|
1 Introduction and Motivation for Conducting Medical Image Analysis |
|
|
1 | (26) |
|
1.1 Introduction to Time-Resolved Terahertz Spectroscopy and Imaging |
|
|
2 | (8) |
|
1.1.1 Time Domain and Frequency Domain THz Spectroscopy |
|
|
2 | (6) |
|
1.1.2 Recent Advances in Simultaneous Time-Frequency Dependent THz Spectroscopy |
|
|
8 | (2) |
|
1.2 The Application of Magnetic Resonance to Biomedical Imaging |
|
|
10 | (7) |
|
1.3 Placing THz Imaging and MRI Time-Series in a Common Signal Processing Framework |
|
|
17 | (2) |
|
1.4 Introduction to Retinal Fundus Imaging |
|
|
19 | (3) |
|
1.5 Introduction to Optical Coherence Tomography (OCT) |
|
|
22 | (5) |
|
2 Overview of Clinical Applications Using THz Pulse Imaging, MRI, OCT and Fundus Imaging |
|
|
27 | (24) |
|
2.1 Recent Advances in the Application of THz Pulse Spectroscopy to Biomedical Imaging |
|
|
27 | (24) |
|
2.1.1 THz Radiation Absorption and Detection in Tissue |
|
|
28 | (1) |
|
2.1.2 Identification of Compounds with Complex Composition |
|
|
29 | (2) |
|
2.1.3 Recent Advances in the Application of DCE-MRI Imaging Techniques to Biomedical Imaging |
|
|
31 | (2) |
|
2.1.4 Recent Advances in the Application of fMRI Imaging to Biomedical Imaging |
|
|
33 | (3) |
|
2.1.5 Advantages and Shortfalls of T-Rays and DCE-MRI & FMRI |
|
|
36 | (2) |
|
2.1.6 Combining MRI with Alternative THz Spectrometric Systems and Other Imaging Modalities |
|
|
38 | (7) |
|
2.1.7 Recent Advances in the Application of the Fundus Camera to Disease Diagnosis |
|
|
45 | (2) |
|
2.1.8 Recent Advances in the Application of OCT Techniques to Disease Diagnosis |
|
|
47 | (2) |
|
2.1.9 Alternative Multichannel and MEMS Based OCT Imaging Modalities |
|
|
49 | (2) |
|
3 Recent Advances in Medical Data Preprocessing and Feature Extraction Techniques |
|
|
51 | (42) |
|
3.1 Overview of Medical Image Data Preprocessing Strategies |
|
|
52 | (12) |
|
3.1.1 Data Windowing and Model Fitting Parametric Approaches |
|
|
52 | (1) |
|
3.1.2 Multi-resolution Wavelet Analysis for Noise Removal |
|
|
53 | (4) |
|
3.1.3 Current Standards and Recent Developments in Multiresolution Feature Representation in Imaging |
|
|
57 | (2) |
|
3.1.4 Recent Advances in MRI Wavelet Denoising |
|
|
59 | (1) |
|
3.1.5 Recent Advances in Fundus Image Denoising |
|
|
60 | (3) |
|
3.1.6 The Need for a Multiresolution Image Fusion Approach |
|
|
63 | (1) |
|
3.2 Overview of Feature Selection Strategies |
|
|
64 | (29) |
|
3.2.1 Feature Selection Strategies in THz TPI Datasets |
|
|
64 | (7) |
|
3.2.2 Feature Extraction and Selection on the Basis of Cross-correlation Sequences |
|
|
71 | (3) |
|
3.2.3 Feature Selection Strategies for MRI Datasets |
|
|
74 | (5) |
|
3.2.4 Spatiotemporal Correlations and Cluster Analysis of Brain Activity Using fMRI |
|
|
79 | (6) |
|
3.2.5 Feature Selection in Retinal Fundus Photography Following Image Enhancement |
|
|
85 | (5) |
|
3.2.6 Feature Extraction and Pattern Identification of Pathology Distortion in SD-OCT Imaging |
|
|
90 | (2) |
|
3.2.7 Statistical Analysis Based on Feature Selection Strategies |
|
|
92 | (1) |
|
|
|
93 | (36) |
|
4.1 Introduction to Pattern Classification |
|
|
93 | (1) |
|
4.2 Feature Based Mahalanobis Distance Classifiers |
|
|
94 | (1) |
|
4.3 Support Vector Machine Classifiers (SVMs) |
|
|
95 | (6) |
|
4.3.1 Binary Classification of SVMs |
|
|
95 | (3) |
|
4.3.2 Pairwise SVM Classification of Multiple Classes |
|
|
98 | (1) |
|
4.3.3 Application of SVM Classifiers to THz-TPI Measurements |
|
|
99 | (2) |
|
4.4 Real-Valued Extreme Learning Machine Classifier |
|
|
101 | (2) |
|
4.5 Complex Valued ELMs for Classification |
|
|
103 | (20) |
|
4.5.1 Review of Complex-Valued RKHS and Wirtinger's Calculus |
|
|
103 | (2) |
|
4.5.2 Defining Higher-Dimension Hyprplanes Using Quaternion and Other Division Algebras for Classification |
|
|
105 | (5) |
|
4.5.3 Determination of the Maximum-Margin Hyperplanes ofCELM |
|
|
110 | (7) |
|
4.5.4 Multinomial Logistic Regression Classifier with Ridge Estimators (MLR) |
|
|
117 | (1) |
|
4.5.5 Naive Bayesian (NB) Classifier |
|
|
118 | (1) |
|
4.5.6 Performance Evaluation of Several Different Classifiers |
|
|
118 | (3) |
|
4.5.7 Clustering Techniques to Segment THz Images |
|
|
121 | (2) |
|
4.6 Retinal Fundus Image Analysis via Supervised and Non-supervised Learning |
|
|
123 | (6) |
|
4.6.1 Fundus Image Vessel Segmentation |
|
|
123 | (1) |
|
4.6.2 Algorithmic Detection of the Optic Disk |
|
|
124 | (2) |
|
4.6.3 Retinal Vessel Classification: Identifying and Sorting Arteries and Veins |
|
|
126 | (1) |
|
4.6.4 Automated Image Classification Using Criteria Directly Developed from Clinicians |
|
|
127 | (2) |
|
5 Introduction to MRI Time Series Image Analysis Techniques |
|
|
129 | (36) |
|
5.1 Analysis of DCE-MRI Data |
|
|
129 | (5) |
|
5.1.1 Outlook for Future Tensorial Algebra Based Feature and Image Registration |
|
|
131 | (2) |
|
5.1.2 Performance Measures |
|
|
133 | (1) |
|
5.2 Tensorial Representations in MRI |
|
|
134 | (2) |
|
5.3 Extensions to Multi-channel Classifiers |
|
|
136 | (7) |
|
5.3.1 Suppression of Background Voxels Through Multi-channel Reconstruction |
|
|
140 | (1) |
|
5.3.2 Increased Image Contrast Between Tumours and Background Through Multi-channel Reconstruction |
|
|
141 | (2) |
|
5.4 Image Registration of MRIs |
|
|
143 | (3) |
|
5.5 Pattern Identification of Spatiotemporal Association of Features in Tumours from DCE-MRI Data |
|
|
146 | (3) |
|
5.6 Pattern Classification of Spatiotemporal Association Features in fMRI Data |
|
|
149 | (16) |
|
5.6.1 Supervised Tensor Learning of Brain Disorders in fMRI Datasets |
|
|
149 | (2) |
|
5.6.2 Supervised Multivariate Learning of Brain Disorders from fMRI Data |
|
|
151 | (3) |
|
5.6.3 Topological Graph Kernel on Multiply Thresholded Functional Connectivity Networks |
|
|
154 | (6) |
|
5.6.4 Machine Learning Using Information from Brain Graphs |
|
|
160 | (1) |
|
5.6.5 Additional Considerations Regarding MRI Feature Extraction Methodologies |
|
|
161 | (2) |
|
5.6.6 Recent Relevant Advances from the Computer Vision Community |
|
|
163 | (2) |
|
6 Outlook for Clifford Algebra Based Feature and Deep Learning AI Architectures |
|
|
165 | (14) |
|
6.1 Prospects for Medical Image Analysis Under a Clifford Algebra Framework |
|
|
165 | (4) |
|
6.2 Outlook for Developing a Geometric Neuron Deep Learning of Time Series Datasets in Medical Images |
|
|
169 | (8) |
|
6.3 Prospects for Alternative Classifiers in Deep Learning of Unlabelled Medical Image Data |
|
|
177 | (2) |
|
|
|
179 | (4) |
| References |
|
183 | (32) |
| Index |
|
215 | |
Lisainfo e-raamatute kohta