Guide to Medical Image Analysis: Methods and Algorithms

Description

This book presents a comprehensive overview of medical image analysis. Practical in approach, the text is uniquely structured by potential applications. Features: presents learning objectives, exercises and concluding remarks in each chapter, in addition to a glossary of abbreviations; describes a range of common imaging techniques, reconstruction techniques and image artefacts; discusses the archival and transfer of images, including the HL7 and DICOM standards; presents a selection of techniques for the enhancement of contrast and edges, for noise reduction and for edge-preserving smoothing; examines various feature detection and segmentation techniques, together with methods for computing a registration or normalisation transformation; explores object detection, as well as classification based on segment attributes such as shape and appearance; reviews the validation of an analysis method; includes appendices on Markov random field optimization, variational calculus and principal component analysis. 001Download PDF (249.2 KB)front-matter Guide to Medical Image Analysis Preface Acknowledgements Contents List of Abbreviations 002Download PDF (1,001.5 KB)fulltext Chapter 1: The Analysis of Medical Images 1.1 Image Analysis in the Clinical Workflow 1.2 Using Tools 1.3 An Example: Multiple Sclerosis Lesion Segmentation in Brain MRI 1.4 Concluding Remarks 1.5 Exercises References 003Download PDF (2.1 MB)fulltext Chapter 2: Digital Image Acquisition 2.1 X-Ray Imaging 2.1.1 Generation, Attenuation, and Detection of X Rays 2.1.1.1 X-Ray Generation 2.1.1.2 X-Ray Attenuation 2.1.2 X-Ray Imaging 2.1.3 Fluoroscopy and Angiography 2.1.4 Mammography 2.1.5 Image Reconstruction for Computed Tomography 2.1.6 Contrast Enhancement in X-Ray Computed Tomography 2.1.7 Image Analysis on X-Ray Generated Images 2.2 Magnetic Resonance Imaging 2.2.1 Magnetic Resonance 2.2.2 MR Imaging 2.2.3 Some MR Sequences 2.2.4 Artefacts in MR Imaging 2.2.5 MR Angiography 2.2.6 BOLD Imaging 2.2.7 Perfusion Imaging 2.2.8 Diffusion Imaging 2.2.9 Image Analysis on Magnetic Resonance Images 2.3 Ultrasound 2.3.1 Ultrasound Imaging 2.3.2 Image Analysis on Ultrasound Images 2.4 Nuclear Imaging 2.4.1 Scintigraphy 2.4.2 Reconstruction Techniques for Tomography in Nuclear Imaging 2.4.3 Single Photon Emission Computed Tomography (SPECT) 2.4.4 Positron Emission Tomography (PET) 2.4.5 Image Analysis on Nuclear Images 2.5 Other Imaging Techniques 2.5.1 Photography 2.5.2 Light Microscopy 2.5.3 EEG and MEG 2.6 Concluding Remarks 2.7 Exercises References 004Download PDF (885.3 KB)fulltext Chapter 3: Image Storage and Transfer 3.1 Information Systems in a Hospital 3.2 The DICOM Standard 3.3 Establishing DICOM Connectivity 3.4 The DICOM File Format 3.5 Technical Properties of Medical Images 3.6 Displays and Workstations 3.7 Compression of Medical Images 3.8 Concluding Remarks 3.9 Exercises References 005Download PDF (1.3 MB)fulltext Chapter 4: Image Enhancement 4.1 Measures of Image Quality 4.1.1 Spatial and Contrast Resolution 4.1.2 Definition of Contrast 4.1.3 The Modulation Transfer Function 4.1.4 Signal-to-Noise Ratio (SNR) 4.2 Image Enhancement Techniques 4.2.1 Contrast Enhancement 4.2.2 Resolution Enhancement 4.2.3 Edge Enhancement 4.3 Noise Reduction 4.3.1 Noise Reduction by Linear Filtering 4.3.2 Edge-Preserving Smoothing: Median Filtering 4.3.3 Edge-Preserving Smoothing: Diffusion Filtering 4.3.4 Edge-Preserving Smoothing: Bayesian Image Restoration 4.4 Concluding Remarks 4.5 Exercises References 006Download PDF (943.3 KB)fulltext Chapter 5: Feature Detection 5.1 Edge Tracking 5.2 Hough Transform 5.3 Corners 5.4 Blobs 5.5 SIFT and SURF Features 5.6 MSER Features 5.7 Key-Point-Independent Features 5.8 Saliency and Gist 5.9 Bag of Features 5.10 Concluding Remarks 5.11 Exercises References 007Download PDF (1.6 MB)fulltext Chapter 6: Segmentation: Principles and Basic Techniques 6.1 Segmentation Strategies 6.2 Data Knowledge 6.2.1 Homogeneity of Intensity 6.2.2 Homogeneity of Texture 6.3 Domain Knowledge About the Objects 6.3.1 Representing Domain Knowledge 6.3.2 Variability of Model Attributes 6.3.3 The Use of Interaction 6.4 Interactive Segmentation 6.5 Thresholding 6.6 Homogeneity-Based Segmentation 6.7 The Watershed Transform: Computing Zero-Crossings 6.8 Seeded Regions 6.9 Live Wire 6.10 Concluding Remarks 6.11 Exercises References 008Download PDF (778.2 KB)fulltext Chapter 7: Segmentation in Feature Space 7.1 Segmentation by Classification in Feature Space 7.1.1 Computing the Likelihood Function 7.1.2 Multidimensional Feature Vectors 7.1.3 Computing the A Priori Probability 7.1.4 Extension to More than Two Classes 7.2 Clustering in Feature Space 7.2.1 Partitional Clustering and k-Means Clustering 7.2.2 Mean-Shift Clustering 7.2.3 Kohonen's Self-organizing Maps 7.3 Concluding Remarks 7.4 Exercises References 009Download PDF (999.3 KB)fulltext Chapter 8: Segmentation as a Graph Problem 8.1 Graph Cuts 8.1.1 Graph Cuts for Computing a Segmentation 8.1.2 Graph Cuts to Approximate a Bayesian Segmentation 8.1.3 Adding Constraints 8.1.4 Normalized Graph Cuts 8.2 Segmentation as a Path Problem 8.2.1 Fuzzy Connectedness 8.2.2 The Image Foresting Transform 8.2.3 Random Walks 8.3 Concluding Remarks 8.4 Exercises References 010Download PDF (1.3 MB)fulltext Chapter 9: Active Contours and Active Surfaces 9.1 Explicit Active Contours and Surfaces 9.1.1 Deriving the Model 9.1.2 The Use of Additional Constraints 9.1.3 T-snakes and T-surfaces 9.2 The Level Set Model 9.2.1 Level Sets 9.2.2 Level Sets and Wave Propagation 9.2.3 Schemes for Computing Level Set Evolution 9.2.4 Computing Stationary Level Set Evolution 9.2.5 Computing Dynamic Level Set Evolution 9.2.6 Segmentation and Speed Functions 9.2.7 Geodesic Active Contours 9.2.8 Level Sets and the Mumford-Shah Functional 9.2.9 Topologically Constrained Level Sets 9.3 Concluding Remarks 9.4 Exercises References 011Download PDF (1.2 MB)fulltext Chapter 10: Registration and Normalization 10.1 Feature Space and Correspondence Criterion 10.2 Rigid Registration 10.3 Registration of Projection Images to 3D Data 10.4 Search Space and Optimization in Nonrigid Registration 10.5 Normalization 10.6 Concluding Remarks 10.7 Exercises References 012Download PDF (1.3 MB)fulltext Chapter 11: Detection and Segmentation by Shape and Appearance 11.1 Shape Models 11.2 Simple Models 11.2.1 Template matching 11.2.2 Hough Transform 11.3 Implicit Models 11.4 The Medial Axis Representation 11.4.1 Computation of the Medial Axis Transform 11.4.2 Shape Representation by Medial Axes 11.5 Active Shape and Active Appearance Models 11.5.1 Creating an ASM 11.5.2 Using ASMs for Segmentation 11.5.3 The Active Appearance Model 11.6 Physically Based Shape Models 11.6.1 Mass Spring Models 11.6.2 Finite Element Models 11.7 Shape Priors 11.8 Concluding Remarks 11.9 Exercises References 013Download PDF (1,015.7 KB)fulltext Chapter 12: Classification and Clustering 12.1 Features and Feature Space 12.1.1 Linear Decorrelation of Features 12.1.2 Linear Discriminant Analysis 12.1.3 Independent Component Analysis 12.2 Bayesian Classifier 12.3 Classification Based on Distance to Training Samples 12.4 Decision Boundaries 12.4.1 Adaptive Decision Boundaries 12.4.2 The Multilayer Perceptron 12.4.3 Support Vector Machines 12.5 Classification by Association 12.6 Clustering Techniques 12.6.1 Agglomerative Clustering 12.6.2 Fuzzy c-Means Clustering 12.7 Bagging and Boosting 12.8 Multiple Instance Learning 12.9 Concluding Remarks 12.10 Exercises References 014Download PDF (951.0 KB)fulltext Chapter 13: Validation 13.1 Measures of Quality 13.1.1 Quality for a Delineation Task 13.1.2 Quality for a Detection Task 13.1.3 Quality for a Registration Task 13.2 The Ground Truth 13.2.1 Ground Truth from Real Data 13.2.2 Ground Truth from Phantoms 13.3 Representativeness of Data 13.3.1 Separation Between Training and Test Data 13.3.2 Identification of Sources of Variation and Outlier Detection 13.3.3 Robustness with Respect to Parameter Variation 13.4 Significance of Results 13.5 Concluding Remarks 13.6 Exercises References 015Download PDF (513.1 KB)fulltext Chapter 14: Appendix 14.1 Optimization of Markov Random Fields 14.1.1 Markov Random Fields 14.1.2 Simulated Annealing 14.1.3 Mean Field Annealing 14.1.4 Iterative Conditional Modes 14.2 Variational Calculus 14.3 Principal Component Analysis 14.3.1 Computing the PCA 14.3.2 Robust PCA References 016Download PDF (372.2 KB)back-matter Index