دانلود کتاب Computer Vision in Medical Imaging (Series in Computer Vision, 2)

فهرست مطالب :

CONTENTS\nPreface\nChapter 1 An Introduction to Computer Vision in Medical Imaging Chi Hau Chen\n 1. Introduction\n 2. Some Medical Imaging Methods\n 2.1. X-ray\n 2.2. Magnetic Resonance Image (MRI)\n 2.3. Intravascular Ultrasound (IVUS)\n 3. Roles of Computer Vision, Image Processing and Pattern Recognition\n 4. Active Contours\n 4.1. Snakes\n 4.2. Level set methods\n 4.3. Geodesic active contours\n 4.4. Region-based active contours\n 4.5. Hybrid evolution method\n 4.6. IVUS image segmentation\n 5. Concluding Remarks\n Acknowledgment\n References\nPart 1 Theory and Methodologies\n Chapter 2 Distribution Matching Approaches to Medical Image Segmentation Ismail Ben Ayed\n 1. Introduction\n 2. Formulations\n 3. Optimization Aspects\n 3.1. Specialized optimizers\n 3.2. Derivative-based optimizers\n 3.2.1. Active curves and level sets\n 3.2.2. Line search and trust region methods\n 3.3. Bound optimizers\n 3.3.1. Graph cuts\n 3.3.2. Convex-relaxation techniques\n 4. Medical Imaging Applications\n 4.1. Left ventricle segmentation in cardiac images\n 4.1.1. Example\n 4.2. Vertebral-body segmentation in spine images\n 4.2.1. Example\n 4.3. Brain tumor segmentation\n 5. Conclusion and Outlook\n References\n Chapter 3 Digital Pathology in Medical Imaging Bikash Sabata, Chukka Srinivas, Pascal Bamford and Gerardo Fernandez\n 1. Introduction\n A. Subtyping and the role of digital pathology\n B. Quantification of IHC markers\n C. Tissue and stain variability\n D. Rules-based segmentation and identification\n E. Learning from image data examples\n F. Object-based learning models\n G. Membrane detection algorithms\n H. HER2 Dual ISH slide scoring algorithm\n 2. DP Enabled Applications\n 3. Multiplexed Quantification\n 4. Quantification Algorithms\n 5. Summary\n Acknowledgment\n References\n Chapter 4 Adaptive Shape Prior Modeling via Online Dictionary Learning Shaoting Zhang, Yiqiang Zhan, Yan Zhou and Dimitris Metaxas\n 1. Introduction\n 2. Relevant Work\n 3. Methodology\n 3.1. Sparse Shape Composition\n 3.2. Shape Dictionary Learning\n 3.3. Online Shape Dictionary Update\n 4. Experiments\n 4.1. Lung Localization\n 4.2. Real-time Left Ventricle Tracking\n 5. Conclusions\n References\n Chapter 5 Feature-Centric Lesion Detection and Retrieval in Thoracic Images Yang Song, Weidong Cai, Stefan Eberl, Michael J Fulham and David Dagan Feng\n 1. Lesion Detection\n 1.1. Review of State-of-the-art\n 1.2. Region-based Feature Classification\n 1.2.1. Region Type Identification\n 1.2.2. Region Type Refinement\n 1.2.3. 3D Object Localization\n 1.3. Multi-stage Discriminative Model\n 1.3.1. Abnormality Detection\n 1.3.2. Tumor and Lymph Node Differentiation\n 1.3.3. Tumor Region Refinement\n 1.3.4. Experimental Results\n 1.4. Data Adaptive Structure Estimation\n 1.4.1. Initial Abnormality Detection\n 1.4.2. Adaptive Structure Estimation\n 1.4.3. Feature Extraction and Classification\n 1.4.4. Experimental Results\n 2. Thoracic Image Retrieval\n 2.1. Review of State-of-the-art\n 2.2. Pathological Feature Description\n 2.3. Spatial Feature Encoding\n 2.3.1. Pathological Centroid Detection\n 2.3.2. Context-based Partitioning Model\n 2.3.3. Similarity Measure\n 2.3.4. Experimental Results\n 3. Summary\n References\n Chapter 6 A Novel Paradigm for Quantitation from MR Phase Joseph Dagher\n 1. Introduction to Phase Mapping in MRI\n 2. Theory\n 2.1. Novel paradigm: Phase Ambiguity functions\n 2.2. Proposed solution: MAGPI\n 2.3. Corresponding estimation method: CL2D\n 3. Results\n 3.1. Simulation results\n 3.2. Real phantom results\n 3.3. In Vivo results\n 4. Discussion and Conclusions\n References\n Chapter 7 A Multi-Resolution Active Contour Framework for Ultrasound Image Segmentation Weiming Wang, Jing Qin, Pheng-Ann Heng, Yim-Pan Chui, Liang Li and Bing Nan Li\n 1. Introduction\n 2. Methods\n 2.1. LGD-driven Active Contour Models\n 2.2. Phase-based Geodesic Active Contours\n 2.2.1. Monogenic Signal\n 2.2.2. FA-based Edge Stop Function\n 3. Experiments and Results\n 4. Conclusions\n Acknowledgments\n References\nPart 2 2-D, 3-D Reconstructions/Imaging Algorithms, Systems & Sensor Fusion\n Chapter 8 Model-Based Image Reconstruction in Optoacoustic Tomography Amir Rosenthal, Daniel Razansky and Vasilis Ntziachristos\n 1. Introduction\n 2. The model matrix\n 3. Image formation\n 4. Wavelet-packet formulation\n 5. Conclusions\n References\n Chapter 9 The Fusion of Three-Dimensional Quantitative Coronary Angiography and Intracoronary Imaging for Coronary Interventions Shengxian Tu, Niels R. Holm, Johannes P. Janssen and Johan H. C. Reiber\n 1. Introduction\n 2. Three-dimensional Angiographic Reconstruction and QCA\n 3. Fusion of 3D QCA and IVUS/OCT\n 4. Validations\n 4.1. Co-registration of X-ray angiography and IVUS/OCT\n Materials and methods\n Statistics\n Results\n 4.2. Comparison of lumen dimensions by 3D QCA and IVUS/OCT\n Materials and methods\n Statistics\n Results\n 5. Discussions\n Co-registration of X-ray angiography and IVUS/OCT\n Lumen sizing assessed by different imaging modalities\n 6. Conclusions\n Acknowledgements\n References\n Chapter 10 Three-Dimensional Reconstruction Methods in Near-Field Coded Aperture for SPECT Imaging System Stephen Baoming Hong\n 1. Introduction\n 2. Theory & Method\n 2.1. Coded aperture imaging and decoding\n 2.2. Iterative reconstruction of 2D coded aperture SPECT imaging\n 2.3. Iterative reconstruction of 3D coded aperture SPECT imaging\n 3. Coded Aperture SPECT Imaging Systems and Phantom Experimental Results\n 3.1. Coded aperture SPECT imaging systems\n 3.2. Experimental setup\n 3.2(a) Reconstruct a simple 3D pyramid shaped phantom\n 3.2(b) Experimental setup and results for micro hot rod phantom\n 4. Discussions\n 5. Conclusion\n Acknowledgements\n References\n Chapter 11 Ultrasound Volume Reconstruction based on Direct Frame Interpolation Sergei Koptenko, Rachel Remlinger, Martin Lachaine,Tony Falco and Ulrich Scheipers\n 1. Introduction\n 2. Overview of volume reconstruction methods\n Voxel Nearest Neighbor\n Pixel Nearest Neighbor\n Description of Pixel Nearest Neighbor Methods Selected as a Test Benchmark\n Other Methods\n 3. Description of the direct frame interpolation method\n 4. Methods\n 5. Results\n Gray level error\n Computation Times\n 6. Conclusion\n Acknowledgements\n References\n Chapter 12 Deconvolution Technique for Enhancing and Classifying the Retinal Images Uvais A. Qidwai and Umair A. Qidwai\n 1. Introduction\n 2. Background\n 3. The Deconvolutional Model\n 4. Restoration of Images\n 5. Problem Formulation\n 5.1. The Retinal images\n 6. Proposed Algorithm\n 6.1. For RGB Images\n 6.2. For Fluorescence Angiographic Images\n 6.3. Region Growing for FA\n 7. Results and Discussion\n 7.1. Image Enhancement for RGB Images\n 8. Conclusion\n References\n Chapter 13 Medical Ultrasound Digital Signal Processing in the GPU Computing Era Marcin Lewandowski\n 1. Foreword\n 2. Signal architecture and processing in ultrasonography\n 3. Hardware architecture\n 4. GPUs\n 4.1. GPU Software & Hardware\n 4.2. Use in ultrasonography\n 4.3. GPU implementation issues\n 4.3.1. Optimisation of SAFT implementation on GPU\n 5. Summary and outlook\n Acknowledgments\n References\n Chapter 14 Developing Medical Image Processing Algorithms for GPU Assisted Parallel Computation Mathias Broxvall and Marios Daoutis\n 1. Introduction\n 2. Background\n 2.1. GPU parallel architectures\n 2.1.1. CUDA\n 2.1.2. OpenCL\n 2.2. Standard mathematical building blocks\n 3. Methods\n 3.1. Convolutions\n 3.1.1. Analysing the performance of a kernel\n 3.1.2. Reworking a memory bound algorithm\n 3.2. Multidimensional adaptive filtering\n 3.2.1. Mathematical model\n 3.2.2. GPU implementation\n 3.2.3. Computational performance\n 3.3. Line detection\n 4. Applications\n 4.1. Image de-noising in 4D echocardiography using adaptive filters\n 4.1.1. Hardware & Software\n 4.1.2. Handling border data\n 4.1.3. Results\n 4.2. Automatic needle detection for image guided HDR prostate brachytherapy treatment\n 5. Discussion\n 5.1. Applications\n 5.2. Numerical precision of arithmetic operations\n References\nPart 3 Specific Image Processing and Computer Vision Methods for Different Imaging Modalities Including IVUS, MRI, etc\n Chapter 15 Computer Vision in Interventional Cardiology Kendall R. Waters\n 1. Introduction\n 2. Coronary Artery Disease\n 2.1. To Treat or Not To Treat\n 2.2. Optimizing the Intervention\n 2.2.1. Angiography\n 2.2.2. Intravascular Ultrasound\n 2.2.3. Intracoronary Optical Coherence Technology\n 2.2.4. Intravascular Near-Infrared Spectroscopy\n 2.3. Emerging Technologies\n 2.3.1. FFRCT\n 2.3.2. Intravascular Photoacoustics\n 3. Valvular Heart Disease\n 3.1. Prevalence and Treatment\n 3.2. Echocardiographic Guidance and Computer Vision\n 4. Summary\n References\n Chapter 16 Pattern Classification of Brain Diffusion MRI: Application to Schizophrenia Diagnosis Ali Tabesh, Matthew J. Hoptman, Debra D’Angelo and Babak A. Ardekani\n 1. Introduction\n 2. Review of Pattern Classification\n 2.1. Standardization and Dimensionality Reduction\n 2.2. Pattern Classifiers\n 2.2.1. Linear Gaussian Classifier\n 2.2.2. L1-Regularized Logistic Regression\n 2.2.3. k-Nearest Neighbor Classifier\n 2.2.4. Support Vector Classifier\n 2.3. Discriminant Pattern\n 2.4. Error Estimation\n 3. Application to Schizophrenia Diagnosis\n 3.1. Participants\n 3.2. Image Acquisition\n 3.3. Image Processing\n 4. Results and Discussion\n 5. Conclusions\n Acknowledgments\n References\n Chapter 17 On Compressed Sensing Reconstruction for Magnetic Resonance Imaging Benjamin Paul Berman, Sagar Mandava and Ali Bilgin\n 1. Introduction\n 2. Principles of Signal Generation and Detection in MRI\n 3. Compressed Sensing Theory\n 4. Sparsity in MRI\n 4.1. Wavelet sparsity\n 4.2. Total Variation\n 5. Data Acquisition in MRI\n 6. Reconstruction Methods\n 6.1. Nonlinear Conjugate Gradient (NLCG)\n 6.2. Projection Onto Convex Sets (POCS)\n 6.3. Iterative Hard Thresholding (IHT)\n 6.4. Comparison\n 7. Conclusion\n 8. Acknowledgment\n References\n Chapter 18 On Hierarchical Statistical Shape Models with Application to Brain MRI Juan J. Cerrolaza, Arantxa Villanueva and Rafael Cabeza\n 1. Introduction\n 2. Active Shape Models\n 2.1. Shape Model Construction using PDMs\n 2.2. Appearance Model\n 3. Multi-Resolution Representation of Composed Structures\n 3.1. Matrix Notation in Wavelet Filtering\n 3.2. Wavelet Filtering of Multi-Object Structures\n 4. Hierarchical PDMs Using Wavelets\n 4.1. Previous Approaches\n 4.2. General Description of the Algorithm\n 4.3. Mathematical Formulation\n 4.4. Grouping of Shapes\n 5. Results and Discussion\n 5.1. Experimental Set-up\n 5.2. Results\n 6. Summary and Conclusions\n Appendix A. Extension to 3D\n References\n Chapter 19 Advanced PDE-based Methods for Automatic Quantification of Cardiac Function and Scar from Magnetic Resonance Imaging Durco Turco and Cristiana Corsi\n 1. PDEs in Medical Image Segmentation\n 2. Cardiac Magnetic Resonance Imaging\n 3. Methods for Ventricular Volume Estimation\n 3.1. The basic level set model\n 3.1.1. Initial condition setting\n 3.1.2 Numerical implementation\n 3.1.3. Data analysis\n 3.1.4. Results\n 3.2. The “region-based” level set model\n 3.2.1. Numerical implementation\n 3.2.2. Data analysis\n 3.2.3. Results\n 4. Scar Quantification\n 5. Discussion\n 6. Conclusion\n References\n Chapter 20 Automated IVUS Segmentation Using DeformableTemplate Model with Feature Tracking Prakash Manandhar and Chi Hau Chen\n 1. Introduction\n 2. Guidewire detection and tracking\n 3. Catheter position and vessel diameter estimate using the Circular Hough Transform (CHT)\n 4. Deformable template model for IVUS\n 5. Concluding Remarks\n Acknowledgements\n References\nIndex