MULTISPECTRAL MAGNETIC RESONANCE IMAGE ANALYSIS.

Michael W. Vannier, Robert L. Butterfield, Douglas L. Rickman, Douglas M. Jordan, William A. Murphy, Pietro R. Biondetti

Research output: Contribution to journalArticle

Abstract

Multispectral image classification techniques, originally developed for satellite imaging, have recently been applied to MR tissue characterization. Statistical assessment of multispectral tissue classification techniques has been used to select the most promising of several alternative methods. Normal and pathological images have been analyzed using multispectral analysis and image classification. These synthetic maps are then compared pixel by pixel with manually prepared classification maps of the same MR images. Using these methods, the authors have found that both supervised and unsupervised classification techniques yielded theme maps (class maps) which demonstrated tissue characteristic signatures and tissue classification errors found in computer-generated theme maps were due to subtle graph scale changes present in the original MR data sets arising from radiometric inhomogeneity and spatial nonuniformity.

Original languageEnglish
Pages (from-to)117-144
Number of pages28
JournalCritical Reviews in Biomedical Engineering
Volume15
Issue number2
Publication statusPublished - 1987

Fingerprint

Magnetic resonance
Image analysis
Tissue
Image classification
Pixels
Satellites
Imaging techniques

ASJC Scopus subject areas

  • Biomedical Engineering

Cite this

Vannier, M. W., Butterfield, R. L., Rickman, D. L., Jordan, D. M., Murphy, W. A., & Biondetti, P. R. (1987). MULTISPECTRAL MAGNETIC RESONANCE IMAGE ANALYSIS. Critical Reviews in Biomedical Engineering, 15(2), 117-144.

MULTISPECTRAL MAGNETIC RESONANCE IMAGE ANALYSIS. / Vannier, Michael W.; Butterfield, Robert L.; Rickman, Douglas L.; Jordan, Douglas M.; Murphy, William A.; Biondetti, Pietro R.

In: Critical Reviews in Biomedical Engineering, Vol. 15, No. 2, 1987, p. 117-144.

Research output: Contribution to journalArticle

Vannier, MW, Butterfield, RL, Rickman, DL, Jordan, DM, Murphy, WA & Biondetti, PR 1987, 'MULTISPECTRAL MAGNETIC RESONANCE IMAGE ANALYSIS.', Critical Reviews in Biomedical Engineering, vol. 15, no. 2, pp. 117-144.
Vannier MW, Butterfield RL, Rickman DL, Jordan DM, Murphy WA, Biondetti PR. MULTISPECTRAL MAGNETIC RESONANCE IMAGE ANALYSIS. Critical Reviews in Biomedical Engineering. 1987;15(2):117-144.
Vannier, Michael W. ; Butterfield, Robert L. ; Rickman, Douglas L. ; Jordan, Douglas M. ; Murphy, William A. ; Biondetti, Pietro R. / MULTISPECTRAL MAGNETIC RESONANCE IMAGE ANALYSIS. In: Critical Reviews in Biomedical Engineering. 1987 ; Vol. 15, No. 2. pp. 117-144.
@article{da844089c6ad40bf8316eeb5e67a8f77,
title = "MULTISPECTRAL MAGNETIC RESONANCE IMAGE ANALYSIS.",
abstract = "Multispectral image classification techniques, originally developed for satellite imaging, have recently been applied to MR tissue characterization. Statistical assessment of multispectral tissue classification techniques has been used to select the most promising of several alternative methods. Normal and pathological images have been analyzed using multispectral analysis and image classification. These synthetic maps are then compared pixel by pixel with manually prepared classification maps of the same MR images. Using these methods, the authors have found that both supervised and unsupervised classification techniques yielded theme maps (class maps) which demonstrated tissue characteristic signatures and tissue classification errors found in computer-generated theme maps were due to subtle graph scale changes present in the original MR data sets arising from radiometric inhomogeneity and spatial nonuniformity.",
author = "Vannier, {Michael W.} and Butterfield, {Robert L.} and Rickman, {Douglas L.} and Jordan, {Douglas M.} and Murphy, {William A.} and Biondetti, {Pietro R.}",
year = "1987",
language = "English",
volume = "15",
pages = "117--144",
journal = "Critical Reviews in Biomedical Engineering",
issn = "0278-940X",
publisher = "Begell House Inc.",
number = "2",

}

TY - JOUR

T1 - MULTISPECTRAL MAGNETIC RESONANCE IMAGE ANALYSIS.

AU - Vannier, Michael W.

AU - Butterfield, Robert L.

AU - Rickman, Douglas L.

AU - Jordan, Douglas M.

AU - Murphy, William A.

AU - Biondetti, Pietro R.

PY - 1987

Y1 - 1987

N2 - Multispectral image classification techniques, originally developed for satellite imaging, have recently been applied to MR tissue characterization. Statistical assessment of multispectral tissue classification techniques has been used to select the most promising of several alternative methods. Normal and pathological images have been analyzed using multispectral analysis and image classification. These synthetic maps are then compared pixel by pixel with manually prepared classification maps of the same MR images. Using these methods, the authors have found that both supervised and unsupervised classification techniques yielded theme maps (class maps) which demonstrated tissue characteristic signatures and tissue classification errors found in computer-generated theme maps were due to subtle graph scale changes present in the original MR data sets arising from radiometric inhomogeneity and spatial nonuniformity.

AB - Multispectral image classification techniques, originally developed for satellite imaging, have recently been applied to MR tissue characterization. Statistical assessment of multispectral tissue classification techniques has been used to select the most promising of several alternative methods. Normal and pathological images have been analyzed using multispectral analysis and image classification. These synthetic maps are then compared pixel by pixel with manually prepared classification maps of the same MR images. Using these methods, the authors have found that both supervised and unsupervised classification techniques yielded theme maps (class maps) which demonstrated tissue characteristic signatures and tissue classification errors found in computer-generated theme maps were due to subtle graph scale changes present in the original MR data sets arising from radiometric inhomogeneity and spatial nonuniformity.

UR - http://www.scopus.com/inward/record.url?scp=0023573004&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0023573004&partnerID=8YFLogxK

M3 - Article

C2 - 3691157

AN - SCOPUS:0023573004

VL - 15

SP - 117

EP - 144

JO - Critical Reviews in Biomedical Engineering

JF - Critical Reviews in Biomedical Engineering

SN - 0278-940X

IS - 2

ER -