Pattern recognition in medical imaging

Anke Meyer-Baese0124932908, 9780124932906

Medical Imaging has become one of the most important visualization and interpretation methods in biology and medecine over the past decade. This time has witnessed a tremendous development of new, powerful instruments for detecting, storing, transmitting, analyzing, and displaying medical images. This has led to a huge growth in the application of digital processing techniques for solving medical problems. The most challenging aspect of medical imaging lies in the development of integrated systems for the use of the clinical sector. Design, implementation, and validation of complex medical systems requires a tight interdisciplinary collaboration between physicians and engineers because poor image quality leads to problematic feature extraction, analysis, and recognition in medical application. Therefore, much of the research done today is geared towards improvement of imperfect image material. This important book by academic authority Anke Meyer-Baese compiles and organizes a complete range of proven and cutting-edge new methods, which are playing a leading role in the improvement of image quality, analysis and interpretation in modern medical imaging. These methods offer fresh tools of hope for physicians investigating a vast number of medical problems for which classical methods prove insufficient. Each chapter in Pattern Recognition for Medical Imaging provides a chapter summary and bibliographic remarks for in-depth study. Each presented classification approach is elucidated by a flow-diagram and highlighted with practical medical imaging applications. This is an essential tool for the serious student and professional working with Medical Imaging. *Essential tool for serious students and professionals working with Medical Imaging

---

Table of contents :
Cover……Page 1
Date-line……Page 2
CONTENTS……Page 3
GLOSSARY……Page 7
LIST OF SYMBOLS……Page 9
PREFACE……Page 13
ACKNOWLEDGMENTS……Page 17
I INTRODUCTION……Page 19
1.1. Microscopic Image Analysis……Page 20
1.2. Macroscopic Image Analysis……Page 22
2.1. Introduction……Page 32
2.2. Role of Feature Selection and Extraction……Page 33
2.4. Feature Extraction Methods……Page 35
2.5. Feature Selection Methods……Page 59
3.1. Introduction……Page 68
3.2. The Theory of Subband Coding……Page 69
3.3. The Wavelet Transform……Page 83
3.4. The Discrete Wavelet Transformation……Page 91
3.5. Multiscale Signal Decomposition……Page 93
3.6. Overview: Types of Wavelet Transforms……Page 109
4.1. Introduction……Page 115
4.2. The Two-Dimensional Discrete Wavelet Transform……Page 116
4.3. Biorthogonal Wavelets and Filter Banks……Page 118
4.4. Applications……Page 123
5.1. Introduction……Page 139
5.2. Encoding and Optimization Problems……Page 140
5.3. The Canonical Genetic Algorithm……Page 141
5.4. Optimization of a Simple Function……Page 145
5.5. Theoretical Aspects of Genetic Algorithms……Page 148
5.6. Feature Selection Based on Genetic Algorithms……Page 151
6.1. Introduction……Page 154
6.2. Learning Paradigms in Statistical Pattern Recognition……Page 155
6.3. Parametric Estimation Methods……Page 157
6.4. Nonparametric Estimation Methods……Page 166
6.5. Binary Decision Trees……Page 172
6.6. Syntactic Pattern Recognition……Page 174
6.7. Diagnostic Accuracy Measured by ROC-Curves……Page 185
6.8. Application of Statistical Classification Methods……Page 189
6.9. Application of Syntactic Pattern Recognition……Page 195
7.1. Introduction……Page 204
7.2. Multilayer Perception (MLP)……Page 207
7.3. Self-Organizing Neural Networks……Page 215
7.4. Radial Basis Neural Networks (RBNN)……Page 222
7.5. Transformation Radial Basis Neural Networks……Page 233
7.6. Hopfield Neural Networks……Page 237
7.7. Comparing Pattern Recognition Methods……Page 239
7.8. Pixel Labeling Using Neural Networks……Page 241
7.9. Classification Strategies for Medical Images……Page 243
7.10. Classifier Evaluation Techniques……Page 246
8.1. Introduction……Page 252
8.2. Neurodynamical Aspects of Neural Networks……Page 253
8.3. PCA-Type Neural Networks……Page 259
8.4. ICA-Type Neural Networks……Page 272
9.1. Introduction……Page 300
9.2. Fuzzy Sets……Page 301
9.3. Neuro-Fuzzy Integration……Page 303
9.4. Fuzzy Neural Network……Page 305
9.5. Fuzzy Clustering……Page 306
9.6. Comparison of Fuzzy Clustering versus PCA for fMRI……Page 327
9.7. Fuzzy Algorithms for LVQ……Page 329
10.1. Introduction……Page 336
10.2. Basic Aspects……Page 337
10.3. Convolution Neural Networks (CNNs)……Page 340
10.4. Hierarchical Pyramid Neural Networks……Page 343
10.5. Problem Factorization……Page 345
10.6. Modified Hopfield Neural Network……Page 346
10.7. Hopfield Neural Network Using a Priori Information……Page 350
10.8. Tumor Boundary Detection……Page 354
10.9. Cascaded Self-Organized Neural Network……Page 359
11.1. Introduction……Page 364
11.2. Segmentation of Mass and Normal Breast Tissue……Page 367
11.3. Classification of Mass and Normal Breast Tissue……Page 372
11.4. CAD System for Mass Detection……Page 375
11.5. Microcalcification Analysis System……Page 378
11.6. CAD System for Microcalcification Detection……Page 381
REFERENCES……Page 385
INDEX……Page 401