{"product_id":"biomedical-image-understanding-isbn-9781118715154","title":"Biomedical Image Understanding","description":"\u003cp\u003e\u003cb\u003eA comprehensive guide to understanding and interpreting digital images in medical and functional applications\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e\u003ci\u003eBiomedical Image Understanding\u003c\/i\u003e focuses on image understanding and semantic interpretation, with clear introductions to related concepts, in-depth theoretical analysis, and detailed descriptions of important biomedical applications. It covers image processing, image filtering, enhancement, de-noising, restoration, and reconstruction; image segmentation and feature extraction; registration; clustering, pattern classification, and data fusion.\u003c\/p\u003e \u003cp\u003eWith contributions from experts in China, France, Italy, Japan, Singapore, the United Kingdom, and the United States, Biomedical Image Understanding:\u003c\/p\u003e \u003cul\u003e \u003cli\u003eAddresses motion tracking and knowledge-based systems, two areas which are not covered extensively elsewhere in a biomedical context\u003c\/li\u003e \u003cli\u003eDescribes important clinical applications, such as virtual colonoscopy, ocular disease diagnosis, and liver tumor detection\u003c\/li\u003e \u003cli\u003eContains twelve self-contained chapters, each with an introduction to basic concepts, principles, and methods, and a case study or application\u003c\/li\u003e \u003c\/ul\u003e \u003cp\u003eWith over 150 diagrams and illustrations, this bookis an essential resource for the reader interested in rapidly advancing research and applications in biomedical image understanding.\u003c\/p\u003e \u003cp\u003e\u003cb\u003eList of Contributors xv\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e\u003cb\u003ePreface xix\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e\u003cb\u003eAcronyms xxiii\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e\u003cb\u003ePART I INTRODUCTION 1\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e\u003cb\u003e1 Overview of Biomedical Image Understanding Methods 3\u003cbr\u003e\u003c\/b\u003e\u003ci\u003eWei Xiong, Jierong Cheng, Ying Gu, Shimiao Li and Joo Hwee Lim\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e1.1 Segmentation and Object Detection 5\u003c\/p\u003e \u003cp\u003e1.1.1 Methods Based on Image Processing Techniques 6\u003c\/p\u003e \u003cp\u003e1.1.2 Methods Using Pattern Recognition and Machine Learning Algorithms 7\u003c\/p\u003e \u003cp\u003e1.1.3 Model and Atlas-Based Segmentation 8\u003c\/p\u003e \u003cp\u003e1.1.4 Multispectral Segmentation 9\u003c\/p\u003e \u003cp\u003e1.1.5 User Interactions in Interactive Segmentation Methods 10\u003c\/p\u003e \u003cp\u003e1.1.6 Frontiers of Biomedical Image Segmentation 11\u003c\/p\u003e \u003cp\u003e1.2 Registration 11\u003c\/p\u003e \u003cp\u003e1.2.1 Taxonomy of Registration Methods 12\u003c\/p\u003e \u003cp\u003e1.2.2 Frontiers of Registration for Biomedical Image Understanding 15\u003c\/p\u003e \u003cp\u003e1.3 Object Tracking 16\u003c\/p\u003e \u003cp\u003e1.3.1 Object Representation 17\u003c\/p\u003e \u003cp\u003e1.3.2 Feature Selection for Tracking 18\u003c\/p\u003e \u003cp\u003e1.3.3 Object Tracking Technique 19\u003c\/p\u003e \u003cp\u003e1.3.4 Frontiers of Object Tracking 19\u003c\/p\u003e \u003cp\u003e1.4 Classification 20\u003c\/p\u003e \u003cp\u003e1.4.1 Feature Extraction and Feature Selection 21\u003c\/p\u003e \u003cp\u003e1.4.2 Classifiers 22\u003c\/p\u003e \u003cp\u003e1.4.3 Unsupervised Classification 23\u003c\/p\u003e \u003cp\u003e1.4.4 Classifier Combination 24\u003c\/p\u003e \u003cp\u003e1.4.5 Frontiers of Pattern Classification for Biomedical Image Understanding 25\u003c\/p\u003e \u003cp\u003e1.5 Knowledge-Based Systems 26\u003c\/p\u003e \u003cp\u003e1.5.1 Semantic Interpretation and Knowledge-Based Systems 26\u003c\/p\u003e \u003cp\u003e1.5.2 Knowledge-Based Vision Systems 27\u003c\/p\u003e \u003cp\u003e1.5.3 Knowledge-Based Vision Systems in Biomedical Image Analysis 28\u003c\/p\u003e \u003cp\u003e1.5.4 Frontiers of Knowledge-Based Systems 29\u003c\/p\u003e \u003cp\u003eReferences 29\u003c\/p\u003e \u003cp\u003e\u003cb\u003ePARTII SEGMENTATION AND OBJECT DETECTION 47\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e\u003cb\u003e2 Medical Image Segmentation and its Application in Cardiac MRI 49\u003cbr\u003e\u003c\/b\u003e\u003ci\u003eDong Wei, Chao Li, and Ying Sun\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e2.1 Introduction 50\u003c\/p\u003e \u003cp\u003e2.2 Background 51\u003c\/p\u003e \u003cp\u003e2.2.1 Active Contour Models 51\u003c\/p\u003e \u003cp\u003e2.2.2 Parametric and Nonparametric Contour Representation 52\u003c\/p\u003e \u003cp\u003e2.2.3 Graph-Based Image Segmentation 53\u003c\/p\u003e \u003cp\u003e2.2.4 Summary 54\u003c\/p\u003e \u003cp\u003e2.3 Parametric Active Contours – The Snakes 54\u003c\/p\u003e \u003cp\u003e2.3.1 The Internal Spline Energy \u003ci\u003eE\u003c\/i\u003eint 54\u003c\/p\u003e \u003cp\u003e2.3.2 The Image-Derived Energy \u003ci\u003eE\u003c\/i\u003eimg 55\u003c\/p\u003e \u003cp\u003e2.3.3 The External Control Energy \u003ci\u003eE\u003c\/i\u003econ 55\u003c\/p\u003e \u003cp\u003e2.3.4 Extension of Snakes and Summary of Parametric Active Contours 57\u003c\/p\u003e \u003cp\u003e2.4 Geometric Active Contours – The Level Sets 58\u003c\/p\u003e \u003cp\u003e2.4.1 Variational Level Set Methods 58\u003c\/p\u003e \u003cp\u003e2.4.2 Region-Based Variational Level Set Methods 60\u003c\/p\u003e \u003cp\u003e2.4.3 Summary of Level Set Methods 64\u003c\/p\u003e \u003cp\u003e2.5 Graph-Based Methods – The Graph Cuts 65\u003c\/p\u003e \u003cp\u003e2.5.1 Basic Graph Cuts Formulation 65\u003c\/p\u003e \u003cp\u003e2.5.2 Patch-Based Graph Cuts 66\u003c\/p\u003e \u003cp\u003e2.5.3 An Example of Graph Cuts 68\u003c\/p\u003e \u003cp\u003e2.5.4 Summary of Graph Cut Methods 72\u003c\/p\u003e \u003cp\u003e2.6 Case Study: Cardiac Image Segmentation Using A Dual Level Sets Model 73\u003c\/p\u003e \u003cp\u003e2.6.1 Introduction 73\u003c\/p\u003e \u003cp\u003e2.6.2 Method 74\u003c\/p\u003e \u003cp\u003e2.6.3 Experimental Results 79\u003c\/p\u003e \u003cp\u003e2.6.4 Conclusion of the Case Study 81\u003c\/p\u003e \u003cp\u003e2.7 Conclusion and Near-Future Trends 81\u003c\/p\u003e \u003cp\u003eReferences 83\u003c\/p\u003e \u003cp\u003e\u003cb\u003e3 Morphometric Measurements of the Retinal Vasculature in Fundus Images With Vampire 91\u003cbr\u003e\u003c\/b\u003e\u003ci\u003eEmanuele Trucco, Andrea Giachetti, Lucia Ballerini, Devanjali Relan, Alessandro Cavinato, and Tom Macgillivray\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e3.1 Introduction 92\u003c\/p\u003e \u003cp\u003e3.2 Assessing Vessel Width 93\u003c\/p\u003e \u003cp\u003e3.2.1 Previous Work 93\u003c\/p\u003e \u003cp\u003e3.2.2 Our Method 94\u003c\/p\u003e \u003cp\u003e3.2.3 Results 95\u003c\/p\u003e \u003cp\u003e3.2.4 Discussion 96\u003c\/p\u003e \u003cp\u003e3.3 Artery or Vein? 98\u003c\/p\u003e \u003cp\u003e3.3.1 Previous Work 98\u003c\/p\u003e \u003cp\u003e3.3.2 Our Solution 99\u003c\/p\u003e \u003cp\u003e3.3.3 Results 101\u003c\/p\u003e \u003cp\u003e3.3.4 Discussion 103\u003c\/p\u003e \u003cp\u003e3.4 Are My Program’s Measurements Accurate? 104\u003c\/p\u003e \u003cp\u003e3.4.1 Discussion 106\u003c\/p\u003e \u003cp\u003eReferences 107\u003c\/p\u003e \u003cp\u003e\u003cb\u003e4 Analyzing Cell and Tissue Morphologies Using Pattern Recognition Algorithms 113\u003cbr\u003e\u003c\/b\u003e\u003ci\u003eHwee Kuan Lee, Yan Nei Law, Chao-Hui Huang, and Choon Kong Yap \u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e4.1 Introduction, 113\u003c\/p\u003e \u003cp\u003e4.2 Texture Segmentation of Endometrial Images Using the Subspace Mumford–Shah Model 115\u003c\/p\u003e \u003cp\u003e4.2.1 Subspace Mumford–Shah Segmentation Model 116\u003c\/p\u003e \u003cp\u003e4.2.2 Feature Weights 118\u003c\/p\u003e \u003cp\u003e4.2.3 Once-and-For-All Approach 119\u003c\/p\u003e \u003cp\u003e4.2.4 Results 119\u003c\/p\u003e \u003cp\u003e4.3 Spot Clustering for Detection of Mutants in Keratinocytes 120\u003c\/p\u003e \u003cp\u003e4.3.1 Image Analysis Framework 123\u003c\/p\u003e \u003cp\u003e4.3.2 Results 124\u003c\/p\u003e \u003cp\u003e4.4 Cells and Nuclei Detection 124\u003c\/p\u003e \u003cp\u003e4.4.1 Model 125\u003c\/p\u003e \u003cp\u003e4.4.2 Neural Cells and Breast Cancer Cells Data 127\u003c\/p\u003e \u003cp\u003e4.4.3 Performance Evaluation 127\u003c\/p\u003e \u003cp\u003e4.4.4 Robustness Study 127\u003c\/p\u003e \u003cp\u003e4.4.5 Results 128\u003c\/p\u003e \u003cp\u003e4.5 Geometric Regional Graph Spectral Feature 134\u003c\/p\u003e \u003cp\u003e4.5.1 Conversion of Image Patches into Region Signatures 134\u003c\/p\u003e \u003cp\u003e4.5.2 Comparing Region Signatures 135\u003c\/p\u003e \u003cp\u003e4.5.3 Classification of Region Signatures 136\u003c\/p\u003e \u003cp\u003e4.5.4 Random Masking and Object Detection 136\u003c\/p\u003e \u003cp\u003e4.5.5 Results 137\u003c\/p\u003e \u003cp\u003e4.6 Mitotic Cells in the H\u0026amp;E Histopathological Images of Breast Cancer Carcinoma 138\u003c\/p\u003e \u003cp\u003e4.6.1 Mitotic Index Estimation 139\u003c\/p\u003e \u003cp\u003e4.6.2 Mitotic Candidate Selection 140\u003c\/p\u003e \u003cp\u003e4.6.3 Exclusive Independent Component Analysis (XICA) 140\u003c\/p\u003e \u003cp\u003e4.6.4 Classification Using Sparse Representation 143\u003c\/p\u003e \u003cp\u003e4.6.5 Training and Testing Over Channels 144\u003c\/p\u003e \u003cp\u003e4.6.6 Results 146\u003c\/p\u003e \u003cp\u003e4.7 Conclusions 147\u003c\/p\u003e \u003cp\u003eReferences 147\u003c\/p\u003e \u003cp\u003e\u003cb\u003ePARTIII REGISTRATION AND MATCHING 153\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e\u003cb\u003e5 3D Nonrigid Image Registration by Parzen-Window-Based Normalized Mutual Information and its Application on Mr-Guided Microwave Thermocoagulation of Liver Tumors 155\u003cbr\u003e\u003c\/b\u003e\u003ci\u003eRui Xu, Yen-Wei Chen, Shigehiro Morikawa, and Yoshimasa Kurumi\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e5.1 Introduction 155\u003c\/p\u003e \u003cp\u003e5.2 Parzen-Window-Based Normalized Mutual Information 157\u003c\/p\u003e \u003cp\u003e5.2.1 Definition of Parzen-Window Method 157\u003c\/p\u003e \u003cp\u003e5.2.2 Parzen-Window-Based Estimation of Joint Histogram 158\u003c\/p\u003e \u003cp\u003e5.2.3 Normalized Mutual Information and its Derivative 160\u003c\/p\u003e \u003cp\u003e5.3 Analysis of Kernel Selection 163\u003c\/p\u003e \u003cp\u003e5.3.1 The Designed Kernel 163\u003c\/p\u003e \u003cp\u003e5.3.2 Comparison in Theory 167\u003c\/p\u003e \u003cp\u003e5.3.3 Comparison by Experiments 170\u003c\/p\u003e \u003cp\u003e5.4 Application on MR-Guided Microwave Thermocoagulation of Liver Tumors 174\u003c\/p\u003e \u003cp\u003e5.4.1 Introduction of MR-Guided Microwave Thermocoagulation of Liver Tumors 174\u003c\/p\u003e \u003cp\u003e5.4.2 Nonrigid Registration by Parzen-Window-Based Mutual Information 175\u003c\/p\u003e \u003cp\u003e5.4.3 Evaluation on Phantom Data 177\u003c\/p\u003e \u003cp\u003e5.4.4 Evaluation on Clinical Cases 180\u003c\/p\u003e \u003cp\u003e5.5 Conclusion 185\u003c\/p\u003e \u003cp\u003eAcknowledgements 186\u003c\/p\u003e \u003cp\u003eReferences 187\u003c\/p\u003e \u003cp\u003e\u003cb\u003e6 2D\/3D Image Registration For Endovascular Abdominal Aortic Aneurysm (AAA) Repair 189\u003cbr\u003e\u003c\/b\u003e\u003ci\u003eShun Miao and Rui Liao\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e6.1 Introduction 189\u003c\/p\u003e \u003cp\u003e6.2 Background 190\u003c\/p\u003e \u003cp\u003e6.2.1 Image Modalities 190\u003c\/p\u003e \u003cp\u003e6.2.2 2D\/3D Registration Framework 192\u003c\/p\u003e \u003cp\u003e6.2.3 Feature-Based Registration 194\u003c\/p\u003e \u003cp\u003e6.2.4 Intensity-Based Registration 196\u003c\/p\u003e \u003cp\u003e6.2.5 Number of Imaging Planes 197\u003c\/p\u003e \u003cp\u003e6.2.6 2D\/3D Registration for Endovascular AAA Repair 198\u003c\/p\u003e \u003cp\u003e6.3 Smart Utilization of Two X-Ray Images for Rigid-Body 2D\/3D Registration 199\u003c\/p\u003e \u003cp\u003e6.3.1 2D\/3D Registration: Challenges in EVAR 199\u003c\/p\u003e \u003cp\u003e6.3.2 3D Image Processing and DRR Generation 202\u003c\/p\u003e \u003cp\u003e6.3.3 2D Image Processing 203\u003c\/p\u003e \u003cp\u003e6.3.4 Similarity Measure 205\u003c\/p\u003e \u003cp\u003e6.3.5 Optimization 207\u003c\/p\u003e \u003cp\u003e6.3.6 Validation 210\u003c\/p\u003e \u003cp\u003e6.4 Deformable 2D\/3D Registration 211\u003c\/p\u003e \u003cp\u003e6.4.1 Problem Formulation 212\u003c\/p\u003e \u003cp\u003e6.4.2 Graph-Based Difference Measure 213\u003c\/p\u003e \u003cp\u003e6.4.3 Length Preserving Term 215\u003c\/p\u003e \u003cp\u003e6.4.4 Smoothness Term 215\u003c\/p\u003e \u003cp\u003e6.4.5 Optimization 216\u003c\/p\u003e \u003cp\u003e6.4.6 Validation 217\u003c\/p\u003e \u003cp\u003e6.5 Visual Check of Patient Movement Using Pelvis Boundary Detection 220\u003c\/p\u003e \u003cp\u003e6.6 Discussion and Conclusion 222\u003c\/p\u003e \u003cp\u003eReferences 223\u003c\/p\u003e \u003cp\u003e\u003cb\u003ePARTIV OBJECT TRACKING 229\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e\u003cb\u003e7 Motion Tracking in Medical Images 231\u003cbr\u003e\u003c\/b\u003e\u003ci\u003eChuqing Cao, Chao Li, and Ying Sun\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e7.1 Introduction 232\u003c\/p\u003e \u003cp\u003e7.1.1 Point-Based Tracking 233\u003c\/p\u003e \u003cp\u003e7.1.2 Silhouette-Based Tracking 233\u003c\/p\u003e \u003cp\u003e7.1.3 Kernel-Based Tracking 233\u003c\/p\u003e \u003cp\u003e7.2 Background 234\u003c\/p\u003e \u003cp\u003e7.2.1 Point-Based Tracking 234\u003c\/p\u003e \u003cp\u003e7.2.2 Silhouette-Based Tracking 236\u003c\/p\u003e \u003cp\u003e7.2.3 Kernel-Based Tracking 237\u003c\/p\u003e \u003cp\u003e7.2.4 Summary 238\u003c\/p\u003e \u003cp\u003e7.3 Bayesian Tracking Methods 238\u003c\/p\u003e \u003cp\u003e7.3.1 Kalman Filters 239\u003c\/p\u003e \u003cp\u003e7.3.2 Particle Filters 240\u003c\/p\u003e \u003cp\u003e7.3.3 Summary of Bayesian Tracking Methods 241\u003c\/p\u003e \u003cp\u003e7.4 Deformable Models 241\u003c\/p\u003e \u003cp\u003e7.4.1 Mathematical Foundations of Deformable Models 241\u003c\/p\u003e \u003cp\u003e7.4.2 Energy-Minimizing Deformable Models 242\u003c\/p\u003e \u003cp\u003e7.4.3 Probabilistic Deformable Models 244\u003c\/p\u003e \u003cp\u003e7.4.4 Summary of Deformable Models 245\u003c\/p\u003e \u003cp\u003e7.5 Motion Tracking Based on the Harmonic Phase Algorithm 246\u003c\/p\u003e \u003cp\u003e7.5.1 HARP Imaging 246\u003c\/p\u003e \u003cp\u003e7.5.2 HARP Tracking 248\u003c\/p\u003e \u003cp\u003e7.5.3 Summary 249\u003c\/p\u003e \u003cp\u003e7.6 Case Study: Pseudo Ground Truth-Based Nonrigid Registration of MRI for Tracking the Cardiac Motion 250\u003c\/p\u003e \u003cp\u003e7.6.1 Data Fidelity Term 251\u003c\/p\u003e \u003cp\u003e7.6.2 Spatial Smoothness Constraint 252\u003c\/p\u003e \u003cp\u003e7.6.3 Temporal Smoothness Constraint 253\u003c\/p\u003e \u003cp\u003e7.6.4 Energy Minimization 254\u003c\/p\u003e \u003cp\u003e7.6.5 Preliminary Results 255\u003c\/p\u003e \u003cp\u003e7.6.6 Nonrigid Registration of Myocardial Perfusion MRI 255\u003c\/p\u003e \u003cp\u003e7.6.7 Experimental Results 259\u003c\/p\u003e \u003cp\u003e7.7 Discussion 264\u003c\/p\u003e \u003cp\u003e7.8 Conclusion and Near-Future Trends 265\u003c\/p\u003e \u003cp\u003eReferences 267\u003c\/p\u003e \u003cp\u003e\u003cb\u003ePARTV CLASSIFICATION 275\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e\u003cb\u003e8 Blood Smear Analysis, Malaria Infection Detection, and Grading from Blood Cell Images 277\u003cbr\u003e\u003c\/b\u003e\u003ci\u003eWei Xiong, Sim-Heng Ong, Joo-Hwee Lim, Jierong Cheng, and Ying Gu\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e8.1 Introduction 278\u003c\/p\u003e \u003cp\u003e8.2 Pattern Classification Techniques 282\u003c\/p\u003e \u003cp\u003e8.2.1 Supervised and Nonsupervised Learning 282\u003c\/p\u003e \u003cp\u003e8.2.2 Bayesian Decision Theory 283\u003c\/p\u003e \u003cp\u003e8.2.3 Clustering 284\u003c\/p\u003e \u003cp\u003e8.2.4 Support Vector Machines 286\u003c\/p\u003e \u003cp\u003e8.3 GWA Detection 287\u003c\/p\u003e \u003cp\u003e8.3.1 Image Analysis 288\u003c\/p\u003e \u003cp\u003e8.3.2 Association between the Object Area and the Number of Cells Per Object 289\u003c\/p\u003e \u003cp\u003e8.3.3 Clump Splitting 291\u003c\/p\u003e \u003cp\u003e8.3.4 Clump Characterization 293\u003c\/p\u003e \u003cp\u003e8.3.5 Classification 295\u003c\/p\u003e \u003cp\u003e8.4 Dual-Model-Guided Image Segmentation and Recognition 295\u003c\/p\u003e \u003cp\u003e8.4.1 Related Work 296\u003c\/p\u003e \u003cp\u003e8.4.2 Strategies and Object Functions 297\u003c\/p\u003e \u003cp\u003e8.4.3 Endpoint Adjacency Map Construction and Edge Linking 299\u003c\/p\u003e \u003cp\u003e8.4.4 Parsing Contours and Their Convex Hulls 300\u003c\/p\u003e \u003cp\u003e8.4.5 A Recursive and Greedy Splitting Approach 301\u003c\/p\u003e \u003cp\u003e8.4.6 Incremental Model Updating and Bayesian Decision 301\u003c\/p\u003e \u003cp\u003e8.5 Infection Detection and Staging 302\u003c\/p\u003e \u003cp\u003e8.5.1 Related Work 302\u003c\/p\u003e \u003cp\u003e8.5.2 Methodology 303\u003c\/p\u003e \u003cp\u003e8.6 Experimental Results 305\u003c\/p\u003e \u003cp\u003e8.6.1 GWA Classification 305\u003c\/p\u003e \u003cp\u003e8.6.2 RBC Segmentation 310\u003c\/p\u003e \u003cp\u003e8.6.3 RBC Classification 315\u003c\/p\u003e \u003cp\u003e8.7 Summary 320\u003c\/p\u003e \u003cp\u003eReferences 321\u003c\/p\u003e \u003cp\u003e\u003cb\u003e9 Liver Tumor Segmentation Using SVM Framework and Pathology Characterization Using Content-Based Image Retrieval 325\u003cbr\u003e\u003c\/b\u003e\u003ci\u003eJiayin Zhou, Yanling Chi, Weimin Huang, Wei Xiong, Wenyu Chen, Jimin Liu, and Sudhakar K. Venkatesh\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e9.1 Introduction 325\u003c\/p\u003e \u003cp\u003e9.2 Liver Tumor Segmentation Under a Hybrid SVM Framework 327\u003c\/p\u003e \u003cp\u003e9.2.1 Fundamentals of SVM for Classification 327\u003c\/p\u003e \u003cp\u003e9.2.2 SVM Framework for Liver Tumor Segmentation and the Problems 330\u003c\/p\u003e \u003cp\u003e9.2.3 A Three-Stage Hybrid SVM Scheme for Liver Tumor Segmentation 331\u003c\/p\u003e \u003cp\u003e9.2.4 Experiment 334\u003c\/p\u003e \u003cp\u003e9.2.5 Evaluation Metrics 335\u003c\/p\u003e \u003cp\u003e9.2.6 Results 336\u003c\/p\u003e \u003cp\u003e9.3 Liver Tumor Characterization by Content-Based Image Retrieval 338\u003c\/p\u003e \u003cp\u003e9.3.1 Existing Work and the Rationale of Using CBIR 339\u003c\/p\u003e \u003cp\u003e9.3.2 Methodology Overview and Preprocessing 340\u003c\/p\u003e \u003cp\u003e9.3.3 Tumor Feature Representation 341\u003c\/p\u003e \u003cp\u003e9.3.4 Similarity Query and Tumor Pathological Type Prediction 343\u003c\/p\u003e \u003cp\u003e9.3.5 Experiment 345\u003c\/p\u003e \u003cp\u003e9.3.6 Results 346\u003c\/p\u003e \u003cp\u003e9.4 Discussion 351\u003c\/p\u003e \u003cp\u003e9.4.1 About Liver Tumor Segmentation Using Machine Learning 351\u003c\/p\u003e \u003cp\u003e9.4.2 About Liver Tumor Characterization Using CBIR 353\u003c\/p\u003e \u003cp\u003e9.5 Conclusion 356\u003c\/p\u003e \u003cp\u003eReferences 357\u003c\/p\u003e \u003cp\u003e\u003cb\u003e10 Benchmarking Lymph Node Metastasis Classification for Gastric Cancer Staging 361\u003cbr\u003e\u003c\/b\u003e\u003ci\u003eSu Zhang, Chao Li, Shuheng Zhang, Lifang Pang, and Huan Zhang\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e10.1 Introduction 362\u003c\/p\u003e \u003cp\u003e10.1.1 Introduction of GSI-CT 363\u003c\/p\u003e \u003cp\u003e10.1.2 Imaging Findings of Gastric Cancer 366\u003c\/p\u003e \u003cp\u003e10.2 Related Feature Selection, Metric Learning, and Classification Methods 367\u003c\/p\u003e \u003cp\u003e10.2.1 Feature Extraction 367\u003c\/p\u003e \u003cp\u003e10.2.2 KNN 367\u003c\/p\u003e \u003cp\u003e10.2.3 Feature Selection 369\u003c\/p\u003e \u003cp\u003e10.2.4 AdaBoost and EAdaBoost Algorithms 374\u003c\/p\u003e \u003cp\u003e10.3 Preprocessing Method for GSI-CT Data 377\u003c\/p\u003e \u003cp\u003e10.3.1 Data Acquisition for GSI-CT Data 377\u003c\/p\u003e \u003cp\u003e10.3.2 Univariate Analysis 378\u003c\/p\u003e \u003cp\u003e10.4 Classification Results For GSI-CT Data of Gastric Cancer 379\u003c\/p\u003e \u003cp\u003e10.4.1 Experimental Results of mRMR-KNN 379\u003c\/p\u003e \u003cp\u003e10.4.2 Experimental Results of SFS-KNN 383\u003c\/p\u003e \u003cp\u003e10.4.3 Experimental Results of Metric Learning 385\u003c\/p\u003e \u003cp\u003e10.4.4 Experiments Results of AdaBoost and EAdaBoost 385\u003c\/p\u003e \u003cp\u003e10.4.5 Experiment Analysis 388\u003c\/p\u003e \u003cp\u003e10.5 Conclusion and Future Work 388\u003c\/p\u003e \u003cp\u003eAcknowledgment 388\u003c\/p\u003e \u003cp\u003eReferences 388\u003c\/p\u003e \u003cp\u003e\u003cb\u003ePARTVI KNOWLEDGE-BASED SYSTEMS 393\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e\u003cb\u003e11 The Use of Knowledge in Biomedical Image Analysis 395\u003cbr\u003e\u003c\/b\u003e\u003ci\u003eFlorence Cloppet\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e11.1 Introduction 395\u003c\/p\u003e \u003cp\u003e11.2 Data, Information, and Knowledge? 397\u003c\/p\u003e \u003cp\u003e11.2.1 Data Versus Information 397\u003c\/p\u003e \u003cp\u003e11.2.2 Knowledge Versus Information 398\u003c\/p\u003e \u003cp\u003e11.3 What Kind of Information\/Knowledge Can be Introduced? 399\u003c\/p\u003e \u003cp\u003e11.4 How to Introduce Information in Computer Vision Systems? 400\u003c\/p\u003e \u003cp\u003e11.4.1 Nature of Prior Information\/Knowledge 402\u003c\/p\u003e \u003cp\u003e11.4.2 Frameworks Allowing Prior Information Introduction 408\u003c\/p\u003e \u003cp\u003e11.5 Conclusion 418\u003c\/p\u003e \u003cp\u003eReferences 418\u003c\/p\u003e \u003cp\u003e\u003cb\u003e12 Active Shape Model for Contour Detection of Anatomical Structure 429\u003cbr\u003e\u003c\/b\u003e\u003ci\u003eHuiqi Li and Qing Nie\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e12.1 Introduction 429\u003c\/p\u003e \u003cp\u003e12.2 Background 430\u003c\/p\u003e \u003cp\u003e12.2.1 Free-Form Deformable Models 430\u003c\/p\u003e \u003cp\u003e12.2.2 Parametrically Deformable Models 432\u003c\/p\u003e \u003cp\u003e12.3 Methodology 434\u003c\/p\u003e \u003cp\u003e12.3.1 Point Distribution Model 434\u003c\/p\u003e \u003cp\u003e12.3.2 Active Shape Model (ASM) 436\u003c\/p\u003e \u003cp\u003e12.3.3 A Modified ASM 438\u003c\/p\u003e \u003cp\u003e12.4 Applications 440\u003c\/p\u003e \u003cp\u003e12.4.1 Boundary Detection of Optic Disk 440\u003c\/p\u003e \u003cp\u003e12.4.2 Lens Structure Detection 450\u003c\/p\u003e \u003cp\u003e12.5 Summary 456\u003c\/p\u003e \u003cp\u003eAcknowledgment 457\u003c\/p\u003e \u003cp\u003eReferences 457\u003c\/p\u003e \u003cp\u003e\u003cb\u003eIndex 463\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e\u003cb\u003eJoo-Hwee Lim\u003c\/b\u003e is the Head of the Visual Computing Department at the Institute for Infocomm Research (I2R), A*STAR, Singapore, and an Adjunct Associate Professor at the School of Computer Engineering, Nanyang Technological University, Singapore. He is the co-Director of IPAL (Image \u0026amp; Pervasive Access Laboratory), a French-Singapore Joint Lab. He established the medical image analysis group at I2R in 2006, collaborating with clinicians closely, resulting in strong competency in ocular imaging, brain image analysis, cell image understanding etc at the institute. He has published over 200 journal and conference papers and owns 17 patents in the areas of computer vision, cognitive vision, pattern recognition, and medical image analysis.\u003cbr\u003e\u003cbr\u003e\u003cb\u003eSim-Heng Ong\u003c\/b\u003e is an Associate Professor in the Departments of Electrical Engineering and Bioengineering at the National University of Singapore. He received his PhD from the University of Sydney, Australia. His major research areas are computer vision and medical image analysis and visualization. He has worked extensively with clinicians in developing algorithms for a variety of medical applications, and has publications in many highly respected journals and conferences.\u003cbr\u003e\u003cbr\u003e\u003cb\u003eWei Xiong\u003c\/b\u003e is a Research Scientist at the Institute for Infocomm Research (I2R), A*STAR, Singapore. He obtained his PhD degree from the National University of Singapore.  His research interest is in computer vision, image processing, pattern classification and acoustic imaging. Dr. Xiong has published over 60 technical papers.\u003c\/p\u003e \u003cp\u003e\u003cb\u003eA comprehensive guide to understanding and interpreting digital images in medical and functional applications\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e\u003cb\u003eBiomedical Image Understanding focuses on image understanding and semantic interpretation, with clear introductions to related concepts, in-depth theoretical analysis, and detailed descriptions of important biomedical applications. It covers image processing, image filtering, enhancement, de-noising, restoration, and reconstruction; image segmentation and feature extraction; registration; clustering, pattern classification, and data fusion.\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eWith contributions from experts in China, France, Italy, Japan, Singapore, the United Kingdom, and the United States, Biomedical Image Understanding:\u003c\/p\u003e \u003cp\u003e• Addresses motion tracking and knowledge-based systems, two areas which are not covered extensively elsewhere in a biomedical context\u003c\/p\u003e \u003cp\u003e• Describes important clinical applications, such as virtual colonoscopy, ocular disease diagnosis, and liver tumor detection\u003c\/p\u003e \u003cp\u003e• Contains twelve self-contained chapters, each with an introduction to basic concepts, principles, and methods, and a case study or application\u003c\/p\u003e \u003cp\u003eWith over 150 diagrams and illustrations, this bookis an essential resource for the reader interested in rapidly advancing research and applications in biomedical image understanding.\u003c\/p\u003e","brand":"Wiley","offers":[{"title":"Default Title","offer_id":47988838990053,"sku":"NP9781118715154","price":173.95,"currency_code":"USD","in_stock":false}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/1842\/7735\/files\/9781118715154.jpg?v=1761781723","url":"https:\/\/k12savings.com\/es\/products\/biomedical-image-understanding-isbn-9781118715154","provider":"K12savings","version":"1.0","type":"link"}