Machine Learning in Medical Imaging

Name: Machine Learning in Medical Imaging | 6th International Workshop, MLMI 2015, Held in Conjunction with MICCAI 2015, Munich, Germany, October 5, 2015, Proceedings
Brand: Springer
Price: 53.49 EUR
Availability: OnlineOnly

6th International Workshop, MLMI 2015, Held in Conjunction with MICCAI 2015, Munich, Germany, October 5, 2015, Proceedings

Luping Zhou Li Wang Qian Wang Yinghuan Shi(Editor)

Springer (Publisher)

Published on 8. October 2015

XII, 341 pages

E-Book

PDF with digital watermarking

System requirements

978-3-319-24888-2 (ISBN)

€53.49incl. 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
Segmentation of Right Ventricle in Cardiac MR Images Using Shape Regression
1 Introduction
2 Methodology
2.1 Data Augmentation
2.2 Feature Extraction
2.3 Training the Regressors
2.4 Prediction
3 Experiments
4 Conclusions
References
Visual Saliency Based Active Learning for Prostate MRI Segmentation
1 Introduction
2 Image Features
3 Semi Supervised Learning With Random Forests
4 SSL-AL Based Segmentation From MR Images
4.1 AL Query Strategy
4.2 Random Walks and Most Salient Node
4.3 Graph Cut Segmentation
5 Experiments and Results
5.1 Results on MICCAI PROMISE12 Online Challenge Dataset
5.2 Savings in Labeling Effort and Time
6 Discussion and Conclusion
References
Soft-Split Random Forest for Anatomy Labeling
1 Introduction
2 Random Forest
3 Proposed Metho od
3.1 Soft-Split Random Forest
3.2 Haar-Features Based Context Model (HCM)
4 Experiments
5 Conclusion
References
A New Image Data Set and Benchmark for Cervical Dysplasia Classification Evaluation
1 Introduction
2 The Image Data Set for CIN Classification
3 Seven Classifiers for Comparison
4 Experiments
4.1 Results on Balanced Datasets
4.2 Results on Imbalanced Datasets
4.3 Cervigram Based RandomForest (RF) vs. Pap and HPV Tests
5 Conclusions
References
Machine Learning on High Dimensional Shape Data from Subcortical Brain Surfaces: A Comparison of Feature Selection and Classification Methods
1 Introduction
2 Methods
2.1 Subjects
2.2 High Dimensional Shape Features
2.3 Feature Selection
2.4 Classifiers
3 Results
3.1 Feature Selection Subsets
3.2 Classification Results
4 Discussion
References
Node-Based Gaussian Graphical Model for Identifying Discriminative Brain Regions from Connectivity Graphs
1 Introduction
2 Methods
2.1 Gaussian Graphical Model
2.2 Row-Column Overlap Norm
2.3 Node-Based Gaussian Graphical Model
2.4 Group Analysis with NBGGM
3 Materials
4 Results and Disc cussion
5 Conclusions
References
BundleMAP: Anatomically Localized Features from dMRI for Detection of Disease
1 Introduction
2 Related Work
3 BundleMAP for Tract-Based Feature Extraction
3.1 Tracking the Bundles
3.2 Eliminating Fibers from Adjacent Bundles
3.3 Manifold Learning of BundleMAP Coordinates
3.4 Feature Extraction and Selection
4 Results
4.1 Classification Accuracy
4.2 Anatomical Interpretability
4.3 Selecting the Number of Bins
5 Conclusion
References
FADR: Functional-Anatomical Discriminative Regions for Rest fMRI Characterization
1 Introduction
2 Functional-Anatomical Discriminative Regions Method
3 Experiments and Results
4 Conclusions
References
Craniomaxillofacial Deformity Correction via Sparse Representation in Coherent Space
1 Introduction
2 Method
2.1 Sparse Representat tion (SR)-Based Jaw Prediction
2.2 Mapping-Based Sparse Representation for Jaw Prediction
3 Experiments
3.1 Dataset
3.2 Measurement
3.3 Quantitative Results
3.4 Qualitative Compa arison
4 Conclusion
References
Nonlinear Graph Fusion for Multi-modal Classification of Alzheimer's Disease
1 Introduction
2 Methods
2.1 Graph Construction
2.2 Nonlinear Graph Fusion
2.3 Classification
3 Experiments and Results
3.1 Influence of k
3.2 Comparison with Other Methods
4 Discussion and Conclusion
References
HEp-2 Staining Pattern Recognition Using Stacked Fisher Network for Encoding Weber Local Descriptor
1 Introduction
2 Materials
3 Methods
3.1 Weber's Law
3.2 The First Layer FN
3.3 The Second Layer FN
4 Experimental Results
5 Conclusions
References
Supervoxel Classification Forests for Estimating Pairwise Image Correspondences
1 Introduction
2 Methods
2.1 Problem Formulation
2.2 Random Forests
2.3 Supervoxel Classification Forest (SVF)
3 Experiments and Results
4 Discussion and Conclusion
References
Non-rigid Free-Form 2D-3D Registration Using Statistical Deformation Model
1 Introduction
2 Materials and Methods
2.1 Training Process
2.2 Reconstruction Process
3 Experiments and Results
4 Discussions and Conclusions
References
Learning and Combining Image Similarities for Neonatal Brain Population Studies
1 Introduction
2 Methods
3 Data and Results
4 Conclusions
References
Deep Learning, Sparse Coding, and SVM for Melanoma Recognition in Dermoscopy Images
1 Introduction
2 Related Work
3 Methods
3.1 Dataset
3.2 Deep Learning Modeling Components
3.3 Classical Modeling Approach
4 Results
4.1 Ensembles of Low-Level Visual Features
4.2 Convolutional Neural Networks
4.3 Sparse Coding
4.4 Fusions
5 Conclusion
References
Predicting Standard-Dose PET Image from Low-Dose PET and Multimodal MR Images Using Mapping-Based Sparse Representation
1 Introduction
2 Patch-Based Sparse Representation (SR)
3 Proposed Method
3.1 Mapping Based SR
3.2 Incremental Refinement
3.3 Patch Selection Based Dictionary Construction
4 Experiments
4.1 Comparison of
4.2 Efficacy of the Incremental Refinement Strategy
5 Conclusion
References
Boosting Convolutional Filters with Entropy Sampling for Optic Cup and Disc Image Segmentation from Fundus Images
1 Introduction
2 Method
2.1 Boosting Convolutional Filters
2.2 Classification
3 Experimental Results
3.1 Segmentation Performance
4 Discussion and Conclusion
References
Brain Fiber Clustering Using Non-negative Kernelized Matching Pursuit
1 Introduction
2 Kernelized Dictionary Learning for Clustering
2.1 Dictionary Learning Using Kernelized k-means
2.2 Non-negative Kernelized Sparse Clustering
3 Experiments
4 Conclusion
References
Automatic Detection of Good/Bad Colonies of iPS Cells Using Local Features
1 Introduction
2 Methods
2.1 Extracting Local Features from iPS Cell Colony Images
2.2 Cell Colony Classification with a Kernelized Novelty Detector
2.3 Cell Colony Classification with 2-Class Support Vector Machine
2.4 Cell Colony Classification with the Bag-of-Features Approach
3 Experimental Results
4 Conclusion
References
Detecting Abnormal Cell Division Patterns in Early Stage Human Embryo Development
1 Introduction
2 Methodology
3 Experiments
4 Conclusion
References
Identification of Infants at Risk for Autism Using Multi-parameter Hierarchical White Matter Connectomes
1 Introduction
2 Multi-Parameter Hierarchical Connectome Classification
2.1 Overview
2.2 ROI Parcellation
2.3 Hierarchical Conne ectomes
2.4 Multi-Kernel Classification
3 Experiment Results
3.1 Subjects and Data Processing
3.2 Experiment Setting
3.3 Classification Results
3.4 Most ve Discriminativ Connections
4 Conclusion
References
Group-Constrained Laplacian Eigenmaps: Longitudinal AD Biomarker Learning
1 Introduction
2 Manifold Learning MR Image Based Features
2.1 Multilevel Feature Selection
2.2 Local Binary Patterns
2.3 Laplacian Eigenmaps
3 Experiments and Results
4 Discussion and Future Work
References
Multi-atlas Context Forests for Knee MR Image Segmentation
1 Introduction
2 Method
2.1 Multi-atlas Context Forests
2.2 Bone and Cartilage Segmentation
3 Experimental Results
3.1 Bone Segmentation
3.2 Cartilage Segmentation
4 Conclusions
References
Longitudinal Patch-Based Segmentation of Multiple Sclerosis White Matter Lesions
1 Introduction
2 Materials and Method
2.1 Dataset
2.2 Method
2.3 Dictionary Modification
3 Results
3.1 Number of Reference Images
3.2 Quantitative Evaluation
4 Discussion
References
Hierarchical Multi-modal Image Registration by Learning Common Feature Representations
1 Introduction
2 Method
2.1 Learning Common Feature Representations via Kernel CCA
2.2 Hierarchical Feature-Based Multi-modal Image Registration
3 Experiments
3.1 MR/CT Prostate Image Registration
3.2 Image Registration for Infant Brain MR Images in the First Year of Life
4 Conclusion
References
Semi-automatic Liver Tumor Segmentation in Dynamic Contrast-Enhanced CT Scans Using Random Forests and Supervoxels
1 Introduction
2 Methodology
2.1 Traditional Approach: Single-Phase Voxel-Wise Random Forest
2.2 Proposed Methodology: Multi-phase Cluster-Wise Random Forest
3 Results
4 Conclusion
References
Flexible and Latent Structured Output Learning
1 Introduction
2 Methodology
2.1 Inference and Learning
2.2 The Flexible and Latent Structure G = (V,E)
3 Materials and Methods
4 Results
5 Discussion and Conclusion
References
Identifying Abnormal Network Alterations Common to Traumatic Brain Injury and Alzheimer's Disease Patients Using Functional Connectome Data
1 Introduction
2 Materials and Methods
2.1 Participants
2.2 rsfMRI Data Acquisition
2.3 rsfMRI Data Preprocessing
2.4 Functional Connectome Reconstruction
2.5 Node-Based Connectome Feature Vector
2.6 Alzheimer's Disease Classification Pipeline
2.7 TBI Connectome Classification Using AD Pipeline
3 Results
3.1 AD Classification Results
3.2 TBI Connectome Classification Resutls Using AD Pipeline
4 Discussion
References
Multimodal Multi-label Transfer Learning for Early Diagnosis of Alzheimer's Disease
1 Introduction
2 Method
2.1 Multi-domain Multi-label Feature Selection
2.2 Multimodal Regression and Classification
3 Experiments
3.1 Experimental Settings
3.2 Results
4 Conclusion
References
Soft-Split Sparse Regression Based Random Forest for Predicting Future Clinical Scores of Alzheimer's Disease
1 Introduction
2 Method
2.1 Random Forest
2.2 Sparse Regression in Random Forest
2.3 Soft Split in Random Forest
3 Experiment Results
4 Conclusion
References
Multi-view Classification for Identification of Alzheimer's Disease
1 Introduction
2 Approach
2.1 Notations
2.2 Image Processing
2.3 Multi-view Learning
2.4 AD Classification
3 Experimental Results and Discussion
3.1 Experimental Setting
3.2 Performance and Discussion
4 Conclusion
References
Clustering Analysis for Semi-supervised Learning Improves Classification Performance of Digital Pathology
1 Introduction
2 Related Works
3 Image Dataset and Data Collection
4 Methodology
4.1 Texture Feature Extraction from Patches
4.2 Method for Supervised Learning
4.3 Methods for Semi-supervised Learning
4.4 Experimental Design
5 Results and Discussion
5.1 Summary and Conclusion
References
A Composite of Features for Learning-Based Coronary Artery Segmentation on Cardiac CT Angiography
1 Introduction
2 Composite Features
2.1 Relative Density
2.2 Local Shape Feature
2.3 Global Structure Feature
3 Supervised Learning-Based Segmentation
4 Experimental Results and Discussion
5 Conclusions and Future works
References
Ensemble Prostate Tumor Classification in H&E Whole Slide Imaging via Stain Normalization and Cell Density Estimation
1 Introduction
2 Methods
3 Results
4 Discussion
5 Conclusions
References
Computer-Assisted Diagnosis of Lung Cancer Using Quantitative Topology Features
1 Introduction
2 Methodology
2.1 Overview
2.2 Local Features
2.3 Topological Features
2.4 Summary of Features
3 Experiments
4 Conclusion
References
Inherent Structure-Guided Multi-view Learning for Alzheimer's Disease and Mild Cognitive Impairment Classification
1 Introduction
2 Proposed Method
2.1 Feature Extraction
2.2 Inherent Structure-Guided Sparse Feature Selection
2.3 Ensemble Classification
3 Experiments
3.1 Data and Experimental Settings
3.2 Results and Discussion
4 Conclusion
References
Nonlinear Feature Transformation and Deep Fusion for Alzheimer's Disease Staging Analysis
1 Introduction
2 TPS Metric Learning for Support Vector Machines (TML-SVM)
3 Neuroimage Data and Feature Extraction
4 Experiments and Results
4.1 Comparisons of Different Features
4.2 Comparisons of Different Feature Fusion Strategies
4.3 Comparisons of TML-SVM with Other Classifiers
5 Conclusions
References
Tumor Classification by Deep Polynomial Network and Multiple Kernel Learning on Small Ultrasound Image Dataset
1 Introduction
2 DPN-MKL Framework
2.1 Deep Polynomial Network Algorithm
2.2 Multiple Kernel Learning
3 Experiments and Results
3.1 Breast Ultrasound Image Dataset
3.2 Prostate Ultrasound Elastography Image Dataset
4 Conclusion
Reference
Multi-source Information Gain for Random Forest: An Application to CT Image Prediction from MRI Data
1 Introduction
2 Random Forest
2.1 Classic Random Forest
2.2 Structured Random Forest
3 Multi-source Information Gain
4 Experimental Analysis
4.1 Predicting CT Image from MR image
4.2 Integration to Auto-context Model
5 Discussion and Conclusion
References
Joint Learning of Multiple Longitudinal Prediction Models by Exploring Internal Relations
1 Introduction
2 Method
2.1 Notation and Problem Statement
2.2 Proposed Method
3 Experiments
4 Conclusions
References
Author Index

System requirements

Save as PDF Copy link into clipboard

Schweitzer Fachinformationen

Machine Learning in Medical Imaging

Description

More details

Other editions

Additional editions

Content

System requirements