Implementation Details
4.2 Visual Evaluation
4.3 Quantitative Comparison
4.4 CAP Dataset
5 Conclusion
References
Transfer Learning for the Fully Automatic Segmentation of Left Ventricle Myocardium in Porcine Cardiac Cine MR Images
Abstract
1 Introduction
2 Method
2.1 Data Description
2.2 Image Preprocessing
2.3 CNN Architecture and Training Setup
2.4 Transfer Learning
3 Experiments and Results
4 Conclusion and Discussions
References
Left Atrial Appendage Neck Modeling for Closure Surgery
1 Introduction
2 LAA Segmentation
3 LAA Neck Modeling
3.1 Auto-Detection of the Ostium of the LAA
3.2 Establishment of the Standard Coordinate System Based on the Ostium Plane
3.3 Auto-Building of Circumscribed Cylindrical Model of LAA Neck
4 Experiments and Results
4.1 Dataset
4.2 Ground Truth
4.3 Evaluation
5 Conclusion
References
Detection of Substances in the Left Atrial Appendage by Spatiotemporal Motion Analysis Based on 4D-CT
1 Introduction
2 Method
2.1 Extraction of Optical Flow Fields of Adjacent Phase
2.2 The Tracking of Key Voxels in Whole Cardiac Cycle
2.3 Hierarchical Clustering of All Trajectory Curves
2.4 Time-Frequency Analysis of the Track Curve of Critical Lumps - to Realize the Stress and Strain Detection of Lumps
3 Experiment and Discussion
3.1 Dataset
3.2 Evaluation and Results
4 Conclusion
References
Estimation of Healthy and Fibrotic Tissue Distributions in DE-CMR Incorporating CINE-CMR in an EM Algorithm
1 Introduction
2 Methods
3 Experimental Results
4 Conclusions
References
Multilevel Non-parametric Groupwise Registration in Cardiac MRI: Application to Explanted Porcine Hearts
1 Introduction
2 Methods
2.1 Data Acquisition
2.2 Pairwise Registration of the Anatomical MR Images
3 Groupwise Registration
4 Results
5 Future Work and Conclusions
References
ACDC Challenge
GridNet with Automatic Shape Prior Registration for Automatic MRI Cardiac Segmentation
1 Introduction
2 Our Method
2.1 Shape Prior
2.2 Loss
2.3 Proposed Network
3 Experimental Setup and Results
3.1 Dataset, Evaluation Criteria, and Other Methods
3.2 Experimental Results
4 Conclusion
References
A Radiomics Approach to Computer-Aided Diagnosis with Cardiac Cine-MRI
1 Introduction
2 Method
2.1 Data Description
2.2 Semi-automatic Segmentation
2.3 Radiomics Features for Cardiac Diagnosis
2.4 Classification Method
2.5 Radiomic Feature Selection
3 Results
4 Conclusions
References
Fast Fully-Automatic Cardiac Segmentation in MRI Using MRF Model Optimization, Substructures Tracking and B-Spline Smoothing
1 Introduction
2 Automatic Localization of the Heart
3 Segmentation of an ED Phase Slice in Between Base and Mid-Ventricle
4 Segmentation Based on Tracking the Cardiac Substructures in ED Phase
5 Segmentation in the ES Phase
6 Left Ventricle Epicardial Boundary Smoothing
7 Global Results and First Conclusions
References
Automatic Segmentation and Disease Classification Using Cardiac Cine MR Images
1 Introduction
2 Data
3 Methods
3.1 Segmentation
3.2 Diagnosis
4 Experiments and Results
4.1 Segmentation Results
4.2 Diagnosis Results
5 Discussion and Conclusion
References
An Exploration of 2D and 3D Deep Learning Techniques for Cardiac MR Image Segmentation
1 Introduction
2 Method
2.1 Pre-Processing
2.2 Network Architectures
2.3 Optimisation
2.4 Post-Processing
3 Experiments and Results
3.1 Data
3.2 Evaluation Measures
3.3 Experiment 1: Comparison of Loss Functions
3.4 Experiment 2: Comparison of Network Architectures
3.5 Discussion and Conclusion
References
Automatic Cardiac Disease Assessment on cine-MRI via Time-Series Segmentation and Domain Specific Features
1 Introduction
2 Methods
2.1 Cardiac cine-MRI Dataset
2.2 Segmentation
2.3 Cardiac Disease Classification
3 Results
4 Discussion
References
2D-3D Fully Convolutional Neural Networks for Cardiac MR Segmentation
1 Introduction
2 Method
2.1 Network Architecture
2.2 Dataset, Preprocessing and Augmentation
2.3 Training
2.4 Optimization Function
3 Results
4 Discussion
5 Conclusion
References
Densely Connected Fully Convolutional Network for Short-Axis Cardiac Cine MR Image Segmentation and Heart Diagnosis Using Random Forest
1 Introduction and Related Work
2 Our Method
2.1 Data Pre-processing Pipeline
2.2 Proposed Network Architecture: Densely Connected Fully Convolutional Network (DFCN)
2.3 Loss Function
2.4 Post-processing
2.5 Cardiac Disease Diagnosis
3 Experimental Setup and Results
3.1 Dataset and Evaluation Criteria
3.2 Experimental Results
3.3 Conclusion
References
Class-Balanced Deep Neural Network for Automatic Ventricular Structure Segmentation
1 Introduction
2 Methodology
2.1 Efficient Semantic Labeling with 3D FCN
2.2 Transfer Learning from C3D Model
2.3 Promote Training with Deep Supervision
2.4 Investigation of Class-Balanced Loss
3 Experimental Results
4 Conclusions
References
Automatic Segmentation of LV and RV in Cardiac MRI
Abstract
1 Introduction
2 Methods
2.1 Dataset
2.2 Preprocessing
2.3 Architecture
3 Experimental Results
3.1 Implemented Details
3.2 Results and Quantitative Analysis with Other Methods
4 Conclusion and Discussion
Acknowledgement
References
Automatic Multi-Atlas Segmentation of Myocardium with SVF-Net
1 Introduction
2 Rigid Alignment by Landmarks Detection
3 Non-rigid Diffeomorphic Registration with SVF-Net
4 Label Fusion Method
5 Results and Discussion
6 Conclusion
References
MM-WHS Challenge
3D Convolutional Networks for Fully Automatic Fine-Grained Whole Heart Partition
1 Introduction
2 Methodology
2.1 Dense Semantic Labeling with 3D FCN
2.2 Knowledge Transfer from C3D Model
2.3 Promote Training with Deep Supervision
2.4 Multi-class Balanced Loss Function
3 Experimental Results
4 Conclusions
References
Multi-label Whole Heart Segmentation Using CNNs and Anatomical Label Configurations
1 Introduction
2 Method
3 Experimental Setup
4 Results and Discussion
5 Conclusion
References
Multi-Planar Deep Segmentation Networks for Cardiac Substructures from MRI and CT
1 Introduction
2 Multi-Object Multi-Planar CNN (MO-MP-CNN)
3 Experimental Results
4 Discussion and Conclusion
References
Local Probabilistic Atlases and a Posteriori Correction for the Segmentation of Heart Images
1 Introduction
2 Methods
2.1 Construction of the a Priori Information
2.2 Segmentation
2.3 A Posteriori Correction
3 Experiments
4 Results
5 Conclusion
References
Hybrid Loss Guided Convolutional Networks for Whole Heart Parsing
1 Introduction
2 Methodology
2.1 Intensity Calibration as Preprocessing
2.2 Enhance the Training of 3D FCN
2.3 Hybrid Loss Guided Class-Balanced Segmentation
3 Experimental Results
4 Conclusions
References
3D Deeply-Supervised U-Net Based Whole Heart Segmentation
1 Introduction
2 Method
2.1 Data Pre-processing
2.2 Network Architecture
3 Experiments and Results
3.1 Data
3.2 Performance on Training Set
3.3 Performance on Testing Set
4 Discussion and Conclusion
References
MRI Whole Heart Segmentation Using Discrete Nonlinear Registration and Fast Non-local Fusion
1 Introduction and Related Work
2 Discrete Registration
3 Non-local Label Fusion
4 Multi-label Random Walk Regularisation
5 Discussion and Conclusion
References
Automatic Whole Heart Segmentation Using Deep Learning and Shape Context
1 Introduction
2 Methods
2.1 2.5D Segmentation Using Orthogonal U-Nets
2.2 Shape Context Generation
2.3 Shape-Context Guided U-Net
2.4 Implementation Details
3 Results
4 Discussion and Conclusion
References
Automatic Whole Heart Segmentation in CT Images Based on Multi-atlas Image Registration
Abstract
1 Introduction
2 Methodology
2.1 A Three-Step Multi-atlas-Based Whole Heart Segmentation
2.2 Multiple Atlas Images
3 Experimental Results
4 Conclusion
References
Author Index

Systemvoraussetzungen

Als PDF speichern Als Link merken