Linked e-resources
Details
Table of Contents
Preface; Acknowledgments; Contents; 1 Introduction; 1.1 What Is Computational Anatomy?; 1.2 Needs, Seeds, and Solutions Around Medical Imaging: History and Perspectives; 1.2.1 Needs in Medical Education and Clinical Practice; 1.2.1.1 From the Viewpoint of Medical Education; 1.2.1.2 From the Viewpoint of Diagnostic Radiology; 1.2.1.3 From the Viewpoint of Therapeutic Radiology; 1.2.1.4 From the Viewpoint of Surgery; 1.2.2 Seeds and Solutions in Science, Technology, and Engineering; 1.3 Whole-Body Computational Anatomy; 1.3.1 Impact of Whole-Body Imaging
1.3.2 Toward Complete Medical Image Understanding1.4 Book Organization; References; 2 Fundamental Theories and Techniques; 2.1 From Anatomy to Computational Anatomy; 2.1.1 Introduction; 2.1.2 Simple Examples; 2.1.2.1 Outline of ASM; 2.1.2.2 Required Techniques; 2.2 Mathematical Foundation; 2.2.1 Signal Processing; 2.2.1.1 Digital Images; 2.2.1.2 Linear Operation; 2.2.1.3 Convolution; 2.2.1.4 Cross Correlation; 2.2.1.5 Fourier Series Expansion; 2.2.1.6 Differentiation of Discrete Signals; 2.2.2 Fundamental Transformations; 2.2.2.1 Coordinate Transformation; 2.2.2.2 Linear Subspace
2.2.2.3 Affine Transformation2.2.2.4 Singular Value Decomposition; 2.2.2.5 Principal Component Analysis; 2.2.3 Probability and Statistics: Foundations of CA; 2.2.3.1 Sum Rule and Product Rule of Probability; 2.2.3.2 Expectation and Variance; 2.2.3.3 Gaussian Distribution; 2.2.4 Foundations of Pattern Recognition; 2.2.4.1 Bayes Decision Theory; 2.2.4.2 Classifier Design; 2.3 Computational Anatomical Model; 2.3.1 Models for Segmentation; 2.3.2 Geometrical Representation; 2.3.2.1 Representation Using Functions of Voxels; 2.3.2.2 Representation Using Parametric Functions; 2.3.2.3 Curves
2.3.2.4 Surfaces2.3.2.5 Registration Required Before Measurement or Analysis; 2.3.3 Image Features and Landmarks; 2.3.3.1 Anatomical Landmarks; 2.3.3.2 Keypoints; 2.3.3.3 Edges and Ridges; 2.3.4 Diffeomorphism Frameworks; 2.3.4.1 LDDMM Framework for Registration; 2.3.4.2 SVF Framework; 2.3.4.3 Statistical Analysis on Shape Manifold; 2.3.4.4 Applications and Future Works; 2.3.5 Computational Anatomy and Registration; 2.3.5.1 Probabilistic Atlas; 2.3.5.2 SSMs; 2.3.6 CA-Based Segmentation; 2.3.6.1 Probabilistic Atlas-Based Segmentation; 2.3.6.2 Active Shape Model; 2.3.6.3 Level Set with CA
2.3.6.4 Graph-Cuts with CA2.3.6.5 Ensemble Learning with CA; 2.3.7 Multiple Organs, Anomaly, and Lesions; 2.3.7.1 Multiple Organs; 2.3.7.2 Anatomical Anomaly; References; 3 Understanding Medical Images Based on Computational Anatomy Models; 3.1 Introduction; 3.2 Bone; 3.3 Skeletal Muscle; 3.3.1 Anatomical Modeling of Skeletal Muscles; 3.3.1.1 Muscle Distribution Model; 3.3.1.2 SSM; 3.4 Lymph Nodes; 3.4.1 Overview of Lymph Node Segmentation on Medical Images; 3.4.2 Overview of Lymph Node Segmentation from Abdominal CT Images; 3.4.2.1 Preprocessing; 3.4.2.2 Blob-Like Structure Enhancement
1.3.2 Toward Complete Medical Image Understanding1.4 Book Organization; References; 2 Fundamental Theories and Techniques; 2.1 From Anatomy to Computational Anatomy; 2.1.1 Introduction; 2.1.2 Simple Examples; 2.1.2.1 Outline of ASM; 2.1.2.2 Required Techniques; 2.2 Mathematical Foundation; 2.2.1 Signal Processing; 2.2.1.1 Digital Images; 2.2.1.2 Linear Operation; 2.2.1.3 Convolution; 2.2.1.4 Cross Correlation; 2.2.1.5 Fourier Series Expansion; 2.2.1.6 Differentiation of Discrete Signals; 2.2.2 Fundamental Transformations; 2.2.2.1 Coordinate Transformation; 2.2.2.2 Linear Subspace
2.2.2.3 Affine Transformation2.2.2.4 Singular Value Decomposition; 2.2.2.5 Principal Component Analysis; 2.2.3 Probability and Statistics: Foundations of CA; 2.2.3.1 Sum Rule and Product Rule of Probability; 2.2.3.2 Expectation and Variance; 2.2.3.3 Gaussian Distribution; 2.2.4 Foundations of Pattern Recognition; 2.2.4.1 Bayes Decision Theory; 2.2.4.2 Classifier Design; 2.3 Computational Anatomical Model; 2.3.1 Models for Segmentation; 2.3.2 Geometrical Representation; 2.3.2.1 Representation Using Functions of Voxels; 2.3.2.2 Representation Using Parametric Functions; 2.3.2.3 Curves
2.3.2.4 Surfaces2.3.2.5 Registration Required Before Measurement or Analysis; 2.3.3 Image Features and Landmarks; 2.3.3.1 Anatomical Landmarks; 2.3.3.2 Keypoints; 2.3.3.3 Edges and Ridges; 2.3.4 Diffeomorphism Frameworks; 2.3.4.1 LDDMM Framework for Registration; 2.3.4.2 SVF Framework; 2.3.4.3 Statistical Analysis on Shape Manifold; 2.3.4.4 Applications and Future Works; 2.3.5 Computational Anatomy and Registration; 2.3.5.1 Probabilistic Atlas; 2.3.5.2 SSMs; 2.3.6 CA-Based Segmentation; 2.3.6.1 Probabilistic Atlas-Based Segmentation; 2.3.6.2 Active Shape Model; 2.3.6.3 Level Set with CA
2.3.6.4 Graph-Cuts with CA2.3.6.5 Ensemble Learning with CA; 2.3.7 Multiple Organs, Anomaly, and Lesions; 2.3.7.1 Multiple Organs; 2.3.7.2 Anatomical Anomaly; References; 3 Understanding Medical Images Based on Computational Anatomy Models; 3.1 Introduction; 3.2 Bone; 3.3 Skeletal Muscle; 3.3.1 Anatomical Modeling of Skeletal Muscles; 3.3.1.1 Muscle Distribution Model; 3.3.1.2 SSM; 3.4 Lymph Nodes; 3.4.1 Overview of Lymph Node Segmentation on Medical Images; 3.4.2 Overview of Lymph Node Segmentation from Abdominal CT Images; 3.4.2.1 Preprocessing; 3.4.2.2 Blob-Like Structure Enhancement