Deep Learning and Data Labeling for Medical Applications

1. Front Matter

   Pages I-XIII

   PDF

2. Deep Learning in Medical Image Analysis

   1. Front Matter

      Pages 1-1

      PDF

   2. HEp-2 Cell Classification Using K-Support Spatial Pooling in Deep CNNs

      • Xian-Hua Han, Jianmei Lei, Yen-Wei Chen

      Pages 3-11

   3. Robust 3D Organ Localization with Dual Learning Architectures and Fusion

      • Xiaoguang Lu, Daguang Xu, David Liu

      Pages 12-20

   4. Cell Segmentation Proposal Network for Microscopy Image Analysis

      • Saad Ullah Akram, Juho Kannala, Lauri Eklund, Janne Heikkilä

      Pages 21-29

   5. Vessel Detection in Ultrasound Images Using Deep Convolutional Neural Networks

      • Erik Smistad, Lasse Løvstakken

      Pages 30-38

   6. Convolutional Neural Network for Reconstruction of 7T-like Images from 3T MRI Using Appearance and Anatomical Features

      • Khosro Bahrami, Feng Shi, Islem Rekik, Dinggang Shen

      Pages 39-47

   7. Fast Predictive Image Registration

      • Xiao Yang, Roland Kwitt, Marc Niethammer

      Pages 48-57

   8. Longitudinal Multiple Sclerosis Lesion Segmentation Using Multi-view Convolutional Neural Networks

      • Ariel Birenbaum, Hayit Greenspan

      Pages 58-67

   9. Automated Retinopathy of Prematurity Case Detection with Convolutional Neural Networks

      • Daniel E. Worrall, Clare M. Wilson, Gabriel J. Brostow

      Pages 68-76

   10. Fully Convolutional Network for Liver Segmentation and Lesions Detection

       • Avi Ben-Cohen, Idit Diamant, Eyal Klang, Michal Amitai, Hayit Greenspan

       Pages 77-85

   11. Deep Learning of Brain Lesion Patterns for Predicting Future Disease Activity in Patients with Early Symptoms of Multiple Sclerosis

       • Youngjin Yoo, Lisa W. Tang, Tom Brosch, David K. B. Li, Luanne Metz, Anthony Traboulsee et al.

       Pages 86-94

   12. De-noising of Contrast-Enhanced MRI Sequences by an Ensemble of Expert Deep Neural Networks

       • Ariel Benou, Ronel Veksler, Alon Friedman, Tammy Riklin Raviv

       Pages 95-110

   13. Three-Dimensional CT Image Segmentation by Combining 2D Fully Convolutional Network with 3D Majority Voting

       • Xiangrong Zhou, Takaaki Ito, Ryosuke Takayama, Song Wang, Takeshi Hara, Hiroshi Fujita

       Pages 111-120

   14. Medical Image Description Using Multi-task-loss CNN

       • Pavel Kisilev, Eli Sason, Ella Barkan, Sharbell Hashoul

       Pages 121-129

   15. Fully Automating Graf’s Method for DDH Diagnosis Using Deep Convolutional Neural Networks

       • David Golan, Yoni Donner, Chris Mansi, Jacob Jaremko, Manoj Ramachandran, on behalf of CUDL

       Pages 130-141

   16. Multi-dimensional Gated Recurrent Units for the Segmentation of Biomedical 3D-Data

       • Simon Andermatt, Simon Pezold, Philippe Cattin

       Pages 142-151

   17. Learning Thermal Process Representations for Intraoperative Analysis of Cortical Perfusion During Ischemic Strokes

       • Nico Hoffmann, Edmund Koch, Gerald Steiner, Uwe Petersohn, Matthias Kirsch

       Pages 152-160

   18. Automatic Slice Identification in 3D Medical Images with a ConvNet Regressor

       • Bob D. de Vos, Max A. Viergever, Pim A. de Jong, Ivana Išgum

       Pages 161-169

   19. Estimating CT Image from MRI Data Using 3D Fully Convolutional Networks

       • Dong Nie, Xiaohuan Cao, Yaozong Gao, Li Wang, Dinggang Shen

       Pages 170-178

This book constitutes the refereed proceedings of two workshops held at the 19th International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2016, in Athens, Greece, in October 2016: the First Workshop on Large-Scale Annotation of Biomedical Data and Expert Label Synthesis, LABELS 2016, and the Second International Workshop on Deep Learning in Medical Image Analysis, DLMIA 2016. The 28 revised regular papers presented in this book were carefully reviewed and selected from a total of 52 submissions. The 7 papers selected for LABELS deal with topics from the following fields: crowd-sourcing methods; active learning; transfer learning; semi-supervised learning; and modeling of label uncertainty.The 21 papers selected for DLMIA span a wide range of topics such as image description; medical imaging-based diagnosis; medical signal-based diagnosis; medical image reconstruction and model selection using deep learning techniques; meta-heuristic techniques for fine-tuning parameter in deep learning-based architectures; and applications based on deep learning techniques.

• active learning
• deep learning
• human-computer interaction
• label uncertainty
• medical image analysis
• anatomical structure segmentation
• cell detection
• clinical prediction
• computer aided diagnosis
• convolutional neural network
• crowdsourcing
• domain adaptation
• MRI
• multi-label annotation
• neurosurgery
• parameter approximation
• semantic description
• semi-supervised learning
• transfer learning
• machine learning

• University of Adelaide, Adelaide, Australia

  Gustavo Carneiro

• Technical University of Munich, Garching, Germany

  Diana Mateus, Loïc Peter

• University of Queensland, St Lucia, Australia

  Andrew Bradley

• Universidade do Porto, Porto, Portugal

  João Manuel R. S. Tavares, Jaime S. Cardoso

• University of Oxford, Oxford, United Kingdom

  Vasileios Belagiannis

• Universidade Estadual Paulista, Bauru, Brazil

  João Paulo Papa

• Instituto Superior Técnico, Lisbon, Portugal

  Jacinto C. Nascimento

• Delft University of Technology, Delft, The Netherlands

  Marco Loog

• University of South Australia, Adelaide, Australia

  Zhi Lu

• Google DeepMind, London, United Kingdom

  Julien Cornebise

Policies and ethics