Medical Image Recognition, Segmentation and Parsing

This book describes the technical problems and solutions for automatically recognizing and parsing a medical image into multiple objects, structures, or anatomies. It gives all the key methods, including state-of- the-art approaches based on machine learning, for recognizing or detecting, parsing or segmenting, a cohort of anatomical structures from a medical image.

Written by top experts in Medical Imaging, this book is ideal for university researchers and industry practitioners in medical imaging who want a complete reference on key methods, algorithms and applications in medical image recognition, segmentation and parsing of multiple objects.

Learn:

• Research challenges and problems in medical image recognition, segmentation and parsing of multiple objects
• Methods and theories for medical image recognition, segmentation and parsing of multiple objects
• Efficient and effective machine learning solutions based on big datasets
• Selected applications of medical image parsing using proven algorithms

• Provides a comprehensive overview of state-of-the-art research on medical image recognition, segmentation, and parsing of multiple objects
• Presents efficient and effective approaches based on machine learning paradigms to leverage the anatomical context in the medical images, best exemplified by large datasets
• Includes algorithms for recognizing and parsing of known anatomies for practical applications

Industry practitioners and university researchers in medical imaging.

• Foreword
• Acknowledgments
• Chapter 1: Introduction to Medical Image Recognition, Segmentation, and Parsing
  • Abstract
  • 1.1 Introduction
  • 1.2 Challenges and Opportunities
  • 1.3 Rough-to-Exact Object Representation
  • 1.4 Simple-to-Complex Probabilistic Modeling
  • 1.5 Medical Image Recognition Using Machine Learning Methods
  • 1.6 Medical Image Segmentation Methods
  • 1.7 Conclusions
  • Recommended Notations
• Part 1: Automatic Recognition and Detection Algorithms
  • Chapter 2: A Survey of Anatomy Detection
    • Abstract
    • 2.1 Introduction
    • 2.2 Methods for Detecting an Anatomy
    • 2.3 Methods for Detecting Multiple Anatomies
    • 2.4 Conclusions
  • Chapter 3: Robust Multi-Landmark Detection Based on Information Theoretic Scheduling
    • Abstract
    • 3.1 Introduction
    • 3.2 Literature Review
    • 3.3 Methods
    • 3.4 Applications
    • 3.5 Conclusion
  • Chapter 4: Landmark Detection Using Submodular Functions
    • Abstract
    • 4.1 Introduction
    • 4.2 Multiple Landmark Detection
    • 4.3 Finding the Anchor Landmark
    • 4.4 Coarse-to-Fine Detection
    • 4.5 Discussion
    • 4.6 Summary
  • Chapter 5: Random Forests for Localization of Spinal Anatomy
    • Abstract
    • 5.1 Introduction
    • 5.2 Anatomy Localization Using Random Forests
    • 5.3 Experimental Comparison
    • 5.4 Conclusion
  • Chapter 6: Integrated Detection Network for Multiple Object Recognition
    • Abstract
    • 6.1 Introduction
    • 6.2 Independent Multiobject Recognition
    • 6.3 Sequential Sampling for Multiobject Recognition
    • 6.4 Applications
    • 6.5 Conclusions
  • Chapter 7: Organ Detection Using Deep Learning
    • Abstract
    • Acknowledgments
    • 7.1 Introduction
    • 7.2 Related Literature
    • 7.3 Methods
    • 7.4 Experiments
    • 7.5 Conclusions
• Part 2: Automatic Segmentation and Parsing Algorithms
  • Chapter 8: A Probabilistic Framework for Multiple Organ Segmentation Using Learning Methods and Level Sets
    • Abstract
    • 8.1 Introduction
    • 8.2 Literature Review
    • 8.3 Proposed Method
    • 8.4 Experimental Results
    • 8.5 Conclusions
  • Chapter 9: LOGISMOS: A Family of Graph-Based Optimal Image Segmentation Methods
    • Abstract
    • Acknowledgments
    • 9.1 Introduction
    • 9.2 Layered Optimal Graph Image Segmentation of Multiple Objects and Surfaces
    • 9.3 Multiobject Multisurface LOGISMOS for Knee Joint Segmentation
    • 9.4 Multisurface Multiimage Co-Segmentation: Retinal OCT
    • 9.5 Complex Multisurface Geometry: LOGISMOS-B for Brain Cortex
    • 9.6 Future Directions
  • Chapter 10: A Context Integration Framework for Rapid Multiple Organ Parsing
    • Abstract
    • 10.1 Introduction
    • 10.2 Related Literature
    • 10.3 Methods
    • 10.4 Object Context
    • 10.5 Automatic Mesh Vertex Selection
    • 10.6 Incomplete Annotations
    • 10.7 Experiments
    • 10.8 Conclusions
  • Chapter 11: Multiple-Atlas Segmentation in Medical Imaging
    • Abstract
    • 11.1 Introduction
    • 11.2 Atlas Selection
    • 11.3 Image Registration
    • 11.4 Label Fusion
    • 11.5 Conclusions
  • Chapter 12: An Overview of the Multi-Object Geometric Deformable Model Approach in Biomedical Imaging
    • Abstract
    • Acknowledgments
    • 12.1 Introduction
    • 12.2 Methods
    • 12.3 Segmentation of a Multi-Object Hand
    • 12.4 Applications
    • 12.5 Discussion and Conclusion
  • Chapter 13: Robust and Scalable Shape Prior Modeling via Sparse Representation and Dictionary Learning
    • Abstract
    • 13.1 Introduction
    • 13.2 Related Work
    • 13.3 Segmentation Framework
    • 13.4 Sparse Shape Composition
    • 13.5 Dictionary Learning for Compact Representations
    • 13.6 Mesh Partition for Local Sparse Shape Composition
    • 13.7 Discussion
• Part 3: Recognition, Segmentation and Parsing of Specific Objects
  • Chapter 14: Semantic Parsing of Brain MR Images
    • Abstract
    • 14.1 Introduction
    • 14.2 Atlas-Based Segmentation Methods
    • 14.3 Brain Atlases From MR Images
    • 14.4 Conclusions
  • Chapter 15: Parsing of the Lungs and Airways
    • Abstract
    • 15.1 Introduction
    • 15.2 Overview
    • 15.3 Lung and Airway Segmentation
    • 15.4 Airway Tree Parsing
    • 15.5 Lobar Segmentation
    • 15.6 Quantification of Airway Dimensions
    • 15.7 Applications
    • 15.8 Conclusion
  • Chapter 16: Aortic and Mitral Valve Modeling From Multi-Modal Image Data
    • Abstract
    • 16.1 Introduction
    • 16.2 Physiological Model of the Heart Valves
    • 16.3 Patient-Specific Model Parameter Estimation
    • 16.4 Experimental Results
    • 16.5 Conclusions
  • Chapter 17: Model-Based 3D Cardiac Image Segmentation With Marginal Space Learning
    • Abstract
    • Acknowledgments
    • 17.1 Introduction
    • 17.2 Marginal Space Learning for 3D Object Segmentation
    • 17.3 Cardiac Chamber Segmentation
    • 17.4 Great Vessel Segmentation
    • 17.5 Coronary Artery Segmentation
    • 17.6 Experiments
    • 17.7 Conclusions and Future Work
  • Chapter 18: Spine Disk and RIB Centerline Parsing
    • Abstract
    • 18.1 Introduction
    • 18.2 Related Work
    • 18.3 Spine Disk Parsing
    • 18.4 RIB Centerline Parsing
    • 18.5 Conclusions
  • Chapter 19: Data-Driven Detection and Segmentation of Lymph Nodes
    • Abstract
    • 19.1 Introduction
    • 19.2 Related Work
    • 19.3 LN Center Candidate Detection
    • 19.4 Segmentation-Based Verification
    • 19.5 Spatial Prior
    • 19.6 Experiments
    • 19.7 Conclusion
  • Chapter 20: Polyp Segmentation on CT Colonography
    • Abstract
    • Acknowledgments
    • 20.1 Colonic Polyp and Colon Cancer
    • 20.2 CT Colonography
    • 20.3 Computer-Aided Detection and Diagnosis on CTC
    • 20.4 Polyp Segmentation
    • 20.5 Polyp Measurement and Characterization
    • 20.6 Data Acquisition and Validation Experiment
    • 20.7 Results
    • 20.8 Discussion
  • Chapter 21: Detect Cells and Cellular Behaviors in Phase Contrast Microscopy Images
    • Abstract
    • 21.1 Introduction
    • 21.2 Computer Vision Tasks in Analyzing Cell Populations
    • 21.3 Cell Segmentation
    • 21.4 Cellular Behavior Understanding
    • 21.5 Systems for Analyzing Cell Populations in Time-Lapse Imaging
    • 21.6 Open Source Cell Image Sequence Data
• Index