- Intro
- Workshop Editors
- Preface GRAIL 2017
- Organization
- Preface MFCA 2017
- Organization
- Preface MICGen 2017
- Organization
- Contents
- First International Workshop on Graphs in Biomedical Image Analysis, GRAIL 2017
- Classifying Phenotypes Based on the Community Structure of Human Brain Networks
- 1 Introduction
- 2 Similarity of Brain Network Community Structures
- 2.1 Detecting Communities in Structural Brain Networks
- 2.2 Measuring Distance Between Community Structures
- 3 Classifying Connectomes Based on their Community Structure
- 4 Experiments: Network-Based Alzheimer's Disease Classification
- 4.1 Data and Network Construction
- 4.2 Experimental Setup
- 4.3 Results and Discussion
- 5 Conclusions
- References
- Autism Spectrum Disorder Diagnosis Using Sparse Graph Embedding of Morphological Brain Networks
- 1 Introduction
- 2 Proposed Sparse Graph Embedding of High-Order Morphological Brain Networks for Autism Classification
- 3 Results and Discussion
- 4 Conclusion
- References
- Topology of Surface Displacement Shape Feature in Subcortical Structures
- 1 Introduction
- 2 Methods
- 2.1 Shape Feature
- 2.2 Shape Topology
- 2.3 Persistent Homology
- 2.4 Experiments
- 2.5 Imaging and Demographics
- 3 Results
- 4 Discussion and Conclusion
- References
- Graph Geodesics to Find Progressively Similar Skin Lesion Images
- 1 Introduction
- 2 Methods
- 3 Results
- 4 Conclusions
- References
- Uncertainty Estimation in Vascular Networks
- 1 Introduction
- 2 Background
- 3 Uncertainty Estimation by Means of Sampling
- 3.1 Perturbation Sampler
- 3.2 Gibbs Sampler
- 4 Experiments and Results
- 5 Conclusion
- References
- Extraction of Airways with Probabilistic State-Space Models and Bayesian Smoothing
- 1 Introduction
- 2 Method
- 2.1 Tracking Individual Branches
- 2.2 Process and Measurement Models
- 2.3 Bayesian Smoothing
- 2.4 Tree as a Collection of Branches
- 2.5 Application to Airways
- 3 Experiments and Results
- 3.1 Data
- 3.2 Error Measure, Initial Parameters and Tuning
- 3.3 Results
- 4 Discussion and Conclusions
- References
- Detection and Localization of Landmarks in the Lower Extremities Using an Automatically Learned Conditional Random Field
- 1 Introduction
- 2 Related Work
- 3 Methods
- 3.1 Landmark Localization Using Regression Tree Ensembles
- 3.2 CRF with Pool of Potential Functions and ``Missing'' Label
- 3.3 Learning of Parameters and Removing Potentials
- 4 Results
- 5 Discussion and Conclusions
- References
- 6th International Workshop on Mathematical Foundations of Computational Anatomy, MFCA 2017
- Bridge Simulation and Metric Estimation on Landmark Manifolds
- 1 Introduction
- 2 Landmarks Manifolds and Stochastic Landmark Dynamics
- 2.1 Brownian Motion
- 2.2 Large Deformation Stochastics
- 3 Brownian Bridge Simulation
- 3.1 Bridge Sampling
This book constitutes the refereed joint proceedings of the First International Workshop on Graphs in Biomedical Image Analysis, GRAIL 2017, the 6th International Workshop on Mathematical Foundations of Computational Anatomy, MFCA 2017, and the Third International Workshop on Imaging Genetics, MICGen 2017, held in conjunction with the 20th International Conference on Medical Imaging and Computer-Assisted Intervention, MICCAI 2017, in Quebec City, QC, Canada, in September 2017. The 7 full papers presented at GRAIL 2017, the 10 full papers presented at MFCA 2017, and the 5 full papers presented at MICGen 2017 were carefully reviewed and selected. The GRAIL papers cover a wide range of graph based medical image analysis methods and applications, including probabilistic graphical models, neuroimaging using graph representations, machine learning for diagnosis prediction, and shape modeling. The MFCA papers deal with theoretical developments in non-linear image and surface registration in the context of computational anatomy. The MICGen papers cover topics in the field of medical genetics, computational biology and medical imaging.
(source: Nielsen Book Data)
