Mode of access: World Wide Web.

System requirements: Adobe Acrobat reader.

Part of: Synthesis digital library of engineering and computer science.

Series from website.

Includes bibliographical references (p. 127-138) and index.

Introduction to medical image analysis -- Medical diagnostic imaging -- Imaging modalities -- Tissue characterization in CT images -- Computer-aided analysis of medical images -- Knowledge-based segmentation -- Atlas-based segmentation -- Landmarking of medical images -- Objectives and organization of the book -- Image segmentation -- Digital image processing -- Histogram -- Thresholding -- Region-based methods -- Region growing -- Region splitting and merging -- Edge-based techniques -- Active contour modeling -- Mathematical model of deformable contours -- Gradient vector flow -- The Hough transform -- The convex hull -- Fuzzy segmentation -- Fuzzy sets -- Fuzzy mapping -- Fuzzy connectivity -- Morphological image processing -- Binary morphological image processing -- Gray-scale morphological image processing -- Morphological reconstruction -- Segmentation using opening-by-reconstruction -- Remarks -- Experimental design and database -- Experimental design -- CT exams and dataset -- Methods of evaluation of the results -- Qualitative assessment -- Quantitative assessment -- Remarks -- Ribs, vertebral column, and spinal canal -- The vertebral column and the spinal canal -- Removal of peripheral artifacts and tissues -- Removal of the external air -- Removal of the skin -- Removal of the peripheral fat -- Removal of the peripheral muscle -- Identification of the rib structure -- Assessment of the results -- Segmentation of the vertebral column -- Qualitative evaluation of the results -- Quantitative evaluation of the results -- Identification of the spinal canal -- Delimitation of the search range for seed detection -- Detection of seed voxels using the Hough transform -- Extraction of the spinal canal -- Qualitative evaluation of the results -- Quantitative evaluation of the results -- Applications -- Remarks -- Delineation of the diaphragm -- The diaphragm -- Segmentation of the lungs -- Delineation of the diaphragm -- Linear least-squares procedure to model the diaphragm -- Active contour modeling of the diaphragm -- Qualitative assessment of the results -- Quantitative assessment of the results -- Applications -- Remarks -- Delineation of the pelvic girdle -- The pelvic girdle -- Delineation of the pelvic girdle -- Detection of seed voxels in the pelvic girdle -- Segmentation of the pelvic girdle -- Linear least-squares procedure to model the upper pelvic surface -- Active contour modeling of the upper pelvic surface -- Qualitative assessment of the results -- Quantitative assessment of the results -- Applications -- Remarks -- Application of landmarking -- Neuroblastoma -- Computer-aided analysis of neuroblastoma -- Segmentation of neuroblastic tumors -- Analysis of the results -- Qualitative analysis -- Quantitative analysis -- Remarks -- Concluding remarks -- Bibliography.

Abstract freely available; full-text restricted to subscribers or individual document purchasers.

Compendex

INSPEC

Google scholar

Google book search

Segmentation and landmarking of computed tomographic (CT) images of pediatric patients are important and useful in computer-aided diagnosis (CAD), treatment planning, and objective analysis of normal as well as pathological regions. Identification and segmentation of organs and tissues in the presence of tumors are difficult. Automatic segmentation of the primary tumor mass in neuroblastoma could facilitate reproducible and objective analysis of the tumor's tissue composition, shape, and size. However, due to the heterogeneous tissue composition of the neuroblastic tumor, ranging from low-attenuation necrosis to high-attenuation calcification, segmentation of the tumor mass is a challenging problem. In this context, methods are described in this book for identification and segmentation of several abdominal and thoracic landmarks to assist in the segmentation of neuroblastic tumors in pediatric CT images. Methods to identify and segment automatically the peripheral artifacts and tissues, the rib structure, the vertebral column, the spinal canal, the diaphragm, and the pelvic surface are described. Techniques are also presented to evaluate quantitatively the results of segmentation of the vertebral column, the spinal canal, the diaphragm, and the pelvic girdle by comparing with the results of independent manual segmentation performed by a radiologist. The use of the landmarks and removal of several tissues and organs are shown to assist in limiting the scope of the tumor segmentation process to the abdomen, to lead to the reduction of the false-positive error, and to improve the result of segmentation of neuroblastic tumors.

Also available in print.

Title from PDF t.p. (viewed on April 7, 2009).