Handbook of Texture Analysis(2024)[El-Baz et al][9780367486082]

Handbook of Texture Analysis(2024)[El-Baz et al][9780367486082] Cover Half Title Title Copyright Dedication Contents Preface List of Contributors Author Bios Acknowledgments Chapter 1 An Exploratory Review on Local Binary Descriptors for Texture Classification 1.1 Introduction 1.2 Texture Methods 1.2.1 Local Binary Pattern (LBP) 1.2.2 Local Directional Pattern (LDP) 1.2.3 Angular Local Directional Pattern 1.2.4 Local Directional Number Pattern (LDNP) 1.2.5 Local Optimal Oriented Pattern (LOOP) 1.2.6 Local Line Directional Neighborhood Pattern (LLDNP) 1.2.7 Volumetric Local Directional Triplet Patterns (VLDTP) 1.2.8 Local Tri-Directional Patterns (LTriDP) 1.2.9 Local Neighborhood Intensity Pattern (LNIP) 1.2.10 Local Triangular Coded Pattern (LTCP) 1.3 Experimental Analysis and Results on Local Descriptors for Texture Classification 1.3.1 Benchmark Texture Datasets 1.3.2 Classifiers 1.3.3 Evaluation Metrics 1.3.4 Result Analysis 1.4 Discussion 1.5 Conclusion References Authors’ Biographies Chapter 2 Precision Grading of Glioma: A System for Accurate Diagnosis and Treatment Planning 2.1 Introduction 2.2 Related Studies 2.2.1 Research Gap 2.3 Materials 2.4 Methodology 2.4.1 Features Engineering 2.4.2 Classification and Hyperparameters Tuning 2.4.3 Engineering Features Selection 2.4.4 Experiments 2.5 Results and Discussion 2.5.1 Results 2.5.2 Discussion 2.6 Conclusions and Future Work References Chapter 3 Enhancing Accuracy in Liver Tumor Detection and Grading: A Computer-Aided Diagnostic System 3.1 Introduction 3.2 Related Studies 3.3.1 Research Gap 3.3 Materials 3.4 Methodology 3.4.1 Features/Markers Extraction 3.4.2 Features/Markers Selection 3.4.3 Integration and Diagnosis of Liver Tumor Markers 3.5 Experiments’ Results 3.6 Conclusions and Future Work References Chapter 4 Texture Analysis in Radiology 4.1 Introduction 4.1.1 Texture Analysis Background 4.2 Textural Analysis Workflow 4.3 Image Acquisition 4.4 Image Segmentation 4.5 Feature Extraction 4.6 Feature Reduction 4.7 Statistical Extraction of Textural Features 4.8 First-Order Methods 4.9 Second-Order Methods 4.10 Applications 4.11 Tumor Classification 4.12 Tumor Grading 4.13 Radiogenomics 4.14 Limitation of Texture Feature Extraction References Chapter 5 Texture Analysis Using a Self-Organizing Feature Map 5.1 Introduction and Background 5.2 The Self-Organizing Map 5.3 Method for Applying SOM to Analyze Radiomic Confounding Variables 5.3.1 Evaluation of the Effectiveness of the SOM in Assessing Radiomic Confounding Variables 5.4 Application of the SOM for Predictive Analysis 5.5 Conclusion References Chapter 6 Sensor-Based Human Activity Recognition Analysis Using Machine Learning and Topological Data Analysis (TDA) 6.1 Introduction 6.2 Literature Review 6.3 Background 6.3.1 HAR Data Acquisition 6.3.2 Imbalanced Datasets and Oversampling Techniques 6.3.3 Features Engineering and Dimensionality Reduction Techniques 6.3.4 Machine Learning Classification and Tuning 6.4 Methodology 6.4.1 Data Retrieval Phase 6.4.2 Preprocessing Phase 6.4.3 Features Engineering 6.4.4 Classification and Tuning 6.5 Experiments and Discussion 6.6 Conclusions and Future Work References Chapter 7 Application of Texture Analysis in Retinal OCT Imaging 7.1 Introduction 7.2 Optical Coherence Tomography and Retina 7.2.1 OCT Principle and Resolution 7.2.2 Cell Scattering Contribution 7.2.3 Retinal OCT 7.2.4 Pathogenesis of Retinal Neurodegeneration 7.3 OCT Texture 7.3.1 Image Processing 7.3.2 Textural Features 7.3.3 Retinal Layers Segmentation Using Texture Analysis 7.3.4 Texture Analysis–Based Classification of Retinal OCT Images 7.4 Limitations and Future Directions Acknowledgments References Chapter 8 Automation in Pneumonia Detection 8.1 Introduction: Background Study 8.2 Detection System Materials 8.2.1 Dataset Collection 8.2.2 Applied Tools 8.3 Methodology 8.3.1 Technique 8.3.2 Equations 8.4 Results and Findings 8.5 Conclusions References Chapter 9 Texture for Neuroimaging 9.1 Introduction 9.2 Historical Context and Current Trends 9.3 The Role of Texture in Neuroimaging 9.4 Texture Methods in Neuroimaging 9.4.1 Statistical-Based Methods 9.4.2 Transform-Based Methods 9.4.3 Model-Based Methods 9.4.4 Other Feature-Based Methods 9.4.5 Learned-Based Methods 9.5 Texture Applications in Neuroimaging 9.5.1 Texture in MRI Applications 9.5.2 Texture in PET Applications 9.5.3 Texture in OCT Applications 9.6 Future Perspectives for Texture in Neuroimaging Bibliography Chapter 10 A Multimodal MR-Based CAD System for Precise Assessment of Prostatic Adenocarcinoma 10.1 Introduction 10.2 Methodology 10.2.1 Data Preparation 10.2.2 Feature Extraction 10.2.3 Feature Integration and Classification 10.3 Results and Discussion 10.4 Conclusion References Chapter 11 Texture Analysis in Cancer Prognosis 11.1 Texture Analysis 11.2 Texture Analysis and Prognosis: Focus on Breast Cancer 11.3 Texture Analysis and Prognosis: Focus on Lung Cancer 11.4 Texture Analysis and Prognosis: Focus on Gastric Cancer 11.5 Texture Analysis and Prognosis: Focus on Liver Cancer 11.6 Texture Analysis and Prognosis: Focus on Rectal Cancer 11.7 Other Cancers Bibliografia Index The major goals of texture research in computer vision are to understand, model, and process texture and, ultimately, to simulate the human visual learning process using computer technologies. In the last decade, artificial intelligence has been revolutionized by machine learning and big data approaches, outperforming human prediction on a wide range of problems. In particular, deep learning convolutional neural networks (CNNs) are particularly well suited to texture analysis. This volume presents important branches of texture analysis methods which find a proper application in AI-based medical image analysis. This book: Discusses first-order, second-order statistical methods, local binary pattern (LBP) methods, and filter bank-based methods Covers spatial frequency-based methods, Fourier analysis, Markov random fields, Gabor filters, and Hough transformation Describes advanced textural methods based on DL as well as BD and advanced applications of texture to medial image segmentation Is aimed at researchers, academics, and advanced students in biomedical engineering, image analysis, cognitive science, and computer science and engineering This is an essential reference for those looking to advance their understanding in this applied and emergent field. The major goals of texture research in computer vision are to understand, model and process texture, and ultimately to simulate the human visual learning process using computer technologies. In the last decade, artificial intelligence has been revolutionized by machine learning and big data approaches, outperforming human prediction on a wide range of problems. In particular, deep learning convolutional neural networks (CNNs) are particularly well suited to texture analysis. This volume presents important branches of texture analysis methods which find a proper application in AI-based medical image analysis. Discusses first-order, second-order statistical methods, local Binary Pattern (LBP) methods, and filter bank based methods Covers spatial-frequency based methods, Fourier analysis, Markov random fields, Gabor filters, and Hough transformation Describes advanced textural methods based on DL as well as BD and advanced applications of texture to medial image segmentation Aimed at researchers, academics, and advanced students in biomedical engineering, image analysis, cognitive science, and computer science and engineering, this is an essential reference for those looking to advance their understanding in this applied and emergent field.