| Description |
1 online resource (173 p.) |
| Contents |
Cover -- Half Title -- Title Page -- Copyright Page -- Table of Contents -- Preface -- Acknowledgments -- Authors -- List of Abbreviations -- Chapter 1 Introduction -- 1.1 Background of the CAD System -- 1.2 Objectives and Significance of the CAD System -- 1.3 Applications of CAD Systems -- 1.4 Previous Studies of CAD Systems -- 1.5 How to Evaluate a CAD System -- 1.5.1 Sensitivity and Specificity -- 1.5.2 Laboratory Studies -- 1.5.3 Actual Clinical Practice Experience -- 1.6 Background of the Glaucoma Disease -- 1.6.1 Tonometry -- 1.6.2 Ophthalmoscopy -- 1.6.3 Gonioscopy |
|
1.6.4 Visual Field Testing -- 1.6.5 Nerve Fiber Analysis -- 1.6.6 Pachymetry -- 1.7 Computer-Aided Diagnosis in Glaucoma -- 1.8 Problems of the Study -- 1.9 Objectives -- 1.9.1 General Aim -- 1.9.2 Specific Objectives -- 1.10 Research Methodology -- 1.11 Significance of the Study -- 1.12 Contributions -- 1.13 Organization of the Book's Chapters -- Chapter 2 Medical and Mathematical Background -- 2.1 The Human Eye -- 2.1.1 Structure of the Human Eye -- 2.2 Image Acquisition of the Retina -- 2.2.1 Fundus Image Capture -- 2.2.2 Other Imaging Devices -- 2.3 The Glaucoma Disease |
|
2.3.1 Glaucoma and the Visual Pathway -- 2.4 Glaucoma Diagnosis -- 2.4.1 Optic Nerve Head -- 2.4.2 Intraocular Pressure -- 2.4.3 Visual Field Function -- 2.4.4 Glaucoma Assessment -- 2.4.5 Glaucoma ONH Evaluation -- 2.4.5.1 Cup-to-Disc Ratio -- 2.4.5.2 Parapapillary Atrophy -- 2.4.5.3 Disc Hemorrhage -- 2.4.5.4 Notching -- 2.4.5.5 Neuroretinal Rim Thinning -- 2.4.5.6 Inter-Eye Asymmetry -- 2.4.5.7 Retinal Nerve Fiber Layer Defect -- 2.5 Motivation of Fundus Image Processing -- 2.5.1 Digital Fundus Image Processing -- 2.5.2 Channel Separation -- 2.5.3 Histogram Equalization -- 2.5.4 Filtering |
|
2.5.5 Morphological Processing -- 2.6 Feature Extraction Background -- 2.7 Shape Features -- 2.7.1 The Centroid -- 2.7.2 Eccentricity -- 2.7.3 Solidity -- 2.7.4 Area -- 2.7.5 Major Axes -- 2.7.6 Minor Axes -- 2.7.7 Extent -- 2.7.8 Perimeter -- 2.8 Color Features -- 2.8.1 Mean -- 2.8.2 Standard Deviation -- 2.8.3 Skewness -- 2.9 Texture Feature -- 2.9.1 GLCM Algorithm -- 2.10 Tamura Method -- 2.10.1 Coarseness -- 2.10.2 Contrast -- 2.10.3 Direction Degrees -- 2.11 Feature Selection -- 2.11.1 Sequential Feature Selector -- 2.11.2 Sequential Forward Selection (SFS) -- 2.12 Classification |
|
2.12.1 Statistical Classification Methods -- 2.12.2 Rule-Based Systems -- 2.12.3 Support Vector Machine (SVM) -- 2.12.4 k-Nearest Neighbors Algorithm (k-NN) -- 2.12.5 Some Advantages and Disadvantages of KNN -- 2.12.5.1 Advantages -- 2.12.5.2 Disadvantages -- 2.12.6 Ensemble Learning -- 2.12.6.1 Bootstrap Aggregating (Bagging) -- 2.12.6.2 Boosting -- 2.12.7 Logistic Regression (Predictive Learning Model) -- 2.12.8 Decision Trees -- 2.12.9 Random Forest -- 2.12.10 Neural Network -- 2.13 Classification Imbalanced -- 2.13.1 Under-Sampling -- 2.13.1.1 Random Under-Sampling For the Majority Class |
| Notes |
Description based upon print version of record |
|
2.13.1.2 Near Miss |
| Form |
Electronic book
|
| Author |
Mohammed Hamza, Alnazier Osman
|
| ISBN |
9781000070095 |
|
1000070093 |
|
