Pattern Recognition and Signal Analysis in Medical Imaging

by Meyer-Baese; Schmid

• ISBN13: 9780124932906
• ISBN10: 0124932908
• Format: Hardcover
• Copyright: 2003-10-31
• Publisher: Elsevier Science

Summary

Pattern Recognition for Medical Imaging is an essential book for students and professionals working with Medical Imaging. This text compiles, organizes and explains a complete range of proven and cutting-edge methods in pattern recognition, which are key to the improvement of image quality, analysis and interpretation in modern medical imaging. These methods offer new tools for physicians investigating medical problems for which classical analysis and detection algorithms may prove insufficient. Meyer-Base's dual emphasis, on both theory and practice, is illustrated by relevant applications in radiology, digital mammography, and fMRI. Biomedical and electrical engineers, physicians, biophysists, biologists, and all other engineers working in medical imaging or related fields will benefit from this incomparable resource. Book jacket.

Table of Contents

DEDICATION	v
PREFACE	xvii
ACKNOWLEDGMENTS	xxi
I INTRODUCTION
1.1. Microscopic Image Analysis	2	(2)
1.2. Macroscopic Image Analysis	4	(10)
II FEATURE SELECTION AND EXTRACTION
2.1. Introduction	14	(1)
2.2. Role of Feature Selection and Extraction	15	(2)
2.3. Preliminary Notations	17	(1)
2.4. Feature Extraction Methods	17	(24)
2.5. Feature Selection Methods	41	(9)
III SUBBAND CODING AND WAVELET TRANSFORM
3.1. Introduction	50	(1)
3.2. The Theory of Subband Coding	51	(14)
3.3. The Wavelet Transform	65	(8)
3.4. The Discrete Wavelet Transformation	73	(2)
3.5. Multiscale Signal Decomposition	75	(16)
3.6. Overview: Types of Wavelet Transforms	91	(6)
IV THE WAVELET TRANSFORM IN MEDICAL IMAGING
4.1. Introduction	97	(1)
4.2. The Two-Dimensional Discrete Wavelet Transform	98	(2)
4.3. Biorthogonal Wavelets and Filter Banks	100	(5)
4.4. Applications	105	(16)
V GENETIC ALGORITHMS
5.1. Introduction	121	(1)
5.2. Encoding and Optimization Problems	122	(1)
5.3. The Canonical Genetic Algorithm	123	(4)
5.4. Optimization of a Simple Function	127	(3)
5.5. Theoretical Aspects of Genetic Algorithms	130	(3)
5.6. Feature Selection Based on Genetic Algorithms	133	(3)
VI STATISTICAL AND SYNTACTIC PATTERN RECOGNITION
6.1. Introduction	136	(1)
6.2. Learning Paradigms in Statistical Pattern Recognition	137	(2)
6.3. Parametric Estimation Methods	139	(9)
6.4. Nonparametric Estimation Methods	148	(6)
6.5. Binary Decision Trees	154	(2)
6.6. Syntactic Pattern Recognition	156	(11)
6.7. Diagnostic Accuracy Measured by ROC-Curves	167	(4)
6.8. Application of Statistical Classification Methods	171	(6)
6.9. Application of Syntactic Pattern Recognition	177	(9)
VII FOUNDATIONS OF NEURAL NETWORKS
7.1. Introduction	186	(3)
7.2. Multilayer Perceptron (MLP)	189	(8)
7.3. Self-Organizing Neural Networks	197	(7)
7.4. Radial Basis Neural Networks (RBNN)	204	(11)
7.5. Transformation Radial Basis Neural Networks	215	(4)
7.6. Hopfield Neural Networks	219	(2)
7.7. Comparing Pattern Recognition Methods	221	(2)
7.8. Pixel Labeling Using Neural Networks	223	(2)
7.9. Classification Strategies for Medical Images	225	(3)
7.10. Classifier Evaluation Techniques	228	(6)
VIII TRANSFORMATION AND SIGNAL-SEPARATION NEURAL NETWORKS
8.1. Introduction	234	(1)
8.2. Neurodynamical Aspects of Neural Networks	235	(6)
8.3. PCA-Type Neural Networks	241	(13)
8.4. ICA-Type Neural Networks	254	(28)
IX NEURO-FUZZY CLASSIFICATION
9.1. Introduction	282	(1)
9.2. Fuzzy Sets	283	(2)
9.3. Neuro-Fuzzy Integration	285	(2)
9.4. Fuzzy Neural Network	287	(1)
9.5. Fuzzy Clustering	288	(21)
9.6. Comparison of Fuzzy Clustering versus PCA for fMRI	309	(2)
9.7. Fuzzy Algorithms for LVQ	311	(7)
X SPECIALIZED NEURAL NETWORKS RELEVANT TO BIOIMAGING
10.1. Introduction	318	(1)
10.2. Basic Aspects	319	(3)
10.3. Convolution Neural Networks (CNNs)	322	(3)
10.4. Hierarchical Pyramid Neural Networks	325	(2)
10.5. Problem Factorization	327	(1)
10.6. Modified Hopfield Neural Network	328	(4)
10.7. Hopfield Neural Network Using a Priori Information	332	(4)
10.8. Tumor Boundary Detection	336	(5)
10.9. Cascaded Self Organized Neural Network	341	(5)
XI NEURAL-BASED COMPUTER-AIDED DIAGNOSIS SYSTEMS IN BREAST CANCER DETECTION
11.1. Introduction	346	(3)
11.2. Segmentation of Mass and Normal Breast Tissue	349	(5)
11.3. Classification of Mass and Normal Breast Tissue	354	(3)
11.4. CAD System for Mass Detection	357	(3)
11.5. Microcalcification Analysis System	360	(3)
11.6. CAD System for Microcalcification Detection	363	(4)
REFERENCES	367	(16)
INDEX	383