Computer-Aided Classification of Magnetic-Resonance Images

From Tetherless World Wiki

Jump to: navigation, search

Citation: Edward Herskovits and Michael Walker. (1989) Computer-Aided Classification of Magnetic-Resonance Images. In KSL-89-47, May,1989.

Publication techreport ( Edit )
type Technical Report
bibtype techreport
Bibtex basics
author Edward Herskovits and Michael Walker
title Computer-Aided Classification of Magnetic-Resonance Images
number KSL-89-47
institution Knowledge Systems, AI Laboratory
year 1989
month May
Bibtex more
Access Paper
abstract We describe the design, implementation, and preliminary evaluation of a computer system to aid clinicians in the interpretation of cranial magnetic-resonance images. The system classifies normal and pathologic tissues in a test set of MR scans with high accuracy. It also provides a simple, rapid means whereby an unassisted expert may reliably label an image with her best judgment of its histologic composition, yielding a gold-standard image; this step facilitates objective evaluation of classifier performance. The system's components are a preprocessing module for normalizing images, an unsupervised clustering algorithm (ISODATA), a maximum-likelihood classifier, and an evaluation module based on confusion-matrix generation. The algorithms for classifier evaluation and gold-standard acquisition are advances over previous methods. The system is best thought of as a data-reduction tool, rather than as an expert system; it highlights salient features of the image for the clinician without requiring user intervention.

KSL Technical Report ID: KSL-89-47
Facts about Computer-Aided Classification of Magnetic-Resonance ImagesRDF feed
Abstract We describe the design, implementation, an … We describe the design, implementation, and preliminary evaluation of a computer system to aid clinicians in the interpretation of cranial magnetic-resonance images. The system classifies normal and pathologic tissues in a test set of MR scans with high accuracy. It also provides a simple, rapid means whereby an unassisted expert may reliably label an image with her best judgment of its histologic composition, yielding a gold-standard image; this step facilitates objective evaluation of classifier performance. The system's components are a preprocessing module for normalizing images, an unsupervised clustering algorithm (ISODATA), a maximum-likelihood classifier, and an evaluation module based on confusion-matrix generation. The algorithms for classifier evaluation and gold-standard acquisition are advances over previous methods. The system is best thought of as a data-reduction tool, rather than as an expert system; it highlights salient features of the image for the clinician without requiring user intervention. ician without requiring user intervention.
Author Edward Herskovits and Michael Walker  +
Bibtype techreport  +
Has author Edward Herskovits and Michael Walker  +
Has identifier KSL-89-47  +
Has publishing details May,1989  +
Has title Computer-Aided Classification of Magnetic-Resonance Images  +
Has where published KSL-89-47  +
Has year 1989  +
Institution Knowledge Systems, AI Laboratory  +
Ksl tr id KSL-89-47  +
Month May  +
Number KSL-89-47  +
Process note NO  +
Title Computer-Aided Classification of Magnetic-Resonance Images  +
Year 1989  +
Retrieved from "http://tw.rpi.edu/wiki/Computer-Aided_Classification_of_Magnetic-Resonance_Images"
Personal tools