| 期刊全称 | Advanced Algorithmic Approaches to Medical Image Segmentation | | 期刊简称 | State-of-the-Art App | | 影响因子2023 | Jasjit S. Suri,S. Kamaledin Setarehdan,Sameer Sing | | 视频video | | | 发行地址 | No other book deals exclusively with the subject of medical image segmentation.It discusses state-of-the-art techniques, comprising contributions from authors from both industry and academia | | 学科分类 | Advances in Computer Vision and Pattern Recognition | | 图书封面 |  | | 影响因子 | Medical imaging is an important topic which is generally recognised as key to better diagnosis and patient care. It has experienced an explosive growth over the last few years due to imaging modalities such as X-rays, computed tomography (CT), magnetic resonance (MR) imaging, and ultrasound..This book focuses primarily on state-of-the-art model-based segmentation techniques which are applied to cardiac, brain, breast and microscopic cancer cell imaging. It includes contributions from authors based in both industry and academia and presents a host of new material including algorithms for:.- brain segmentation applied to MR;.- neuro-application using MR; .- parametric and geometric deformable models for brain segmentation;.- left ventricle segmentation and analysis using least squares and constrained least squares models for cardiac X-rays; .- left ventricle analysis in echocardioangiograms;.- breast lesion detection in digital mammograms;.detection of cells in cell images..As an overview of the latest techniques, this book will be of particular interest to students and researchers in medical engineering, image processing, computer graphics, mathematical modelling and data analysis. | | Pindex | Book 2002 |
| 1 |
Front Matter |
|
|
Abstract
|
| 2 |
,Basic Principles of Image Generation for Ultrasound, X-Rays, Magnetic Resonance, Computed Tomograph |
Jasjit S. Suri,S. K. Setarehdan,Rakesh Sharma,Sameer Singh,Yansun Xu,Laura Reden |
|
Abstract
The usual aim in generating any kind of image in a body organ is to decide whether or not an abnormality is present and/or to follow the temporal variations of the abnormality during the course of a therapeutic treatment. Therefore, the two main goals of a human expert observer are: to detect the abnormality and to recognize it as such. Logically, the detection must occur prior to any useful recognition, however both procedures can be aided by improving the quality of the image by means of any post-processing techniques.
|
| 3 |
,Segmentation in Echocardiographic Images, |
S. K. Setarehdan,John J. Soraghan |
|
Abstract
Echocardiography, ultrasonography of the living heart, has become an important basic tool of diagnosis, treatment evaluation, and research in cardiology. It has achieved a prominent place among the other cardiac imaging modalities for many practical and safety reasons. Since it is basically a pulse-echo imaging system it has all the advantages of the ultrasonic imaging techniques which were described in Chapter 1. Another important reason for its success is that the information it provides is helpful in understanding the mechanisms and evaluating the status and causes of cardiovascular disease in patients. It also provides anatomical information in terms of the heart chambers and their sizes.
|
| 4 |
,Segmentation and Quantification Techniques for Fitting Computer Vision Models to Cardiac MR, CT, X- |
Jasjit S. Suri |
|
Abstract
The field of medical imaging has experienced an explosive growth in recent years (1990-99) due to several imaging modalities, such as X-ray, computer tomography (CT), magnetic resonance imaging (MRI), positron emission tomography (PET) and spectral positron emission computer tomography (SPECT) (see Stytz . [135] for an extensive survey). The digital revolution and the processing power of computers combined with these modalities have helped humans understand to some extent the complex anatomy of the heart and its behavior. There are still, however, some unresolved problems which are linked to computer vision-pattern recognition (CVPR) and clinical cardiology research. The importance of cardiovascular research has increased, due to the inter-linking of effects arising from non-cardiovascular diseases. In the United States alone, the budget for cardiovascular research was $269 billion in 1997. This points towards the national concern and the degree of importance of cardiovascular research. As reported by the American Heart Association (AHA) [136] and the Herald Newspaper, UK [137], heart disease claims an enormous number of lives.
|
| 5 |
,Advances in Computer Vision, Graphics, Image Processing and Pattern Recognition Techniques for MR B |
Jasjit S. Suri,Sameer Singh,Xiaolan Zeng,Laura Reden |
|
Abstract
The importance of 2-D and 3-D brain segmentation has increased tremendously due to the recent growth in functional MRI (fMRI), perfusion-weighted imaging, diffusion-weighted imaging, volume graphics, 3-D segmentation, neurosurgical planning, navigation and MR brain scanning techniques. Besides that, recent growth in supervised and non-supervised brain segmentation techniques in 2-D (see Suri [322], Zavaljevski . [323], Barra . [324]) and 3-D (see Salle . [325], Kiebel . [326], Zeng . [327], Xu . [606], Fischl . [328], Linden . [329], Stokking [330], Smith [331], Hurdal [332] and ter Haar . [333]) have brought the engineering community, in areas such as computer vision, graphics, image processing (CVGIP) and pattern recognition, closer to the medical community, such as neuro-surgeons, psychiatrists, psychologists, physiologists, oncologists, radiologists and internists. This chapter is an attempt to review state-of-the-art cortical segmentation techniques in 2-D and 3-D using magnetic resonance imaging (MRI), and their applications. New challenges in this area are also discussed.
|
| 6 |
,Segmentation Techniques in the Quantification of Multiple Sclerosis Lesions in MRI, |
Rakesh Sharma,Jasjit S. Suri,Ponnada A. Narayana |
|
Abstract
Volumetry of the brain can provide fundamental information about the development and function of the normal human brain and can yield important clues for pathology in patients suffering from neurological brain disorders (see Jernigan . [713]). Valuable information has been gained about the pathological processes in epilepsy (see Stone . [714]) and Alzheimer’s disease (see Tanabe . [715]) from the volume measurements of various brain structures. Brain tissue in Alzheimer’s disease was compared with elderly control volunteers by using an MR-based computerized segmentation program. Semi- automated segmentation of MR brain images revealed significant brain atrophy with significant white matter hyperintensities. In many focal diseases such as Multiple Sclerosis (MS) and cancer, the total lesion volume is indicative of the overall disease burden and may be useful in the quantification and objective evaluation of therapeutic intervention in disease (see Dastidar . [716] and Fillippi . [717]). These investigators demonstrated that MRI images provide excellent quantitative MRI tissue volume measurement. Different tissues can be identified on the images, either manually or by computer-assist
|
| 7 |
,Finite Mixture Models, |
Sanjay S. Gopal |
|
Abstract
Image segmentation can be considered to be essentially a process of classifying the pixels in a two-dimensional (2D) image into different subsets of classes. If the number of classes is known or can be estimated then we can associate a numeric label with each class. Pixel labeling then consists of assigning a numeric label to each pixel. Various different metrics can be used for arriving at a distinct label configuration for the pixels in an image. These include simple grey level thresholding, color, or local property values such as those which measure texture or region homogeneity.
|
| 8 |
,Application of Segmentation in Localized MR Chemical Shift Imaging and MR Spectroscopy, |
Rakesh Sharma |
|
Abstract
Since the discovery of NMR (Nuclear Magnetic Resonance) half a century ago, biophysical NMR approaches to brain imaging have shifted to non-invasive methods. Mainly brain segmentation, metabolic mapping and steady-state biochemical approaches are now being explored for normal and developmental neurochemistry with an exposure to common disorders of brain functions. Basically, NMR detects frequency dependent signals from individual odd numbered atomic nuclei. MRI (Magnetic Resonance Imaging) detects signals from populations of these nuclei at different locations in the tissues. Major advancements have been made in non-invasive MR imaging in two directions. Spatial information with good resolution in different tissue locations was achieved primarily by segmentation. Spatial information of metabolites and the peak sensitivity of metabolites were achieved by Chemical Shift Imaging (CSI). There exists a trade-off between these two informations. The highest quality of spatial chemical information by the MR technique is affected by the trade-off due to several physical and chemical factors. Localized MR Spectroscopy still remains a powerful tool to identify neuro-chemicals and metabolite c
|
| 9 |
,Fast WM/GM Boundary Segmentation From MR Images Using The Relationship Between Parametric and Geome |
Jasjit S. Suri |
|
Abstract
The role of fast shape recovery has always been a critical component in 2-D and 3-D medical imagery since it assists largely in medical therapy such as image guided surgery applications. The applications of shape recovery have been increasing since scanning methods became faster, more accurate and less artifacted (see Chapter 4). Shape recovery of medical organs is more difficult compared to other computer vision and imaging fields. This is primarily due to the large shape variability, structure complexity, several kinds of artifacts and restrictive body scanning methods (the scanning ability is limited to acquiring images in three orthogonal and oblique directions only). The recovery of the White Matter (WM) and Gray Matter (GM) boundaries in the human brain slices is a challenge due to its highly convoluted structure (see Plate 3). In spite of the above complications, we have started to explore faster and more accurate software tools for shape recovery in 2-D and 3-D applications.
|
| 10 |
,Medical Image Segmentation in Digitial Mammography, |
Sameer Singh,Keir Bovis |
|
Abstract
Medical image segmentation is of primary importance in the development of Computer Assisted Detection (CAD) in mammographic systems. The identification of calcifications and masses requires highly sophisticated techniques that can isolate regions of interest from noisy backgrounds. The main objective of this chapter is to highlight the various issues related to digital mammography by providing a brief overview of the segmentation techniques used in this area. We first introduce the role of image segmentation in mammography in section 9.2. This section discusses a typical image analysis system for digital mammography and discusses the issues related to difficulties with segmentation. In order to understand the segmentation process, it is important to discuss some salient aspects of breast anatomy. This is detailed in Section 9.3. Various breast components are explained alongside the description of breast cancers. Image acquisition and storage formats are important as a predecessor to image analysis in mammography and these are discussed next in Section 9.4. This section also discusses different modes of mammography, image digitization and commonly used formats. Image segmentation ca
|
| 11 |
,Cell Image Segmentation for Diagnostic Pathology, |
Dorin Comaniciu,Peter Meer |
|
Abstract
The colors associated with a digitized specimen representing peripheral blood smear are typically characterized by only a few, non-Gaussian clusters, whose shapes have to be discerned solely from the image being processed. Nonparametric methods such as mode-based analysis [952], are particularly suitable for the segmentation of this type of data since they do not constrain the cluster shapes. This chapter reviews an efficient cell segmentation algorithm that detects clusters in the . color space and delineates their borders by employing the gradient ascent mean shift procedure [950], [951]. The color space is randomly tessellated with search windows that are moved till convergence to the nearest mode of the underlying probability distribution. After the pruning of the mode candidates, the colors are classified using the basins of attraction. The segmented image is derived by mapping the color vectors in the image domain and enforcing spatial constraints.
|
| 12 |
,A Note on Future Research in Segmentation Techniques Applied to Neurology, Cardiology, Mammography |
Jasjit S. Suri,Sameer Singh,S. K. Setarehdan,Rakesh Sharma,Keir Bovis,Dorin Comaniciu,Laura Reden |
|
Abstract
In previous chapters, we saw the application of segmentation in different areas of the body, such as the brain, heart, breast and cells. We covered many different kinds of models of CVGIP. and PR., but with the pace at which research in segmentation is progressing, this book would be incomplete if it did not also envision the future of segmentation techniques for the above mentioned areas. Therefore, we present in this chapter the future aspects of the segmentation techniques covered in this book.
|
| 13 |
Back Matter |
|
|
Abstract
|
|
|
发表于 2025-3-21 18:28:42
