Handbook of Biomedical Image Analysis: Segmentation Models (Volume II) is dedicated to the segmentation of complex shapes from the field of imaging sciences using different mathematicaltechniques. This volume is aimed at researchers and educators in imaging sciences, radiological imaging, clinical and diagnostic imaging, physicists covering different medical imaging modalities, as well as researchers in biomedical engineering, applied mathematics, algorithmic development, computer vision, signal processing, computer graphics and multimedia in general, both in academia and industry.

Key Features:

--- Model-based brain tissue classification

--- Supervised texture classification for intravascular tissue characterization

--- Medical image segmentation: methods and applications in functional imaging

--- Automatic segmentation of pancreatic tumors in CT

--- Computerized analysis and vasodilation parameterization in flow-mediated dilation tests from ultrasonic image sequences

--- Adaptive approaches to optical segmentation in brain MRI Images

--- Automatic analysis of color fundus photographs and its application to the diagnosis of diabetic retinopathy

--- Segmentation issues of carotid plaque analysis in MRI

--- Accurate lumen identification, detection, and quantification in MR plaque volumes

--- Hessian-based multiscale enhancement, description, and quantification of second-order 3D local structures from medical volume data

--- A knowledge-based scheme for digital mammography

--- Simultaneous fuzzy segmentation

--- CAD of mammographic calicification: impact of segmentation

About the Editors:

Jasjit Suri, Ph.D. has spent over 20 years in the field of computer and electrical engineering, and more than a decade in imaging sciences. Dr. Suri has a masters degree in computer sciences from the University of Illinois and a doctorate in Electrical Engineering from the University of Washington, Seattle. Dr. Suri has published over 125 technical publications in medical imaging, as well as being a senior member of IEEE and a member of the engineering honor societies Eta-Kappa-Nu and Tau-Beta-Phi, and a recipient of the President's Gold Medal in 1980. He is also a fellow of American Institute of Medical and Biological Engineering.

David Wilson, Ph D. is a Professor of Biomedical Engineering and Radiology at Case Western Reserve University, having gained his doctorate from Rice University. He has over 60 refereed journal publications and is co-owner of several patents. Professor Wilson has actively developed biomedical imaging at CWRU. He has led a faculty recruitment effort, and he has served as PI or has been an active leader on multiple research and equipment developmental awards given to CWRU, including an NIH planning grant award for an in vivo Cellular and Molecular Imaging Center and an Ohio Wright Center of Innovation award. Swamy Laxminarayan, Dsc championed the field of Biomedical Engineering for over 30 years, having held a variety of senior positions within the industry. He is an internationally recognized scientist, engineer, and educator and has been published in over 200 technical publications in biomedical information technology, computation biology, signal and image processing, biotechnology, and physiological system modeling. Prof. Laxminarayan is a fellow of AIMBE and a recipient of IEEE 3rd Millennium Medal.

Autorentext
Jasjit Suri, Ph.D. has spent the last 20 years in the field of computer and electrical engineering, and more than a decade in imaging sciences. Dr. Suri has a masters in computer sciences from the University of Illinois, a doctorate from the University of Washington, Seattle, and will soon receive his EMBA from the Weatherhead School of Management at Case Western Reserve University, Cleveland, Ohio. Dr. Suri has published over 100 technical publications in medical imaging, is a senior member of IEEE, member of the engineering honor societies Eta-Kappa-Nu and Tau-Beta-Phi, and a recipient of the President's Gold Medal in 1980. Prof. Swamy Laxminarayan, D.Sci. championed the field of Biomedical Engineering for over 30 years having held a variety of senior positions within the industry. He is an internationally recognized scientist, engineer, and educator with over 200 technical publications in biomedical information technology, computation biology, signal and image processing, biotechnology, and physiological system modeling. Prof. Laxminarayan is a fellow of AIMBE and a recipient of IEEE 3rd Millennium Medal.

Zusammenfassung
In Chapter 1 we present in detail a framework for fully automated brain tissue classi?cation. The framework consists of a sequence of fully automated state of the art image registration (both rigid and nonrigid) and image segmentation algorithms. Modelsofthespatialdistributionofbraintissuesarecombinedwith models of expected tissue intensities, including correction of MR bias ?elds and estimation of partial voluming. We also demonstrate how this framework can be applied in the presence of lesions. Chapter 2 presents the intravascular ultrasound (IVUS), which is a to- graphic imagingtechnique that has provideduniquetoolforobservationand- pervision of vessel structures and exact vascular dimensions. In this way, it has contributed to the better understanding of the coronary content and processes: vascularremodelling,plaquemorphology,andevolution,etc. Mostinvestigators are convinced that the best way to detect plaque ruptures is by IVUS sequences. At the same time, cardiologists con?rm that due to the speckle nature of IVUS images, conventional IVUS imaging is dif?cult to clearly diagnose potentially vulnerable plaques due to the image resolution, lack of contours, speckle - tion, etc. Advanced automatic classi?cation techniques can signi?cantly help the physicians take decisions about different classes of tissue morphology. The characterizationoftissueandplaqueinvolvesdifferentproblems. Imagefeature spacedeterminesthereliabledescriptionsthatshouldbesuf?cientlyexpressive tocapturedifferencesbetweendifferentclassesbutatthesametimeshouldnot increaseunnecessarilythecomplexityoftheclassi?cationproblem. Weconsider and compare a wide set of different feature spaces (Gabor ?lters, DOG ?lters, cooccurrence matrices, binary local patterns, etc). In particular, we show that xiii xiv Preface the binary local patterns represent an optimal description of ultrasound regions that at the same time allow real-time processing of images.

Inhalt
Model-Based Brain Tissue Classification.- Supervised Texture Classification for Intravascular Tissue Characterization.- Medical Image Segmentation: Methods and Applications in Functional Imaging.- Automatic Segmentation of Pancreatic Tumors in Computed Tomography.- Computerized Analysis and Vasodilation Parameterization in Flow-Mediated Dilation Tests from Ultrasonic Image Sequences.- Statistical and Adaptive Approaches for Optimal Segmentation in Medical Images.- Automatic Analysis of Color Fundus Photographs and Its Application to the Diagnosis of Diabetic Retinopathy.- Segmentation Issues in Carotid Artery Atherosclerotic Plaque Analysis with MRI.- Accurate Lumen Identification, Detection, and Quantification in MR Plaque Volumes.- Hessian-Based Multiscale Enhancement, Description, and Quantification of Second-Order 3-D Local Structures from Medical Volume Data.- A Knowledge-Based Scheme for Digital Mammography.- Simultaneous Fuzzy Segmentation of Medical Images.- Computer-Aided Diagnosis of Mammographic Calcification Clusters: Impact of Segmentation.- Computer-Supported Segmentation of Radiological Data.