
Machine Learning in Medical Imaging
Description
Alles über E-Books | Antworten auf Fragen rund um E-Books, Kopierschutz und Dateiformate finden Sie in unserem Info- & Hilfebereich.
This book constitutes the refereed proceedings of the 7th International Workshop on Machine Learning in Medical Imaging, MLMI 2016, held in conjunction with MICCAI 2016, in Athens, Greece, in October 2016.
The 38 full papers presented in this volume were carefully reviewed and selected from 60 submissions.
The main aim of this workshop is to help advance scientific research within the broad field of machine learning in medical imaging. The workshop focuses on major trends and challenges in this area, and presents works aimed to identify new cutting-edge techniques and their use in medical imaging.
More details
Other editions
Additional editions

Content
- Intro
- Preface
- Organization
- Contents
- Identifying High Order Brain Connectome Biomarkers via Learning on Hypergraph
- Abstract
- 1 Introduction
- 2 Method
- 2.1 Encode Subject-Wise Relationship in Hypergraph
- 2.2 Discover High Order Brain Connectome Patterns by Hypergraph Learning
- 3 Experiments
- 3.1 Critical Subnetworks Learned by Hypergraph Inference
- 3.2 Identification of ASD Subjects with the Learned Subnetwork
- 4 Conclusion
- References
- Bilateral Regularization in Reproducing Kernel Hilbert Spaces for Discontinuity Preserving Image Registration
- 1 Introduction
- 2 Background
- 3 Method
- 3.1 Bilateral Regularizer
- 3.2 Anisotropic Kernel
- 4 Results
- 5 Conclusion
- References
- Do We Need Large Annotated Training Data for Detection Applications in Biomedical Imaging? A Case Study in Renal Glomeruli Detection
- 1 Introduction
- 1.1 Contribution
- 2 Experimental Study
- 2.1 Image Dataset
- 2.2 Proposed Architecture
- 2.3 Image Representations and Evaluation Details
- 2.4 Fraction of Mislabeled Training Data
- 2.5 Variability in Positive and Negative Class
- 2.6 Detection Results
- 3 Discussion
- References
- Building an Ensemble of Complementary Segmentation Methods by Exploiting Probabilistic Estimates
- 1 Introduction
- 2 Method
- 2.1 Regional Learning-Based Segmentation
- 2.2 Ensemble Segmentation Based on Probabilistic Estimates
- 3 Experiments
- 3.1 IBSR Dataset
- 3.2 NeoBrainS12 Challenge
- 4 Conclusions
- References
- Learning Appearance and Shape Evolution for Infant Image Registration in the First Year of Life
- Abstract
- 1 Introduction
- 2 Methods
- 2.1 Integrated Random Forest Regression and Auto-Context Model
- 2.2 Register New Infant Image with Two Learned Models
- 3 Experiments
- 4 Conclusion
- References
- Detecting Osteophytes in Radiographs of the Knee to Diagnose Osteoarthritis
- 1 Introduction
- 2 Background
- 2.1 Osteoarthritis Grading
- 2.2 Automated Methods
- 2.3 Shape Modelling and Matching
- 3 Methods
- 3.1 Osteophyte Features
- 4 Experiments
- 4.1 Data
- 4.2 Classification Experiments
- 4.3 Osteophyte Detection
- 4.4 OA vs Non-OA
- 4.5 Multi-class Experiments
- 5 Discussion and Conclusion
- References
- Direct Estimation of Fiber Orientations Using Deep Learning in Diffusion Imaging
- 1 Introduction
- 2 Material
- 3 Deep Learning
- 4 Using CNN for Estimating the fODF
- 4.1 Class Definition
- 4.2 Pre-processing
- 4.3 The Architecture
- 5 Results
- 6 Discussion
- 7 Conclusion
- References
- Segmentation of Perivascular Spaces Using Vascular Features and Structured Random Forest from 7T MR Image
- 1 Introduction
- 2 Method
- 2.1 Region-of-Interest Generation
- 2.2 Voxel Sampling Strategy
- 2.3 Feature Extraction
- 2.4 Structured Random Forest
- 3 Experiments, Results and Discussions
- 4 Conclusion
- References
- Dual-Layer Groupwise Registration for Consistent Labeling of Longitudinal Brain Images
- Abstract
- 1 Introduction
- 2 Method
- 2.1 Groupwise Time-Serial Image Registration
- 2.2 Manifold-Guided Registration of Atlases and Subject Image Sequence
- 2.3 Consistent ROI Labeling of Longitudinal Image Sequence
- 3 Experimental Results
- 3.1 Evaluation of Longitudinal Labeling Consistency
- 3.2 Evaluation of Longitudinal Labeling Accuracy
- 4 Conclusion
- References
- Joint Discriminative and Representative Feature Selection for Alzheimer's Disease Diagnosis
- 1 Introduction
- 2 Method
- 2.1 Task-Oriented Supervised Feature Selection
- 2.2 Representation-Oriented Unsupervised Feature Selection
- 2.3 Proposed Objective Function
- 3 Experimental Results
- 3.1 Classification Results
- 3.2 Most Discriminative Brain Regions
- 4 Conclusion
- References
- Patch-Based Hippocampus Segmentation Using a Local Subspace Learning Method
- Abstract
- 1 Introduction
- 2 Method
- 2.1 Multi-atlas Based Segmentation Method
- 2.2 Local Subspace Learning Based Patch-Wise Label Propagation Method
- 3 Experiments
- 4 Conclusion
- References
- Improving Single-Modal Neuroimaging Based Diagnosis of Brain Disorders via Boosted Privileged Information Learning Framework
- Abstract
- 1 Introduction
- 2 Boosted-LUPI-Based Classification Framework
- 2.1 Random Subspace Feature Sampling
- 2.2 Privileged Information Learning
- 2.3 Multiple Kernel Boosting Learning
- 3 Experiment and Results
- 3.1 Experiment on MLSP Schizophrenia Dataset
- 3.2 Experiment on ADNI Dataset
- 4 Conclusion
- Acknowledgments
- References
- A Semi-supervised Large Margin Algorithm for White Matter Hyperintensity Segmentation
- 1 Introduction
- 2 Unsupervised One-Class Learning
- 3 Semi-supervised Large Margin Algorithm
- 3.1 Learning Model
- 3.2 Algorithm
- 4 Results
- 5 Conclusion
- References
- Deep Ensemble Sparse Regression Network for Alzheimer's Disease Diagnosis
- 1 Introduction
- 2 Materials and Image Processing
- 3 Deep Ensemble Sparse Regression Network
- 3.1 Sparse Linear/Logistic Regression
- 3.2 Deep Convolutional Neural Network for Classification
- 4 Experimental Settings and Results
- 4.1 Experimental Settings
- 4.2 Performance Comparison
- 5 Conclusion
- References
- Learning Representation for Histopathological Image with Quaternion Grassmann Average Network
- Abstract
- 1 Introduction
- 2 Quaternion Grassmann Average Network
- 2.1 Quaternion Grassmann Average Algorithm
- 2.2 QGA Network (QGANet)
- 2.3 QGANet-Based Classification Framework
- 3 Experiment and Results
- 3.1 Experiments
- 3.2 Results
- 4 Discussion and Conclusion
- Acknowledgments
- References
- Learning Global and Cluster-Specific Classifiers for Robust Brain Extraction in MR Data
- 1 Introduction
- 2 Methods
- 2.1 Supervised Learning via Global Random Forests
- 2.2 Learning Cluster-Specific Classifiers
- 3 Results
- 4 Discussions
- References
- Cross-Modality Anatomical Landmark Detection Using Histograms of Unsigned Gradient Orientations and Atlas Location Autocontext
- 1 Introduction
- 2 Methodology
- 3 Experiments
- 4 Conclusion
- References
- Multi-label Deep Regression and Unordered Pooling for Holistic Interstitial Lung Disease Pattern Detection
- 1 Introduction
- 2 Methods
- 2.1 CNN Architecture for Multi-label ILD Regression
- 2.2 Unordered Pooling Regression via Fisher Vector Encoding
- 3 Experiments and Discussion
- 4 Conclusion
- References
- Segmentation-Free Estimation of Kidney Volumes in CT with Dual Regression Forests
- 1 Introduction
- 2 Methods
- 2.1 Image Representation
- 2.2 Learning and Prediction
- 2.3 Kidney Volume Estimation
- 3 Validation Setup
- 4 Results
- 5 Conclusions
- References
- Multi-resolution-Tract CNN with Hybrid Pretrained and Skin-Lesion Trained Layers
- 1 Introduction
- 2 Methods
- 3 Results
- 4 Conclusions
- References
- Retinal Image Quality Classification Using Saliency Maps and CNNs
- 1 Introduction
- 2 Methods
- 2.1 Saliency Model
- 2.2 CNN Architecture
- 2.3 Training the CNN
- 2.4 Image Quality Classification
- 3 Experiments and Results
- 3.1 Dataset Description
- 4 Conclusion
- References
- Unsupervised Discovery of Emphysema Subtypes in a Large Clinical Cohort
- 1 Introduction
- 2 Model
- 3 Empirical Results
- 3.1 Results
- 4 Conclusions
- References
- Tree-Based Transforms for Privileged Learning
- 1 Introduction
- 2 Method
- 2.1 Building a Support Forest Using Fm
- 2.2 Growing Cross-Modality Tree-Based Feature Transforms
- 2.3 Implementation Details
- 3 Evaluation Data and Methods
- 4 Results
- 5 Conclusions and Future Work
- References
- Automated 3D Ultrasound Biometry Planes Extraction for First Trimester Fetal Assessment
- Abstract
- 1 Introduction
- 2 Related Work
- 3 Localization of the Fetus in the Sagittal Plane
- 3.1 Edge Detection Using Structured Random Forests
- 3.2 Detection of the Fetus Region-of-Interest
- 4 Detection of the Best Head and Abdominal Planes
- 4.1 Fetal-Partitioning via Transfer Learning CNNs
- 4.2 Detection of Best Plane for Fetal Head and Abdomen Biometry
- 5 Experiments
- 6 Results
- 6.1 Localization of the Fetus in the Sagittal Plane
- 6.2 Fetal-Partitioning and Extraction of Biometry Planes
- 7 Discussion and Conclusion
- References
- Learning for Graph-Based Sensorless Freehand 3D Ultrasound
- 1 Introduction
- 2 Method
- 2.1 Rigid Motion Estimation
- 2.2 Graph-Based Trajectory Estimation
- 2.3 Learning to Characterize Measurement Error
- 3 Experiments and Results
- 3.1 Data Acquisition
- 3.2 Evaluation of Probe Trajectory Estimation
- 4 Conclusion
- References
- Learning-Based 3T Brain MRI Segmentation with Guidance from 7T MRI Labeling
- 1 Introduction
- 2 Materials and Methods
- 2.1 Proposed Algorithm
- 2.2 Appearance and Context Features
- 3 Experiments
- 3.1 Comparison with Other Methods on 10 Subjects
- 4 Conclusion
- References
- Transductive Maximum Margin Classification of ADHD Using Resting State fMRI
- Abstract
- 1 Introduction
- 2 Method
- 2.1 Maximum Margin Classification (MMC)
- 2.2 Smoothness Constraints
- 2.3 Transductive-MMC
- 3 Results
- 4 Conclusion
- Acknowledgements
- References
- Automatic Hippocampal Subfield Segmentation from 3T Multi-modality Images
- 1 Introduction
- 2 Motivation and Main Framework
- 3 Relationship Feature Calculation and Updating
- 4 Experiments
- 5 Conclusion
- References
- Regression Guided Deformable Models for Segmentation of Multiple Brain ROIs
- 1 Introduction
- 2 Method
- 2.1 Main Framework
- 2.2 Deformation Field Estimation
- 2.3 Regression Guided Deformable Segmentation
- 2.4 ROI Merging
- 3 Experiments
- 4 Conclusion
- References
- Functional Connectivity Network Fusion with Dynamic Thresholding for MCI Diagnosis
- 1 Introduction
- 2 Method
- 2.1 Data Preprocessing and Network Construction
- 2.2 Dynamical Network Thresholding
- 2.3 Network Fusion
- 2.4 Classification
- 3 Experimental Results
- 3.1 Experimental Setup
- 3.2 Classification Performance
- 4 Conclusion
- References
- Sparse Coding Based Skin Lesion Segmentation Using Dynamic Rule-Based Refinement
- 1 Introduction
- 2 Related Work
- 3 System Overview
- 3.1 Single-Scale Lesion Confidence Map
- 3.2 Dynamic Rule-Based Refinement
- 3.3 Multi-scale Fusion
- 4 Experimental Results
- 4.1 Datasets
- 4.2 Performance Measure and Parameters Setting
- 5 Conclusion
- References
- Structure Fusion for Automatic Segmentation of Left Atrial Aneurysm Based on Deep Residual Networks
- 1 Introduction
- 2 Method
- 3 Experiments and Results
- 4 Conclusion
- References
- Tumor Lesion Segmentation from 3D PET Using a Machine Learning Driven Active Surface
- 1 Introduction
- 2 Method
- 2.1 Machine Learning: Features and Classification
- 2.2 Convex Segmentation with Learned Likelihoods
- 3 Results
- 4 Conclusion
- References
- Iterative Dual LDA: A Novel Classification Algorithm for Resting State fMRI
- 1 Introduction
- 2 Methods
- 2.1 Proposed Algorithm
- 2.2 Simulated Data
- 2.3 Parkinson's Disease Data
- 3 Results and Discussion
- 3.1 Simulated Data
- 3.2 Parkinson's Disease Data
- 4 Conclusion
- References
- Mitosis Detection in Intestinal Crypt Images with Hough Forest and Conditional Random Fields
- Abstract
- 1 Introduction
- 2 Problem Definition
- 3 Methods
- 3.1 Cell Detection with Hough Forest
- 3.2 Joint Detection of Mother and Daughters Using CRF
- 4 Results
- 4.1 Experiment and Dataset Description
- 4.2 Evaluation of Cell Detection
- 4.3 Evaluation of Mitosis Detection
- 5 Discussion
- References
- Comparison of Multi-resolution Analysis Patterns for Texture Classification of Breast Tumors Based on DCE-MRI
- Abstract
- 1 Introduction
- 2 Multi-resolution Image Analysis
- 3 Materials and Methods
- 3.1 DCE MRI Data
- 3.2 Extraction of Texture Features
- 3.3 Classification
- 4 Results
- 5 Conclusion
- Acknowledgements
- References
- Novel Morphological Features for Non-mass-like Breast Lesion Classification on DCE-MRI
- 1 Introduction
- 2 Materials and Methods
- 2.1 Imaging Technique and Data Set
- 2.2 Feature Extraction
- 3 Results and Evaluations
- 3.1 Classification Results with Feature Selection
- 4 Conclusion and Discussion
- References
- Fast Neuroimaging-Based Retrieval for Alzheimer's Disease Analysis
- 1 Introduction
- 2 Proposed Framework
- 2.1 Landmark Detection
- 2.2 Landmark Selection
- 2.3 Hashing Construction
- 2.4 Testing Stage
- 3 Experiments
- 3.1 Experimental Results of Landmark Selection
- 3.2 Experimental Results of Hashing
- 4 Conclusion
- References
- Author Index
System requirements
File format: PDF
Copy protection: Watermark-DRM (Digital Rights Management)
System requirements:
- Computer (Windows; MacOS X; Linux): Use the free software Adobe Reader, Adobe Digital Editions, or any other PDF viewer of your choice (see eBook Help).
- Tablet/Smartphone (Android; iOS): Install the free app Adobe Digital Editions or another reading app for eBooks, e.g., PocketBook (see eBook Help).
- E-reader: Bookeen, Kobo, Pocketbook, Sony, Tolino and many more (only limited: Kindle).
The file format PDF always displays a book page identically on any hardware. This makes PDF suitable for complex layouts such as those used in textbooks and reference books (images, tables, columns, footnotes). Unfortunately, on the small screens of e-readers or smartphones, PDFs are rather annoying, requiring too much scrolling.
This eBook uses Watermark-DRM, a „soft” copy protection. This means that there are no technical restrictions to prevent illegal distribution. However, there is a personalised watermark embedded in the eBook that can be used to identify the purchaser of the eBook in the event of misuse and to provide evidence for legal purposes.
For more information, see our eBook Help page.