Biomedical Image Analysis

Computers have become an integral part of medical imaging systems and are used for everything from data acquisition and image generation to image display and analysis. As the scope and complexity of imaging technology steadily increase, more advanced techniques are required to solve the emerging challenges. Biomedical Image Analysis demonstrates the benefits reaped from the application of digital image processing, computer vision, and pattern analysis techniques to biomedical images, such as adding objective strength and improving diagnostic confidence through quantitative analysis. The book focuses on post-acquisition challenges such as image enhancement, detection of edges and objects, analysis of shape, quantification of texture and sharpness, and pattern analysis, rather than on the imaging equipment and imaging techniques. Each chapter addresses several problems associated with imaging or image analysis, outlining the typical processes, then detailing more sophisticated methods directed to the specific problems of interest. Biomedical Image Analysis is useful for senior undergraduate and graduate biomedical engineering students, practicing engineers, and computer scientists working in diverse areas such as telecommunications, biomedical applications, and hospital information systems.

Table of Contents:
PREFACE THE NATURE OF BIOMEDICAL IMAGES Body Temperature as an Image Transillumination Light Microscopy Electron Microscopy X-ray Imaging Tomography Nuclear Medicine Imaging Ultrasonography Magnetic Resonance Imaging Objectives of Biomedical Image Analysis Computer-aided Diagnosis Remarks Study Questions and Problems Laboratory Exercises and Projects IMAGE QUALITY AND INFORMATION CONTENT Difficulties in Image Acquisition and Analysis Characterization of Image Quality Digitization of Images Optical Density Dynamic Range Contrast Histogram Entropy Blur and Spread Functions Resolution The Fourier Transform and Spectral Content Modulation Transfer Function Signal-to-Noise Ratio Error-based Measures Application: Image Sharpness and Acutance Remarks Study Questions and Problems Laboratory Exercises and Projects REMOVAL OF ARTIFACTS Characterization of Artifacts Synchronized or Multiframe Averaging Space-domain Local-statistics-based Filters Frequency-domain Filters Matrix Representation of Image Processing Optimal Filtering Adaptive Filters Comparative Analysis of Filters for Noise Removal Application: Multiframe Averaging in Confocal Microscopy Application: Noise Reduction in Nuclear Medicine Imaging Remarks Study Questions and Problems Laboratory Exercises and Projects IMAGE ENHANCEMENT Digital Subtraction Angiography Dual-energy and Energy-subtraction X-ray Imaging Temporal Subtraction Gray-scale Transforms Histogram Transformation Convolution Mask Operators High-frequency Emphasis Homomorphic Filtering for Enhancement Adaptive Contrast Enhancement Objective Assessment of Contrast Enhancement Application: Contrast Enhancement of Mammograms Remarks Study Questions and Problems Laboratory Exercises and Projects DETECTION OF REGIONS OF INTEREST Thresholding and Binarization Detection of Isolated Points and Lines Edge Detection Segmentation and Region Growing Fuzzy-set-based Region Growing to Detect Breast Tumors Detection of Objects of Known Geometry Methods for the Improvement of Contour or Region Estimates Application: Detection of the Spinal Canal Application: Detection of the Breast Boundary in Mammograms Application: Detection of the Pectoral Muscle in Mammograms Application: Improved Segmentation of Breast Masses by Fuzzy-set-based Fusion of Contours and Regions Remarks Study Questions and Problems Laboratory Exercises and Projects ANALYSIS OF SHAPE Representation of Shapes and Contours Shape Factors Fourier Descriptors Fractional Concavity Analysis of Spicularity Application: Shape Analysis of Calcifications Application: Shape Analysis of Breast Masses and Tumors Remarks Study Questions and Problems Laboratory Exercises and Projects ANALYSIS OF TEXTURE Texture in Biomedical Images Models for the Generation of Texture Statistical Analysis of Texture Laws' Measures of Texture Energy Fractal Analysis Fourier-domain Analysis of Texture Segmentation and Structural Analysis of Texture Audification and Sonification of Texture in Images Application: Analysis of Breast Masses Using Texture and Gradient Measures {627} Remarks Study Questions and Problems Laboratory Exercises and Projects ANALYSIS OF ORIENTED PATTERNS Oriented Patterns in Images Measures of Directional Distribution Directional Filtering Gabor Filters Directional Analysis via Multiscale Edge Detection Hough-Radon Transform Analysis Application: Analysis of Ligament Healing Application: Detection of Breast Tumors Application: Bilateral Asymmetry in Mammograms Application: Architectural Distortion in Mammograms Remarks Study Questions and Problems Laboratory Exercises and Projects IMAGE RECONSTRUCTION FROM PROJECTIONS Projection Geometry The Fourier Slice Theorem Backprojection Algebraic Reconstruction Techniques Imaging with Diffracting Sources Display of CT Images Agricultural and Forestry Applications Microtomography Application: Analysis of the Tumor in Neuroblastoma Remarks Study Questions and Problems Laboratory Exercises and Projects DECONVOLUTION, DEBLURRING, AND RESTORATION Linear Space-invariant Restoration Filters Blind Deblurring Homomorphic Deconvolution Space-variant Restoration Application: Restoration of Nuclear Medicine Images Remarks Study Questions and Problems Laboratory Exercises and Projects IMAGE CODING AND DATA COMPRESSION Considerations Based on Information Theory Fundamental Concepts of Coding Direct Source Coding Application: Source Coding of Digitized Mammograms The Need for Decorrelation Transform Coding Interpolative Coding Predictive Coding Image Scanning Using the Peano-Hilbert Curve Image Coding and Compression Standards Segmentation-based Adaptive Scanning Enhanced JBIG Coding Lower-limit Analysis of Lossless Data Compression Application: Teleradiology Remarks Study Questions and Problems Laboratory Exercises and Projects PATTERN CLASSIFICATION AND DIAGNOSTIC DECISION Pattern Classification Supervised Pattern Classification Unsupervised Pattern Classification Probabilistic Models and Statistical Decision Logistic Regression The Training and Test Steps Neural Networks Measures of Diagnostic Accuracy Reliability of Features, Classifiers, and Decisions Application: Image Enhancement for Breast Cancer Screening Application: Classification of Breast Masses and Tumors via Shape Analysis Application: Content-based Retrieval and Analysis of Breast Masses Remarks Study Questions and Problems Laboratory Exercises and Projects REFERENCES INDEX