Machine Learning in Medical Imaging

Name: Machine Learning in Medical Imaging | Second International Workshop, MLMI 2011, Held in Conjunction with MICCAI 2011, Toronto, Canada, September 18, 2011, Proceedings
Brand: Springer
Price: 53.49 EUR
Availability: OnlineOnly

Second International Workshop, MLMI 2011, Held in Conjunction with MICCAI 2011, Toronto, Canada, September 18, 2011, Proceedings

Kenji Suzuki Fei Wang Dinggang Shen Pingkun Yan(Editor)

Springer (Publisher)

Published on 25. September 2011

XIII, 371 pages

E-Book

PDF with digital watermarking

System requirements

978-3-642-24319-6 (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

Title
Preface
Organization
Table of Contents
Learning Statistical Correlation of Prostate Deformations for Fast Registration
Introduction
Method
Description
Learning Statistical Correlation from a Population of Training Patients
Refining Interpolation of Dense Correspondences by Patient-Specific Information
Experimental Resuults
Conclusion
References
Automatic Segmentation of Vertebrae from Radiographs: A Sample-Driven Active Shape Model Approach
Introduction
Methods
Statistical Shape Models
Coarse Sample-Based Segmentation
Conditional Shape Model
Active Shape Model Segmentation
Evaluation
Discussion and Conclusions
References
Computer-Assisted Intramedullary Nailing Using Real-Time Bone Detection in 2D Ultrasound Images
Introduction
Proposed Method
Preprocessing Step
False Alarm Elimination
Contour Closure
Results
Conclusion
References
Multi-Kernel Classification for Integration of Clinical and Imaging Data: Application to Prediction of Cognitive Decline in Older Adults
Introduction
Background
Classification of Imaging and Clinical Evaluations
Results
Materials and Evaluation
Classification of Single-Visit Evaluations
Biomarker of Cognitive Decline
Analysis of Individuals with Uncertain Trends of Decline
Conclusion
References
Automated Selection of Standardized Planes from Ultrasound Volume
Introduction
Plane Selection Method
Feature Extraction
Learning Algorithm
Slice Selection
Datasets and Experiments
Data Acquisition
Results and Performance Analysis
Conclusion
References
Maximum Likelihood and James-Stein Edge Estimators for Left Ventricle Tracking in 3D Echocardiography
Introduction
Tracking Framework
Edge Detection Methods
Maximum Gradient Edge Detector (MG)
Step Criterion Edge Detector (STEP)
Max Flow/Min Cut Edge Detector (MFMC)
Maximum Likelihood (MLE) and James-Stein (JS) Estimators
Results
Discussion and Conclusion
References
A Locally Deformable Statistical Shape Model
Introduction and Related Work
Statistical Shape Model
Locally Deformable Statistical Shape Model
Comparison of Global and Local Model
Summary and Outlook
References
Monte Carlo Expectation Maximization with Hidden Markov Models to Detect Functional Networks in Resting-State fMRI
Introduction
Hidden Markov Models of Functional Networks
Markov Prior Model
Likelihood Model
Monte Carlo EM
Sampling from the Posterior
Parameter Estimation
MCEM-Based Algorithm for Hidden-MRF Model Estimation
Results and Conclusion
References
DCE-MRI Analysis Using Sparse Adaptive Representations
Introduction
Methods
Dictionary Learning on Enhancement Curves
Unsupervised Segmentation
Results
Synthetic Data
Real Data
Conclusions
References
Learning Optical Flow Propagation Strategies Using Random Forests for Fast Segmentation in Dynamic 2D & 3D Echocardiography
Introduction
Method
Data Sets
Random Forests
Optical Flow
Experiments
Results and Discussion
Conclusion
References
A Non-rigid Registration Framework That Accommodates Pathology Detection
Introduction
Method
Bayesian Formulation
Intensity Matching and Tumor Probability Map
Results
Registration Results
Detection Results
Discussion and Conclusion
References
Segmentation Based Features for Lymph Node Detection from 3-D Chest CT
Introduction
Proposed Method for Detecting and Segmenting Lymph Nodes
Candidate Generation
Joint Detection and Segmentation
Results
Conclusion
References
Segmenting Hippocampus from 7.0 Tesla MR Images by Combining Multiple Atlases and Auto-Context Models
Introduction
Method
Learn the Classifiers in Each Atlas Space by Auto-Context Model
Multi-atlases Based Hippocampus Segmentation
Experimental Results
Qualitative Results
Quantitative Results
Conclusion
Reference
Texture Analysis by a PLS Based Method for Combined Feature Extraction and Selection
Introduction
Background
Partial Least Squares in Classification Problems
Feature Selection Based on PLS
The Dimensionality Reduction Method
Feature Selection and Extraction
Framework
Data Collection
Data Set Generation
ROI Definition
Classification and Evaluation
Experiments and Results
Results
Discussion and Conclusion
References
An Effective Supervised Framework for Retinal Blood Vessel Segmentation Using Local Standardisation and Bagging
Introduction
Method
Pixel Features
Classification with Bagging and Bayesian Classifier
Smoothing Central Reflex Artefacts
Experimental Results
Effect of Local Standardisation, Bagging and Smoothing
Comparison to Existing Methods
Conclusions
References
Automated Identification of Thoracolumbar Vertebrae Using Orthogonal Matching Pursuit
Introduction
Method
MIP Generation and Vertebra Detection
SOMP Based Classifiers
Experimental Results
Conclusions
References
Segmentation of Skull Base Tumors from MRI Using a Hybrid Support Vector Machine-Based Method
Introduction
Method
Overview
Pipeline of the HSVM Scheme
Parameter Selection
Experiment
Results
Conclusions
References
Spatial Nonparametric Mixed-Effects Model with Spatial-Varying Coefficients for Analysis of Populations
Introduction
Statistical Model: Nonparametric Approach
Model Estimation
Experiments and Results
Numerical Phantoms
Clinical Data: Predictive Model of Rectal Bleeding from Planned Dose Distribution
Conclusion
References
A Machine Learning Approach to Tongue Motion Analysis in 2D Ultrasound Image Sequences
Introduction
Methods
Audio-Based Temporal Alignment via Dynamic Time Warp
Explicit Characterization of Dynamic Gestures via 2D+Time Registration
Feature Extraction
Training the SVM Classifier
Experiments
Conclusions
References
Random Forest-Based Manifold Learning for Classification of Imaging Data in Dementia
Introduction
Methods
Random Forests for Classification
Manifold Learning Based on Random Forest Proximities
Data and Results
Imaging Data and Feature Extraction
Results
Discussion and Conclusions
References
Probabilistic Graphical Model of SPECT/MRI
Introduction
Methods
Probabilistic Graphical Model of SPECT
Probabilistic Graphical Model of MRI
Probabilistic Graphical Model of SPECT/MRI
Inference
Validation Study
Discussion
References
Directed Graph Based Image Registration
Introduction
Method
The Importance of Directionality in Registration
Directed Graph Based Pairwise Registration
MSA Based Groupwise Registration
Discussion
Experiments
Synthetic Dataset
Real Brain MR Image Datasets
Conclusion
References
Improving the Classification Accuracy of the Classic RF Method by Intelligent Feature Selection and Weighted Voting of Trees with Application to Medical Image Segmentation
Introduction
Classic RF in Medical Image Segmentation and Detection
Proposed Method
Training RF
Testing RF
Experimental Setup
Results
Discussion
References
Network-Based Classification Using Cortical Thickness of AD Patients
Introduction
Materials and Methods
Data Acquisition
Construction of Individual Networks
Classification of Individual Networks
Results
Classification Result of Individual Networks
Most Discriminative Features Selected by the Proposal Method
Conclusion
References
Anatomical Regularization on Statistical Manifolds for the Classification of Patients with Alzheimer's Disease
Introduction
Spatially Regularized SVM on Riemannian Manifold
Background
Regularization Operator
Spatial Regularization on Compact Riemannian Manifold
Spatial Proximity
Fisher Metric
Computing the Gram Matrix
Setting the Diffusion Parameter
Experiments and Results
Materials
Classification Experiments
Conclusion
References
Rapidly Adaptive Cell Detection Using Transfer Learning with a Global Parameter
Introduction
Method
Adaptive Boosting (AdaBoost)
Transfer Learning with AdaBoost (TaskTrAdaBoost)
Global Parameter Integration (GlobalTrAdaBoost)
Experiments
Evaluation Procedure
Detection Accuracy
Sensitivity of Global Parameter
Conclusion
References
Automatic Morphological Classification of Lung Cancer Subtypes with Boosting Algorithms for Optimizing Therapy
Introduction
Materials
Methods
Results
Discussion
References
Hot Spots Conjecture and Its Application to Modeling Tubular Structures
Introduction
The Second Laplace-Beltrami Eigenfunction
Hot Spots Conjecture Applied to Fiedler's Vector
Application: Mandible Growth Modeling
References
Fuzzy Statistical Unsupervised Learning Based Total Lesion Metabolic Activity Estimation in Positron Emission Tomography Images
Introduction
Related Works
Materials and Methods
Total Lesion Metabolic Activity and Statistical TLA
Stochastic Expectation Maximization and TLA Estimation
State-of-the-Art PET Delineation Schemes
Simulated Lesions
Quantitative Evaluation
Experiments
Simulated Lesions
Discussion and Conclusion
References
Predicting Clinical Scores Using Semi-supervised Multimodal Relevance Vector Regression
Introduction
Method
Multimodal RVR (M-RVR)
Semi-supervised Multimodal RVR (SM-RVR)
Results
Subjects
Experimental Setup
Experimental Results
Conclusion
References
Automated Cephalometric Landmark Localization Using Sparse Shape and Appearance Models
Introduction
Method
Bayesian Inference
Sparse Appearance Model
Sparse Shape Model
Edge Definition
Model Training
Model Fitting
Discretization
Markov Random Field Optimization
Experiments and Results
Conclusion
References
A Comparison Study of Inferences on Graphical Model for Registering Surface Model to 3D Image
Introduction
Surface Registration with Graphical Model
Surface Model Construction
Registration of Surface Model
Simulation Study of GS and NBP
Comparison of the Registration Accuracy
Construction of Statistical Model
Comparison Study of GS and NBP
Comparison Study of Structures of Graphical Models
Summary
References
A Large-Scale Manifold Learning Approach for Brain Tumor Progression Prediction
Introduction
Method
Data Preparation
Proposed System
Experiments and Results
Results for a Simulated Dataset - The Swiss Roll
Results from the Marked FLAIR Slices at Visit 1
Results from the Marked Post-contrast T1 Slices at Visit 1
Conclusion and Future Work
References
Automated Detection of Major Thoracic Structures with a Novel Online Learning Method
Introduction
Proposed Method
Histogram-Based Weak Learner
Learning Algorithm
Contributions
Experiments
Conclusion
References
Accurate Regression-Based 4D Mitral Valve Surface Reconstruction from 2D+t MRI Slices
Introduction
Methods
Regression-Based Surface Reconstruction (RSR)
Invariant Shape Descriptors
Ensembles of Additive Boosting Regressors
Mitral Valve Model Estimation from 2D+t CMR Slices
Experimental Setting and Results
MRI Acquisition Protocol Definition
Mitral Valve Surface Reconstruction
Results on Regression-Based Surface Reconstruction vs ASM
Conclusion
References
Tree Structured Model of Skin Lesion Growth Pattern via Color Based Cluster Analysis
Introduction
Method
Extraction of Weighted Center of Dark Pixels
Computing Radial Distance
Clustering and Shrinking
Multi-scale Tree Structure Construction
Feature Extraction
Implementation Detail
Results
Conclusion
References
Subject-Specific Cardiac Segmentation Based on Reinforcement Learning with Shape Instantiation
Introduction
Methods
Two-Layer Reinforcement Learning
Shape Instantiation for Subject-Specific Geometrical Constraint
Validation
Results
Conclusion
References
Faster Segmentation Algorithm for Optical Coherence Tomography Images with Guaranteed Smoothness
Introduction
Problem Description
Curvature and Mean Curvature
Single Surface Detection
The Algorithm
Experimental Results
Discussion and Conclusion
References
Automated Nuclear Segmentation of Coherent Anti-Stokes Raman Scattering Microscopy Images by Coupling Superpixel Context Information with Artificial Neural Networks
Introduction
Methodology
Experimental Validation
Conclusion and Future Work
References
3D Segmentation in CT Imagery with Conditional Random Fields and Histograms of Oriented Gradients
Introduction
Our Approach
Experiments and Results
Discussion and Conclusions
References
Automatic Human Knee Cartilage Segmentation from Multi-contrast MR Images Using Extreme Learning Machines and Discriminative Random Fields
Introduction
Related Works
Overview of the Work Presented
Methodology
Conditional and Discriminative Random Fields
Extreme Learning Machines
The Proposed Method
Experiments and Results
Description of Multi-contrast Human Knee MR Images and Preprocessing
Evaluation Metrics
Results
Conclusions
References
MultiCost: Multi-stage Cost-sensitive Classification of Alzheimer's Disease
Introduction
MultiCost
Cost-sensitive Feature Selection
Multimodal Data Fusion
Cost-sensitive Classification
Experiments
Experimental Settings
Results
Conclusion
References
Classifying Small Lesions on Breast MRI through Dynamic Enhancement Pattern Characterization
Introduction
Data
Methods
Lesion Annotation and Pre-processing
Texture Analysis
Classification
Results
Discussion
References
Computer-Aided Detection of Polyps in CT Colonography with Pixel-Based Machine Learning Techniques
Introduction
Methods
Manifold Learning
Classification in Manifold Space
Materials
Results
Optimal Nonlinear Embedding
Manifold Visualization
Classification Performance
Conclusion
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