Cardiovascular imaging and image analysis

Description

This will be a comprehensive multi-contributed reference work that will detail the latest developments in spatial, temporal, and functional cardiac imaging. It will include several prominent imaging modalities such as MRI, CT, and PET technologies. There will be special emphasis placed on automated imaging analysis techniques, which are important to biomedical imaging analysis of the cardiovascular system. Novel 4D based approach will be a unique characteristic of this product--  Read more... Abstract: This will be a comprehensive multi-contributed reference work that will detail the latest developments in spatial, temporal, and functional cardiac imaging. It will include several prominent imaging modalities such as MRI, CT, and PET technologies. There will be special emphasis placed on automated imaging analysis techniques, which are important to biomedical imaging analysis of the cardiovascular system. Novel 4D based approach will be a unique characteristic of this product Content: Cover Half Title Title Page Copyright Page Dedication Contents Preface Acknowledgments About the Editors Contributors Chapter 1: Detection of Cerebrovascular Changes Using Magnetic Resonance Angiography Contents 1.1. Introduction 1.2. Methods 1.2.1. Patient Demographics 1.2.2. Data Analysis 1.2.2.1. Manual Segmentation of Training Slices 1.2.2.2. Automatic Segmentation 1.2.2.3. Voxel Matching 1.2.2.4. Generation of Probability Distribution Function and Validation 1.2.2.5. Calculation of Cumulative Distribution Function 1.2.3. Statistical Analysis 1.2.4. 3D Reconstruction of the Cerebral Vasculature1.3. Results 1.4. Discussion 1.5. Limitations 1.6. Conclusion Appendices A. Initialization Sequentially Using EM Algorithm B. Refining LCDGs using Modified EM Algorithm References Chapter 2: Segmentation of Blood Vessels Using Magnetic Resonance Angiography Images Contents 2.1. Introduction 2.2. Probability Model of Vascular Signals 2.3. Adaptive Model of Multi-Modal MRA 2.4. Segmentation of Blood Vessels 2.5. Validation 2.6. Conclusion References Chapter 3: Vascular Tree Segmentation from Different Image Modalities 3.1. Introduction 3.2. Surface Modelling by Level Sets 3.3. Statistical Gray Level Distribution Model 3.3.1. Modified EM Algorithm for LCGs 3.3.2. Sequential EM-Based Initialization 3.3.3. Classification of the Model Components 3.4. Evolutionary Surface Model 3.4.1. PDE System 3.4.2. Data Consistency Coefficient hi(I) 3.5. Evaluation of the Segmentation Approach 3.6. Experimental Results 3.6.1. Separation of Blood Vessels in MRA-TOF Images 3.6.2. Extraction of Blood Vessels from Phase Contrast Images 3.6.3. Extraction of the Aorta from CTA Images 3.7. Conclusion and Future ResearchReferences Chapter 4: Accurate Unsupervised 3D Segmentation of Blood Vessels Using Magnetic Resonance Angiography Contents 4.1. Introduction 4.2. Slice-Wise Segmentation with the LCDG Models 4.3. Experimental Results 4.3.1. Segmentation of Natural TOF -- and PC-MRA Images 4.3.2. Validating the Segmentation Accuracywith Special Phantoms 4.4. Conclusion Appendices A. Sequential EM-based initialization B. Modified EM algorithm for refining LCDGs References Chapter 5: An Unsupervised Parametric Mixture Model for Automatic Cerebrovascular Segmentation 5.1. Introduction 5.2. Magnetic Resonance Imaging 5.3. Cerebrovascular Segmentation Using Magnetic Resonance Imaging 5.3.1. Related Work on Cerebrovascular Segmentation 5.3.2. Proposed Work 5.3.3. Experimental Results 5.4. Conclusion References Chapter 6: Left Atrial Scarring Segmentation from Delayed-Enhancement Cardiac MRI Images: A Deep Learning Approach Contents 6.1. Introduction 6.1.1. Background 6.1.2. Related Work 6.1.3. Our Contributions 6.2. Method 6.2.1. Study Population 6.2.2. MRI Protocol 6.2.3. Multi-Atlas Whole Heart Segmentation (MA-WHS)