Machine Learning in Medical Imaging 8th International Workshop, MLMI 2017, Held in Conjunction with MICCAI 2017, Quebec City, QC, Canada, September 10, 2017, Proceedings

This book constitutes the refereed proceedings of the 8th International Workshop on Machine Learning in Medical Imaging, MLMI 2017, held in conjunction with MICCAI 2017, in Quebec City, QC, Canada, in September 2017. The 44 full papers presented in this volume were carefully reviewed and selected fr...

Full description

Saved in:
Bibliographic Details
Main Authors Wang, Qian, Shi, Yinghuan, Suk, Heung-Il, Suzuki, Kenji
Format eBook Conference Proceeding
LanguageEnglish
Published Cham Springer Nature 2017
Springer International Publishing AG
Springer International Publishing
Springer
Edition1
SeriesLecture Notes in Computer Science
Subjects
Artificial Intelligence
Computer programming, programs, data
Computer Science
Data Mining and Knowledge Discovery
Diagnostic imaging
Health Informatics
Image Processing and Computer Vision
Machine learning
Software engineering
Software Engineering/Programming and Operating Systems
Online AccessGet full text

Cover

Table of Contents:
  • 3D U-net with Multi-level Deep Supervision: Fully Automatic Segmentation of Proximal Femur in 3D MR Images
  • Intro -- Preface -- Organization -- Contents -- From Large to Small Organ Segmentation in CT Using Regional Context -- 1 Introduction -- 2 Methods -- 2.1 Vantage Point Forest -- 2.2 Initial Labelling -- 2.3 Iterated Forest with Regional Context Descriptors -- 2.4 Final Shape Voting (SV) -- 3 Experiments -- 4 Conclusion -- References -- Motion Corruption Detection in Breast DCE-MRI -- Abstract -- 1 Introduction -- 2 Methodology -- 2.1 Data Acquisition -- 2.2 Generating Deformation Estimates for Unlabeled Images -- 2.3 Preprocessing Data -- 2.4 Training a Supervised Learning Model -- 3 Results -- 3.1 Comparing Learning Models -- 3.2 Visualizing Neural Networks -- 4 Conclusion -- References -- Detection and Localization of Drosophila Egg Chambers in Microscopy Images -- 1 Introduction -- 2 Methodology -- 2.1 Superpixel Segmentation -- 2.2 Center Detection -- 2.3 Ellipse Fitting and Segmentation -- 3 Materials and Experiments -- 3.1 Center Detection Performance -- 3.2 Egg Chamber Detection -- 4 Conclusions -- References -- Growing a Random Forest with Fuzzy Spatial Features for Fully Automatic Artery-Specific Coronary Calcium Scoring -- 1 Introduction -- 2 Material and Methods -- 2.1 Data -- 2.2 CAC Candidates -- 2.3 Atlas Creation -- 2.4 Feature Generation -- 3 Experiments and Results -- 4 Discussion and Conclusions -- References -- Atlas of Classifiers for Brain MRI Segmentation -- 1 Introduction -- 2 The Atlas of Classifier Approach -- 2.1 AoC Model Overview -- 2.2 Multi-Class Segmentation -- 2.3 Features -- 2.4 Registration -- 3 Experimental Results -- 4 Discussion -- References -- Dictionary Learning and Sparse Coding-Based Denoising for High-Resolution Task Functional Connectivity MRI Analysis -- 1 Introduction -- 2 Methods -- 2.1 Dataset -- 2.2 Dictionary Learning and Sparse Coding (DLSC)-Based Denoising -- 3 Results -- 4 Discussion
  • Finding Dense Supervoxel Correspondence of Cone-Beam Computed Tomography Images -- 1 Introduction -- 2 Methods -- 2.1 Clustering Forest -- 2.2 Tree Pruning -- 3 Experiments -- 3.1 Correspondence Results -- 4 Conclusion -- References -- Multi-scale Volumetric ConvNet with Nested Residual Connections for Segmentation of Anterior Cranial Base -- 1 Introduction -- 2 Methods -- 2.1 Network Architecture -- 2.2 Training -- 3 Experiments -- 4 Discussion and Conclusion -- References -- Feature Learning and Fusion of Multimodality Neuroimaging and Genetic Data for Multi-status Dementia Diagnosis -- 1 Introduction -- 2 Methodology -- 3 Experimental Results and Analysis -- 3.1 Dataset -- 3.2 Experimental Setup -- 4 Conclusion -- References -- 3D Convolutional Neural Networks with Graph Refinement for Airway Segmentation Using Incomplete Data Labels -- 1 Introduction -- 2 Method -- 2.1 3D FCN Architecture -- 2.2 Training with Incomplete Labeling -- 2.3 Graph-Based Refinement -- 3 Experiments and Results -- 4 Conclusion -- References -- Efficient Groupwise Registration for Brain MRI by Fast Initialization -- Abstract -- 1 Introduction -- 2 Method -- 2.1 Training Dataset Augmentation -- 2.2 Efficient Groupwise Registration by Fast Initialization -- 3 Experiments and Results -- 4 Conclusion -- References -- Sparse Multi-view Task-Centralized Learning for ASD Diagnosis -- Abstract -- 1 Introduction -- 2 Method -- 2.1 Sparse Multi-view Task-Centralized (Sparse-MVTC) Learning -- 2.2 Iterative Optimization in Sparse-MVTC -- 2.3 Ensemble Implementation of Sparse-MVTC -- 3 Experimental Results -- 3.1 Experimental Settings -- 3.2 Comparisons with State-of-the-Art Methods -- 4 Conclusion -- References -- Inter-subject Similarity Guided Brain Network Modeling for MCI Diagnosis -- Abstract -- 1 Introduction -- 2 Methods -- 2.1 GSR for Brain Network Modeling
  • A Point Says a Lot: An Interactive Segmentation Method for MR Prostate via One-Point Labeling -- 1 Introduction -- 2 Our Method -- 3 Experimental Results -- 4 Conclusion -- References -- Collage CNN for Renal Cell Carcinoma Detection from CT -- 1 Introduction -- 2 Materials and Methods -- 2.1 Data -- 2.2 Collage Representation of 3D Image Data -- 2.3 Pathological vs Healthy Kidney Classification -- 3 Results -- 4 Conclusions -- References -- Aggregating Deep Convolutional Features for Melanoma Recognition in Dermoscopy Images -- Abstract -- 1 Introduction -- 2 Methodology -- 2.1 Image Preprocessing and Data Augmentation -- 2.2 Extraction of Local Convolutional Features -- 2.3 Fisher Vector Encoding Strategy -- 2.4 Kernel-Based Classification -- 3 Experimental Setting and Results -- 4 Conclusion -- Acknowledgment -- References -- Localizing Cardiac Structures in Fetal Heart Ultrasound Video -- 1 Introduction -- 2 Partitioned Particle Filters -- 3 A Fourier Model for Structure Trajectories -- 4 A Filtering Architecture for Structure Localization -- 4.1 Structure Visibility Prediction Potential, ga(st st-1 ) -- 4.2 Structure Position Prediction Potential, a(st st-1 ) -- 4.3 Observation Potential, Da(st,zt) -- 5 Experiments and Results -- 6 Conclusions -- References -- Deformable Registration Through Learning of Context-Specific Metric Aggregation -- 1 Introduction -- 2 The Deformable Registration Problem -- 3 Learning the Parameters -- 4 Results and Discussion -- References -- Segmentation of Craniomaxillofacial Bony Structures from MRI with a 3D Deep-Learning Based Cascade Framework -- 1 Introduction -- 2 Methods -- 2.1 Data Acquisition and Preprocessing -- 2.2 Coarse Segmentation with Anatomical Constraint -- 2.3 Fine-Grained Segmentation -- 2.4 Implementation Details -- 3 Experiments and Results -- 4 Discussion and Conclusions -- References
  • References -- Yet Another ADNI Machine Learning Paper? Paving the Way Towards Fully-Reproducible Research on Classification of Alzheimer's Disease -- 1 Introduction -- 2 Material and Methods -- 2.1 Dataset -- 2.2 A Standardized Data Structure -- 2.3 Preprocessing and Feature Extraction Pipelines -- 2.4 Classification Methods -- 2.5 Validation -- 3 Results -- 4 Conclusions -- References -- Multi-factorial Age Estimation from Skeletal and Dental MRI Volumes -- 1 Introduction -- 2 Method -- 3 Experimental Setup and Results -- 4 Discussion and Conclusion -- References -- Automatic Classification of Proximal Femur Fractures Based on Attention Models -- 1 Introduction -- 2 Method -- 2.1 Attention Model -- 3 Experimental Validation -- 4 Conclusion -- References -- Joint Supervoxel Classification Forest for Weakly-Supervised Organ Segmentation -- 1 Introduction -- 2 Method -- 2.1 Object-Sized Supervoxels -- 2.2 Joint Supervoxel Random Classification Forest -- 2.3 Weakly-Supervised Segmentation -- 3 Experiments and Results -- 4 Discussion and Conclusion -- References -- Accurate and Consistent Hippocampus Segmentation Through Convolutional LSTM and View Ensemble -- 1 Introduction -- 2 Method -- 2.1 U-Seg-Net+CLSTM -- 3 Implementation Details -- 4 Experimental Results -- 5 Conclusion -- References -- STAR: Spatio-Temporal Architecture for Super-Resolution in Low-Dose CT Perfusion -- 1 Introduction -- 2 Methodology -- 3 Experiments and Results -- 4 Conclusion -- References -- Classification of Alzheimer's Disease by Cascaded Convolutional Neural Networks Using PET Images -- Abstract -- 1 Introduction -- 2 Materials and Proposed Method -- 2.1 Image Acquisition and Processing -- 2.2 Feature Extraction with Multiple 3D CNNs -- 2.3 Cascaded Ensemble Classification for AD Diagnosis -- 3 Experimental Results -- 4 Conclusions -- Acknowledgement -- References
  • 2.2 Inter-subject Similarity-Guided GSR for Brain Network Modeling -- 3 Experiments -- 3.1 Data Preprocessing -- 3.2 Performance Evaluation -- 3.3 Experimental Results -- 4 Conclusion -- Acknowledgements -- References -- Scalable and Fault Tolerant Platform for Distributed Learning on Private Medical Data -- 1 Introduction -- 2 Methodology -- 3 Results and Discussions -- 4 Conclusions -- References -- Triple-Crossing 2.5D Convolutional Neural Network for Detecting Neuronal Arbours in 3D Microscopic Images -- 1 Introduction -- 2 Methods -- 2.1 Scale-Space Distance Transform of Neuronal Centreline -- 2.2 Triple-Crossing Patches for 2.5D CNN -- 2.3 Triple-Crossing 2.5D CNNs with Residual-Blocks -- 2.4 Gradient-Based Intensity Normalisation -- 3 Experiments and Results -- 4 Conclusion -- References -- Longitudinally-Consistent Parcellation of Infant Population Cortical Surfaces Based on Functional Connectivity -- Abstract -- 1 Introduction -- 2 Methods -- 3 Results -- 4 Conclusion -- References -- Gradient Boosted Trees for Corrective Learning -- 1 Introduction -- 2 Methods -- 2.1 Host Segmentation Methods -- 2.2 Construction of Candidate Locations -- 2.3 Raw Feature Set -- 2.4 Feature Engineering -- 2.5 Gradient Boosted Trees -- 3 Experimental Methods -- 3.1 Data and Cross-Validation -- 3.2 Evaluation Metrics -- 4 Results -- 5 Discussion -- References -- Self-paced Convolutional Neural Network for Computer Aided Detection in Medical Imaging Analysis -- Abstract -- 1 Introduction -- 2 Materials and Methods -- 2.1 Method Overview -- 2.2 Architecture of the CNN Applied in the Framework -- 2.3 Bootstrapping Module for Virtual Sample Selection -- 3 Experimental Results -- 3.1 Data Acquisition and Preprocessing -- 3.2 Performance Comparisons -- 3.3 Time Cost for the Virtual Sample Selection -- 4 Conclusion and Discussion -- References