Warping Strategies for Intersubject Registration

Challenges in 3D Brain Imaging 569

1.1 Pathology Detection • 1.2 Analyzing Brain Data • 1.3 Measuring Anatomical Differences • 1.4 Population-Based Atlases • 1.5 Measuring Brain Changes • 1.6 Hybrid Algorithms

Classification of Warping Algorithms 571

2.1 Model-Driven and Intensity-Driven Algorithms • 2.2 Intensity-Driven Approaches •

2.3 Navier-Stokes Equilibrium Equations • 2.4 Viscous Fluid Approaches • 2.5 Convolution Filters •

2.6 Multigrid and Coarse-to-Fine Optimization • 2.7 Bayesian Registration Models •

2.8 Model-Driven Algorithms • 2.9 Point-Based Matching • 2.10 Neural Network Approaches • 2.11 Curve-Based Approaches • 2.12 Automated Matching • 2.13 Surface-Based Approaches • 2.14 Anatomical Models • 2.15 Parameterization • 2.16 Displacement Maps • 2.17 3D Volume Transformation

Cortical Pattern Matching 581

3.1 Overview of Method • 3.2 Algorithm Details • 3.3 Maps of the Cortical Parameter Space •

3.4 Cortical Curvature • 3.5 Covariant Formalism • 3.6 Covariant Matching of Cortical Surfaces •

3.7 Advantages

Pathology Detection 587

4.1 Encoding Brain Variation • 4.2 Emerging Patterns • 4.3 Mapping Cortical Variability • 4.4 Variability and Asymmetry • 4.5 Comparing Registration Methods • 4.6 Population-Based Brain Image Templates • 4.7 Random Tensor Field Models • 4.8 Abnormal Asymmetry • 4.9 Shape Theory Approaches • 4.10 Pattern-Theoretic Approaches • 4.11 Learning Information on Anatomic Variability • 4.12 Disease Classification and Subtyping • 4.13 Pathology Detection in Image Databases

Conclusion 596

References 596

0 0

Post a comment