Medical Image Computing and Computer Assisted Intervention - MICCAI 2017

Name: Medical Image Computing and Computer Assisted Intervention - MICCAI 2017 | 20th International Conference, Quebec City, QC, Canada, September 11-13, 2017, Proceedings, Part I
Brand: Springer
Price: 96.29 EUR
Availability: OnlineOnly

20th International Conference, Quebec City, QC, Canada, September 11-13, 2017, Proceedings, Part I

Maxime Descoteaux Lena Maier-Hein Alfred Franz Pierre Jannin D. Louis Collins Simon Duchesne(Editor)

Springer (Publisher)

Published on 3. September 2017

XLVI, 811 pages

E-Book

PDF with digital watermarking

System requirements

978-3-319-66182-7 (ISBN)

€96.29incl. 7% vat

System requirements

for PDF with digital watermarking

E-Book Single Licence

Available for download

Description

More details

Other editions

Content

Intro
Preface
Organization
Contents - Part I
Contents - Part II
Contents -- Part III
Atlas and Surface-Based Techniques
The Active Atlas: Combining 3D Anatomical Models with Texture Detectors
1 Introduction
2 The Active Atlas
2.1 Preprocessing
2.2 Estimation of Anatomical Model
2.3 Learning Texture Classifiers
2.4 Registering Atlas to Specimen
2.5 Evaluating Registration Confidence
2.6 Updating Atlas
3 Results
3.1 Confidence of Registrations
3.2 Variability of Structure Position
3.3 Accuracy of Texture Classifiers
4 Conclusion
References
Exploring Gyral Patterns of Infant Cortical Folding Based on Multi-view Curvature Information
Abstract
1 Introduction
2 Materials and Methods
2.1 Dataset and Image Processing
2.2 Computing Multi-view Curvature-Based Features
2.3 Fusing Similarity Matrices of Multi-view Features
2.4 Clustering Gyral Folding Patterns
3 Results
4 Conclusion
Acknowledgements
References
Holistic Mapping of Striatum Surfaces in the Laplace-Beltrami Embedding Space
1 Introduction
2 Methods
3 Results
4 Conclusion
References
Novel Local Shape-Adaptive Gyrification Index with Application to Brain Development
1 Introduction
2 Wavefront Propagation
3 Novel Local Shape-Adaptive Gyrification Index
3.1 Outer Hull Creation and Surface Correspondence
3.2 Travel-Time Map for Local Cortical Region Segmentation
3.3 Tensor Field
3.4 Adaptive Kernel and Local Gyrification Index
4 Reproducibility
5 Longitudinal Study in Early Postnatal Phase
6 Conclusion
References
Joint Sparse and Low-Rank Regularized Multi-Task Multi-Linear Regression for Prediction of Infant Brain Development with Incomplete Data
1 Introduction
2 Materials and Feature Extraction
3 Joint Sparse and Low-Rank Regularized MTMLR
4 Experiments
5 Conclusions
References
Graph-Constrained Sparse Construction of Longitudinal Diffusion-Weighted Infant Atlases
1 Introduction
2 Method
2.1 Longitudinal Image Normalization
2.2 Patch Fusion via Graph-Constrained Sparse Representation
3 Experiments
3.1 Materials
3.2 Implementation Detail
3.3 Comparison with Existing Image Fusion Methods
3.4 Evaluation of Temporal Consistency
4 Conclusion
References
4D Infant Cortical Surface Atlas Construction Using Spherical Patch-Based Sparse Representation
1 Introduction
2 Method
2.1 Materials and Image Processing
2.2 Establishing Intra-subject and Inter-subject Correspondences
2.3 Atlas Built by Spherical Patch-Based Sparse Representation
3 Experiments
4 Conclusion
References
Developmental Patterns Based Individualized Parcellation of Infant Cortical Surface
Abstract
1 Introduction
2 Method
2.1 Population-Based Parcellation and Inter-subject Variability
2.2 Population-Guided Iterative Individualized Parcellation
3 Results
4 Conclusion
Acknowledgements
References
Longitudinal Modeling of Multi-modal Image Contrast Reveals Patterns of Early Brain Growth
1 Introduction
2 Methods
3 Analysis of Early Brain Growth
4 Discussion
References
Prediction of Brain Network Age and Factors of Delayed Maturation in Very Preterm Infants
1 Introduction
2 Method and Materials
3 Results
4 Discussion
5 Conclusions
References
Falx Cerebri Segmentation via Multi-atlas Boundary Fusion
1 Introduction
2 Method
2.1 Data and Preprocessing
2.2 Point-Set Correspondence
2.3 Boundary Fusion and Final Falx
3 Results
4 Conclusion
References
A 3D Femoral Head Coverage Metric for Enhanced Reliability in Diagnosing Hip Dysplasia
1 Introduction
2 Methods
2.1 Femoral Head Segmention
2.2 Localizing Vertical Cortex of Ilium and Estimating FHC3D
3 Results and Discussion
4 Conclusions
References
Learning-Based Multi-atlas Segmentation of the Lungs and Lobes in Proton MR Images
1 Introduction
2 Materials and Methods
2.1 Image Data
2.2 Construction of a CT-Based Lung MRI Atlas Library
2.3 Learning-Based Multi-atlas Segmentation
3 Experiments and Results
3.1 Experimental Setup
3.2 Impact of the Number of Atlas Forests
3.3 Comparison with Multi-atlas and Learning-Based Segmentation Methods
4 Discussion and Conclusion
References
Unsupervised Discovery of Spatially-Informed Lung Texture Patterns for Pulmonary Emphysema: The MESA COPD Study
1 Introduction
2 Method
2.1 Spatial Mapping of the Lung Shape
2.2 Augmented Lung Texture Patterns
2.3 Final Spatially-Informed LTPs
3 Experimental Results
3.1 Data
3.2 Population Evaluation Using PDCM
3.3 Qualitative and Quantitative Evaluations of sLTPs
4 Discussions and Conclusions
References
Shape and Patch-Based Techniques
Automatic Landmark Estimation for Adolescent Idiopathic Scoliosis Assessment Using BoostNet
1 Introduction
2 Methodology
2.1 Novel BoostNet Architecture
2.2 Training Algorithm
2.3 Dataset
3 Results
4 Conclusion
References
Nonlinear Statistical Shape Modeling for Ankle Bone Segmentation Using a Novel Kernelized Robust PCA
1 Introduction
2 KRPCA for Statistical Shape Modeling
2.1 Kernel RPCA
2.2 Applying KRPCA to Statistical Shape Modeling
3 Evaluation
3.1 Model Evaluation
3.2 Application in Ankle Bone Segmentation
4 Discussion
References
Adaptable Landmark Localisation: Applying Model Transfer Learning to a Shape Model Matching System
1 Introduction
2 Methods
2.1 Random Forest Regression-Voting Constrained Local Models
2.2 Tuning the Shape Model
2.3 Tuning the RF Trees
3 Experiments
3.1 Parameter Optimisation Experiments
3.2 Performance Evaluation
4 Discussion and Conclusions
References
Representative Patch-based Active Appearance Models Generated from Small Training Populations
1 Introduction
2 Methods
2.1 Patch-based AAM Framework: Definition and Optimization
2.2 Building Representative Patch-AAMs from Few Training Samples
3 Experiments and Results
4 Conclusion
References
Integrating Statistical Prior Knowledge into Convolutional Neural Networks
1 Introduction and Related Work
2 Method
2.1 Building a Shape Model Through PCA
2.2 Network Architecture
3 Results
3.1 Segmentation
3.2 Landmark Localization
4 Conclusion
References
Statistical Shape Model of Nested Structures Based on the Level Set
1 Introduction
2 Methods
2.1 Level-set Based Shape Representation
2.2 Level Set Function for Two Nested Objects
2.3 Level Set Function for k Nested Objects
3 Experiments
4 Conclusion
References
Locally Adaptive Probabilistic Models for Global Segmentation of Pathological OCT Scans
1 Introduction
2 Probabilistic Graphical Model
3 Locally Adaptive Priors
4 Results
5 Discussion
References
Learning Deep Features for Automated Placement of Correspondence Points on Ensembles of Complex Shapes
1 Introduction
2 Methodology
3 Results and Discussion
References
Robust Multi-scale Anatomical Landmark Detection in Incomplete 3D-CT Data
1 Introduction
2 Background and Motivation
2.1 Challenges of 3D Landmark Detection in Incomplete Data
2.2 Learning to Search Using Deep Reinforcement Learning
3 Proposed Method
3.1 A Discrete Scale-Space Model
3.2 Learning Multi-scale Search Strategies
3.3 Robust Spatially-Coherent Landmark Detection
4 Experiments
5 Conclusion
References
Learning and Incorporating Shape Models for Semantic Segmentation
1 Introduction
2 Related Work
3 Our Approach
4 Architectures
4.1 Segmentation Network
4.2 Shape Regularization Network
4.3 Implementation Details
4.4 Data Augmentation for Shape Regularization Network
5 Kidney Segmentation from U/S B-Mode Images
6 Results
7 Discussion
References
Surface-Wise Texture Patch Analysis of Combined MRI and PET to Detect MRI-Negative Focal Cortical Dy ...
Abstract
1 Introduction
2 Methods
2.1 Subjects and Image Acquisition
2.2 Image Processing and Cortical Surface Extraction
2.3 Feature Extraction
2.4 Manual Lesion Labeling
2.5 Optimization of Classification
2.6 Evaluation of Classification Accuracy
3 Results
3.1 Performance of the SVM-Based Classifier (Step 1)
3.2 Performance of the Patch-Based Classifier (Step
4 Discussion and Conclusion
References
Registration Techniques
Training CNNs for Image Registration from Few Samples with Model-based Data Augmentation
1 Introduction
2 Methods
2.1 Statistical Appearance Models
2.2 Locality-based Statistical Shape and Appearance Models
2.3 Model-based Data Augmentation for Learning Image Registration
3 Experiments and Results
4 Discussion and Conclusion
References
Nonrigid Image Registration Using Multi-scale 3D Convolutional Neural Networks
1 Introduction
2 Methods
2.1 Network Architecture
2.2 Training
3 Experiments and Results
3.1 Materials
3.2 Experimental Setup and Evaluation
3.3 Results
4 Discussion and Conclusion
References
Multimodal Image Registration with Deep Context Reinforcement Learning
1 Introduction
2 Related Work
3 Method
3.1 Environment Setup
3.2 Training the Agent
3.3 Data Projection
4 Experiments and Results
5 Conclusion and Future Work
References
Directional Averages for Motion Segmentation in Discontinuity Preserving Image Registration
1 Introduction
2 Background
3 Method
3.1 Directional Average Regularizer
3.2 Directional Average Similarity Metric
4 Results
4.1 POPI Model
5 Conclusion
References
2 Similarity Metrics for Diffusion Multi-Compartment Model Images Registration
1 Introduction
2 Methods
2.1 Diffusion Multi-Compartment Models
2.2 2 Space of Square Integrable Functions
2.3 MCM Similarity Measures
2.4 Pairing-Based MCM Similarity Measure
3 Experiments and Results
3.1 Image Database and Registration Algorithm
3.2 Similarity Measures Qualitative Evaluation
3.3 Quantitative Evaluation on HCP Data
4 Conclusion
References
SVF-Net: Learning Deformable Image Registration Using Shape Matching
1 Introduction
2 Methods: Learning Image Deformations
3 Validation on a Cardiac Image Database
4 Conclusions
References
A Large Deformation Diffeomorphic Approach to Registration of CLARITY Images via Mutual Information
1 Introduction
2 Image Registration in the LDDMM Framework
3 Mutual Information Approach for LDDMM
4 Algorithm Implementation
5 Results
5.1 MI Registration Pipeline
5.2 Multi-resolution Registration
6 Conclusion
References
Mixed Metric Random Forest for Dense Correspondence of Cone-Beam Computed Tomography Images
1 Introduction
2 Methods
2.1 Initial Supervoxel-wise Affinity and Weak Labeling
2.2 Mixed Metric Random Forest
2.3 Soft Consistency Evaluation
3 Experiments
3.1 Qualitative Assessment
4 Discussion and Conclusion
References
Optimal Transport for Diffeomorphic Registration
1 Introduction
2 Diffeomorphic Registration
3 Optimal Transport Data Fidelity
4 Numerical Results
5 Conclusion
References
Deformable Image Registration Based on Similarity-Steered CNN Regression
Abstract
1 Introduction
2 Method
2.1 Training Set Preparation
2.2 Similarity-Steered CNN Regression
3 Experiments
3.1 LONI Dataset
3.2 ADNI Dataset
4 Conclusion
References
Generalised Coherent Point Drift for Group-Wise Registration of Multi-dimensional Point Sets
1 Introduction
2 Hybrid Mixture Model-Based Group-Wise Registration
2.1 Rigid Registration
2.2 Non-rigid Registration
3 Validation Using Clinical Data
4 Conclusions
References
Fast Geodesic Regression for Population-Based Image Analysis
1 Introduction
2 Background: Geodesic Regression
3 Fast Geodesic Regression
4 Results
5 Discussion and Conclusions
References
Deformable Registration of a Preoperative 3D Liver Volume to a Laparoscopy Image Using Contour and Shading Cues
1 Introduction
2 Proposed Problem Formulation
2.1 Preliminaries
2.2 Organ Model and Deformation Law
2.3 Visual Cues
3 Proposed Optimisation Solution
3.1 Refining Algorithm
3.2 Constraint Mappings
4 Experimental Results
5 Conclusion
References
Parameter Sensitivity Analysis in Medical Image Registration Algorithms Using Polynomial Chaos Expansions
1 Introduction
2 Method
2.1 Theory
2.2 Distribution Assumptions for User-Defined Input Parameters
2.3 PCE Model Construction
3 Experiments and Results
3.1 Dataset
3.2 Evaluation
3.3 Results
4 Discussion
5 Conclusion
References
Robust Non-rigid Registration Through Agent-Based Action Learning
1 Introduction
2 Method
2.1 Training Artificial Agents
2.2 Statistical Deformation Model
2.3 Training Data Generation
3 Experiments
4 Conclusion
References
Selecting the Optimal Sequence for Deformable Registration of Microscopy Image Sequences Using Two-Stage MST-based Clustering Algorithm
1 Introduction
2 Minimum Spanning Tree (MST) Based Clustering Algorithm for Deformable Registration
3 Experimental Results and Discussions
4 Conclusions and Future Works
References
Functional Imaging, Connectivity, and Brain Parcellation
Dynamic Regression for Partial Correlation and Causality Analysis of Functional Brain Networks
1 Introduction
2 Theory
2.1 Causal-Filter Regression
2.2 Optimal Filter
2.3 Partial Correlation Analysis
2.4 Causality Analysis
3 Experiments
4 Results
5 Conclusion
References
Kernel-Regularized ICA for Computing Functional Topography from Resting-State fMRI
1 Introduction
2 Methods
2.1 Modeling Topographic Regularity in Structural Connectivity
2.2 Incorporating Structural Topography into ICA
3 Experimental Results
3.1 Data Preparation and Experiment Configuration
3.2 Somatotopic Organization in Functional Connectivity
3.3 Reproducibility
4 Conclusion
References
N-way Decomposition: Towards Linking Concurrent EEG and fMRI Analysis During Natural Stimulus
Abstract
1 Introduction
2 Materials and Method
2.1 Overview
2.2 Data Acquisition and Preprocessing
2.3 EEG Time-Frequency Transformation
2.4 Four-way Canonical Polyadic Decomposition on EEG
2.5 Two-way FMRI Sparse Decomposition and Statistics
2.6 Feature Selection
3 Results
3.1 Inter-subject Consistency Analysis for EEG Time-Frequency Data
3.2 The Linked EEG Components and FMRI Networks
4 Discussion
References
Connectome-Based Pattern Learning Predicts Histology and Surgical Outcome of Epileptogenic Malformat ...
Abstract
1 Introduction
2 Methods
2.1 MRI Acquisition
2.2 MRI Processing
2.3 Functional Connectivity Mapping of FCD Lesions
2.4 Data-Driven Clustering of Community-Based Lesion Connectivity
2.5 Supervised Prediction of Histology and Surgical Outcome (Fig. 1D)
3 Experiment and Results
3.1 Subjects
3.2 Connectome-Based Profiling of FCD Lesions
3.3 Machine-Learning Prediction of Histological Grade and Surgical Outcome
4 Discussion
References
Joint Representation of Connectome-Scale Structural and Functional Profiles for Identification of Consistent Cortical Landmarks in Human Brains
Abstract
1 Introduction
2 Materials and Methods
2.1 Overview
2.2 Data Acquisition and Pre-processing
2.3 Representation of Connectome-Scale Functional Profiles for Landmark Location Initialization
2.4 Joint Constraint of Connectome-Scale Structural and Functional Profiles for Landmark Location Optimization
2.5 Prediction of SFCCLs
3 Experimental Results
3.1 Consistent Cortical Landmarks via Joint Representation of Connectome-Scale Structural and Functional Profiles
3.2 Prediction of SFCCLs
4 Conclusion
References
Subject-Specific Structural Parcellations Based on Randomized AB-divergences
1 Introduction
2 Methods
2.1 Connectivity Signatures
2.2 Parcellations and Tessellations
2.3 Randomized AB-divergences
2.4 Parcellation Coherence
2.5 Connectivity Matrices
3 Results
3.1 AB-divergence Selection and Prior Adaptation
3.2 Parcels Coherences
3.3 Connectivity Matrices
4 Discussions
References
Improving Functional MRI Registration Using Whole-Brain Functional Correlation Tensors
Abstract
1 Introduction
2 Method
2.1 Functional Correlation Tensors (FCTs)
2.2 PFCTs Construction
2.3 Multi-channel LDDMM
3 Experimental Results
3.1 Group-Level Performance
3.2 Individual-Level Performance
4 Conclusion
Acknowledgement
References
Multi-way Regression Reveals Backbone of Macaque Structural Brain Connectivity in Longitudinal Datasets
Abstract
1 Introduction
2 Materials and Methods
2.1 Overview
2.2 Data Description and Preprocessing
2.3 Multi-way Regression
2.4 Graphic Statistics
3 Results
3.1 Effectiveness of the Multi-way Regression Method
3.2 Development of Connective Connectome of Infant Macaque Brains
4 Discussions and Conclusions
References
Multimodal Hyper-connectivity Networks for MCI Classification
Abstract
1 Introduction
2 Materials and Methodology
2.1 Dataset
2.2 Data Preprocessing
2.3 Methods
3 Experiment Results
4 Conclusion
References
Multi-modal EEG and fMRI Source Estimation Using Sparse Constraints
1 Introduction
2 Method
2.1 Model
2.2 Proximal Algorithm
2.3 Parameter Calibration
3 Experimental Data and Implementations
4 Results
5 Conclusions and Perspectives
References
Statistical Learning of Spatiotemporal Patterns from Longitudinal Manifold-Valued Networks
1 Introduction
2 Manifold-Valued Networks
2.1 Manifold-Valued Measurements Distributed on a Fixed Graph
2.2 Spatial Smoothness of the Propagation
3 The Statistical Model
3.1 A Propagation Model
3.2 Parameters Estimation with the MCMC-SAEM Algorithm
3.3 Model Instantiation
4 Experimental Results
4.1 Data
4.2 Cortical Thickness Measurements
5 Discussion and Perspectives
References
Population-Shrinkage of Covariance to Estimate Better Brain Functional Connectivity
1 Introduction
2 Covariance Shrinkage Towards a Prior Distribution
2.1 Tangent Space Embedding of the Geometry of Covariances
2.2 Building the Prior from the Population Distribution
2.3 Estimating the Shrunk Covariance as a Posterior Mean
3 Experimental Validation: Shrunk Embedding on HCP
4 Conclusion
References
Distance Metric Learning Using Graph Convolutional Networks: Application to Functional Brain Networks
1 Introduction
2 Methodology
2.1 Spectral Graph Filtering and Convolutions
2.2 Loss Function and Network Architecture
2.3 From fMRI Data to Graph Signals
3 Results
4 Discussion
References
A Submodular Approach to Create Individualized Parcellations of the Human Brain
1 Introduction
2 Previous Work
3 Proposed Submodular Approach
3.1 Exemplar-Based Clustering
3.2 Submodular Functions
3.3 The Greedy Algorithm for Optimization of the Submodular Function
4 Methods
5 Results
6 Conclusion
References
BrainSync: An Orthogonal Transformation for Synchronization of fMRI Data Across Subjects
1 Introduction
2 Methods
2.1 Geometry of the rfMRI Signal Space
2.2 A Method for Temporal Synchronization
3 Applications, Experiments and Results
3.1 Data
3.2 Application 1: Quantifying Variability of RfMRI Across a Population
3.3 Application 2: Cortical Parcellation
3.4 Applications to Task fMRI
4 Discussion and Conclusion
References
Supervised Discriminative EEG Brain Source Imaging with Graph Regularization
1 Introduction
2 The Inverse Problem
3 Proposed Framework
3.1 Graph Regularized Discriminative Source Imaging
3.2 Common Sources Decomposition with Voting Orthogonal Matching Pursue (VOMP)
4 Numerical Results
5 Conclusion
References
Inference and Visualization of Information Flow in the Visual Pathway Using dMRI and EEG
1 Introduction
2 Theory
2.1 Connectivity Informed Maximum Entropy on the Mean
3 Methods
3.1 Synthetic Data
3.2 Experimental Data Acquisition and Preprocessing
3.3 Model Parameters
4 Results
5 Conclusion
References
Diffusion Magnetic Resonance Imaging (dMRI) and Tensor/Fiber Processing
Evaluating 35 Methods to Generate Structural Connectomes Using Pairwise Classification
1 Introduction
2 Structural Connectomics Pipelines
2.1 Reconstruction Models and Tractography
2.2 Parcellations and Network Construction
2.3 Network Features
2.4 Pairwise Features
2.5 Classification Models and Validation
2.6 Reproducibility Measure
3 Experiments
3.1 Base Data
3.2 DWI Preprocessing
3.3 Pairwise and Sex Classification
4 Results
5 Conclusion
References
Dynamic Field Mapping and Motion Correction Using Interleaved Double Spin-Echo Diffusion MRI
1 Introduction
2 Methods
2.1 Acquisition Protocol
2.2 Post-processing
2.3 Experiments
3 Results
3.1 Dynamic Field Mapping and Motion Correction
3.2 Derived Quantitative dMRI Information
4 Discussion and Conclusion
References
A Novel Anatomically-Constrained Global Tractography Approach to Monitor Sharp Turns in Gyri
1 Introduction
2 Materials and Methods
2.1 Non-generative Anatomically Constrained Spin Glass Framework
2.2 The Data Attachment Energy
2.3 The Curvature Energy
2.4 Embedded Anatomical Priors
2.5 The Optimization Process
3 Results and Discussion
3.1 Numerical Fiber Crossing Phantom Experiment
3.2 Real Human Brain Postmortem Sample Experiment
4 Conclusion
References
Learn to Track: Deep Learning for Tractography
1 Introduction
2 Using Deep Learning for Tractography
2.1 Models
2.2 Tractography
3 Related Work
4 Experiments
4.1 ISMRM2015 Challenge
4.2 In Vivo tracking
5 Conclusion
References
FiberNET: An Ensemble Deep Learning Framework for Clustering White Matter Fibers
1 Introduction
2 Harmonic Function
2.1 Defining a Shape-Center
2.2 Boundary Conditions
2.3 Potential Computation
2.4 Computing Potential-Flow Lines
2.5 Parameterizing the Brain
3 Mapping the White Matter Fibers
4 Data Pre-processing and Fiber Tracking
4.1 Data Augmentation
5 Network Architecture
5.1 Training Data and Majority Voting
6 Results
6.1 Conclusions
References
Supra-Threshold Fiber Cluster Statistics for Data-Driven Whole Brain Tractography Analysis
1 Introduction
2 Methods
2.1 Dataset
2.2 Data-Driven WM Parcellation and WM Parcel Neighborhood
2.3 Group Difference at Individual Parcel Level
2.4 Supra-Threshold Fiber Cluster Test
3 Experimental Results
3.1 Synthetic Data
3.2 Real Data
4 Discussion and Conclusion
References
White Matter Fiber Representation Using Continuous Dictionary Learning
1 Introduction
2 Methods
3 Experiments and Results
4 Discussion and Conclusions
References
Fiber Orientation Estimation Guided by a Deep Network
1 Introduction
2 Methods
2.1 Background: FO Estimation by Sparse Reconstruction
2.2 FO Estimation Using a Deep Network
3 Results
3.1 3D Digital Crossing Phantom
3.2 Brain dMRI
4 Conclusion
References
FOD Restoration for Enhanced Mapping of White Matter Lesion Connectivity
1 Introduction
2 Method
2.1 Multi-compartment Modeling for FOD Reconstruction
2.2 Initialization of Lesion FOD
2.3 Inpainting and Restoring Lesion FOD
3 Experiments
3.1 Simulation
3.2 Multi-shell Imaging Data of Human Brains
4 Conclusion
References
Learning-Based Ensemble Average Propagator Estimation
1 Introduction
2 Methods
2.1 EAP Representation Using the SHORE Basis
2.2 A Deep Network for EAP Estimation
2.3 Training and Evaluation
3 Results
4 Conclusion
References
A Sparse Bayesian Learning Algorithm for White Matter Parameter Estimation from Compressed Multi-shell Diffusion MRI
1 Introduction
2 Methods
2.1 Dictionary Representation of Multi-shell Data
2.2 Hierarchical Bayesian Framework
2.3 Sparse Bayesian Learning Based Linear Un-Mixing Inference
3 Experiments and Results
3.1 Synthetic Data from HARDI Reconstruction Challenge
3.2 In-Vivo Data from the Human Connectome Project
4 Discussion and Conclusion
References
Bayesian Image Quality Transfer with CNNs: Exploring Uncertainty in dMRI Super-Resolution
1 Introduction and Background
2 Method
3 Experiments and Results
4 Discussion
References
q-Space Upsampling Using x-q Space Regularization
1 Introduction
2 Approach
2.1 Establishing Relationships of Signals in x-q Space
2.2 q-Space Upsampling
2.3 Implementation Issues
3 Experiments
3.1 Synthetic Data
3.2 Real Data
4 Conclusion
References
Neighborhood Matching for Curved Domains with Application to Denoising in Diffusion MRI
1 Introduction
2 Approach
2.1 Graph Framelet Transforms (GFTs)
2.2 Neighborhood Matching Using GFTs
2.3 Non-local Denoising of Diffusion MRI in x-q Space
2.4 Adaptation to Noncentral Chi Noise
3 Experiments
3.1 Datasets
3.2 Parameter Settings
3.3 Results
4 Conclusion
References
Gray Matter Surface Based Spatial Statistics (GS-BSS) in Diffusion Microstructure
Abstract
1 Introduction
2 Methods
3 Results
4 Discussion
5 Conclusion
Acknowledgements
References
A Bag-of-Features Approach to Predicting TMS Language Mapping Results from DSI Tractography
1 Introduction
2 Data Acquisition
3 Image Analysis and Classification Pipeline
3.1 Preprocessing
3.2 Feature Representation
3.3 Classification, Regression, and Evaluation
4 Results and Discussion
4.1 Within- and Between-Subject Analysis
4.2 Visualization of Feature Weights and Correlations
5 Conclusion
References
Patient-Specific Skeletal Muscle Fiber Modeling from Structure Tensor Field of Clinical CT Images
1 Introduction
2 Method
2.1 Overview of the Proposed Method
2.2 Computation of Structure Tensor Vector Field
2.3 Initialization of B-Spline Grid
2.4 Optimization of B-Spline Grid
2.5 Evaluation Using the Ground Truth Dataset
3 Results
4 Discussion and Conclusion
References
Revealing Hidden Potentials of the q-Space Signal in Breast Cancer
1 Introduction
2 Methods
3 Results
4 Discussion
References
Denoising Moving Heart Wall Fibers Using Cartan Frames
1 Introduction
2 Cartan Forms for Moving Fibers
2.1 Connection Form Distribution Fitting for Outlier Detection
3 Experiments
3.1 Outlier Detection with Canine Simulation Data
3.2 Outlier Detection with Human in vivo Data
4 Conclusion
References
TBS: Tensor-Based Supervoxels for Unfolding the Heart
1 Introduction
2 Method
2.1 Overview
2.2 Supervoxel Over-Segmentation
2.3 Middle-Layer Extraction
2.4 Intensity Projection
3 Experiments and Results
4 Discussion and Conclusions
References
Image Segmentation and Modelling
A Fixed-Point Model for Pancreas Segmentation in Abdominal CT Scans
1 Introduction
2 Approach
2.1 Deep Segmentation Networks
2.2 Fixed-Point Optimization
3 Experiments
3.1 Dataset and Evaluation
3.2 Results
4 Conclusions
References
Semi-supervised Learning for Biomedical Image Segmentation via Forest Oriented Super Pixels(Voxels)
1 Introduction
2 FOSP(FOSV) Based Semi-supervised Learning
2.1 Overview
2.2 Tree and Forest Based Code
2.3 Forest Oriented Super Pixels(Voxels)
2.4 Collect the Low Confidence Super Pixels(Voxels)
2.5 Semi-supervised Learning
3 Experiments
3.1 Vessel Segmentation in 2D Biomedical Images
3.2 Quantitative Comparison
3.3 Interpretation of Low Confidence Regions
3.4 Neuron Segmentation in 3D Biomedical Images
4 Conclusion
References
Towards Automatic Semantic Segmentation in Volumetric Ultrasound
1 Introduction
2 Methodology
2.1 Initial Dense Semantic Labeling with 3D FCN
2.2 Semantic Labeling Refinement with RNN
2.3 Network-Specific Deep Supervision Mechanism
3 Experimental Results
4 Conclusions
References
Automatic Quality Control of Cardiac MRI Segmentation in Large-Scale Population Imaging
1 Introduction
2 Method and Material
3 Results
3.1 Automatic Quality Control on UK Biobank Imaging Study
4 Conclusion
References
Towards Image-Guided Pancreas and Biliary Endoscopy: Automatic Multi-organ Segmentation on Abdominal CT with Dense Dilated Networks
1 Introduction
2 Methods
3 Results
4 Discussion
References
Holistic Segmentation of Intermuscular Adipose Tissues on Thigh MRI
Abstract
1 Introduction
2 Method
2.1 Preprocessing
2.2 Holistic Fascia Lata Detection
2.3 Dual Active Contour Model for Fascia Lata Segmentation
2.4 Holistic Tissue Classification
2.5 Implementation Details
3 Results
4 Conclusion
Acknowledgement
References
Spatiotemporal Segmentation and Modeling of the Mitral Valve in Real-Time 3D Echocardiographic Images
Abstract
1 Introduction
2 Materials and Methods
2.1 Image Data and Manual Segmentation
2.2 Automated Image Analysis
3 Results
4 Discussion
Acknowledgement
References
Unbiased Shape Compactness for Segmentation
1 Introduction
2 Formulation
2.1 ADMM Optimization
3 Experiments
4 Conclusion
References
Joint Reconstruction and Segmentation of 7T-like MR Images from 3T MRI Based on Cascaded Convolutional Neural Networks
1 Introduction
2 Proposed Method
2.1 Proposed 7-Layer 3D Convolutional Neural Network (CNN)
2.2 Proposed Cascaded CNN Architecture for Joint Reconstruction and Segmentation
3 Experimental Results
4 Conclusion
References
Development of a CT-based Patient-Specific Model of the Electrically Stimulated Cochlea
1 Introduction
2 Methods
2.1 Creating CT Based Electro-Anatomical Model
2.2 Solving Electro-Anatomical Models
2.3 Creating Patient-Specific Electro-Anatomical Models
2.4 Creating Generic Electro-Anatomical Models
2.5 Evaluation
3 Results
4 Conclusions
References
Compresso: Efficient Compression of Segmentation Data for Connectomics
1 Introduction
2 The Compresso Scheme
2.1 Encoding
2.2 Decoding
2.3 Complexity
3 Evaluation and Results
4 Conclusions
References
Combining Spatial and Non-spatial Dictionary Learning for Automated Labeling of Intra-ventricular Hemorrhage in Neonatal Brain MRI
1 Introduction
2 Methods
2.1 Preliminaries
2.2 Dictionary Construction
2.3 Implementation Details
3 Experimental Results
3.1 Dataset and Validation
3.2 Parameter Selection
3.3 Results
4 Conclusion
References
Author Index

System requirements

Save as PDF Copy link into clipboard

Schweitzer Fachinformationen

Medical Image Computing and Computer Assisted Intervention - MICCAI 2017

Description

More details

Other editions

Additional editions

Content

System requirements