Published 1989 | Version v1
Book

Use of morphologic information for the automated segmentation of MR images of the spine

Description

Because the occurrence of a wide variety of tissue contrast relationships limits MR automated segmentation based on textural information, the authors have examined the use of morphologic information in automated MR segmentation. Algorithms were developed to automatically identify the spine on the basis of morphologic recognition of vertebrae and the spinal canal. In a prospective evaluation, the spine was automatically identified in 26 of 26 routine clinical studies. Comparable results were obtained in studies performed with a variety of different imaging pulse sequences. The authors conclude that morphologic information could facilitate automated MR segmentation

Additional details

Publishing Information

Publisher
Radiological Society of North America Inc.
Imprint Place
Oak Brook, IL (USA)
Imprint Title
Proceedings of the 75th anniversary scientific assembly and annual meeting of the Radiological Society of North America (Abstracts)
Imprint Pagination
654 p.
Journal Page Range
p. 336.

Conference

Title
75. anniversary scientific assembly and annual meeting of the Radiological Society of North America.
Dates
26 Nov - 1 Dec 1989.
Place
Chicago, IL (USA).

INIS

Country of Publication
United States
Country of Input or Organization
United States
INIS RN
21079340
Subject category
S62: RADIOLOGY AND NUCLEAR MEDICINE;
Resource subtype / Literary indicator
Conference
Descriptors DEI
AUTOMATION; DIAGNOSIS; MORPHOLOGICAL CHANGES; NMR IMAGING; SEQUENTIAL SCANNING; VERTEBRAE
Descriptors DEC
BODY; COUNTING TECHNIQUES; DIAGNOSTIC TECHNIQUES; ORGANS; SKELETON

Optional Information

Secondary number(s)
CONF-8911163--.