Tissue-type discrimination in magnetic resonance images

David Y. Amamoto, Rangachar Kasturi, Alexander Mamourian

Research output: Chapter in Book/Report/Conference proceedingConference contribution

9 Citations (Scopus)

Abstract

A method developed for classifying each location in a set of magnetic resonance (MR) images by tissue type is described. Three MR images of a region of interest are acquired using spin-echo pulse sequences. The sequences used to acquire these images are specifically defined to allow the calculation of MR-related physical parameters from the image intensity data. After preprocessing operators are applied to the original images, the image intensity data are used to calculate three MR-related parameters of each location. Then, in a supervised training environment, this calculated data set is used with the acquired image data set in a minimum-distance classifier to assign a class-specific color or gray level to each location in the image. Following the classification and formation of the tissue-map image, a set of edge detection routines is applied to generate tissue boundary images for all or a selected set of tissue types. Experimental results verify that the method is capable of accurately distinguishing between major tissue types in a region of interest.

Original languageEnglish (US)
Title of host publicationProceedings - International Conference on Pattern Recognition
PublisherPubl by IEEE
Pages603-607
Number of pages5
ISBN (Print)0818620625
StatePublished - Dec 1 1990
EventProceedings of the 10th International Conference on Pattern Recognition - Atlantic City, NJ, USA
Duration: Jun 16 1990Jun 21 1990

Publication series

NameProceedings - International Conference on Pattern Recognition
Volume1

Conference

ConferenceProceedings of the 10th International Conference on Pattern Recognition
CityAtlantic City, NJ, USA
Period6/16/906/21/90

Fingerprint

Magnetic resonance
Tissue
Edge detection
Classifiers
Color

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition

Cite this

Amamoto, D. Y., Kasturi, R., & Mamourian, A. (1990). Tissue-type discrimination in magnetic resonance images. In Proceedings - International Conference on Pattern Recognition (pp. 603-607). (Proceedings - International Conference on Pattern Recognition; Vol. 1). Publ by IEEE.
Amamoto, David Y. ; Kasturi, Rangachar ; Mamourian, Alexander. / Tissue-type discrimination in magnetic resonance images. Proceedings - International Conference on Pattern Recognition. Publ by IEEE, 1990. pp. 603-607 (Proceedings - International Conference on Pattern Recognition).
@inproceedings{e00b50b799e64b779ce7efb47dcafdcc,
title = "Tissue-type discrimination in magnetic resonance images",
abstract = "A method developed for classifying each location in a set of magnetic resonance (MR) images by tissue type is described. Three MR images of a region of interest are acquired using spin-echo pulse sequences. The sequences used to acquire these images are specifically defined to allow the calculation of MR-related physical parameters from the image intensity data. After preprocessing operators are applied to the original images, the image intensity data are used to calculate three MR-related parameters of each location. Then, in a supervised training environment, this calculated data set is used with the acquired image data set in a minimum-distance classifier to assign a class-specific color or gray level to each location in the image. Following the classification and formation of the tissue-map image, a set of edge detection routines is applied to generate tissue boundary images for all or a selected set of tissue types. Experimental results verify that the method is capable of accurately distinguishing between major tissue types in a region of interest.",
author = "Amamoto, {David Y.} and Rangachar Kasturi and Alexander Mamourian",
year = "1990",
month = "12",
day = "1",
language = "English (US)",
isbn = "0818620625",
series = "Proceedings - International Conference on Pattern Recognition",
publisher = "Publ by IEEE",
pages = "603--607",
booktitle = "Proceedings - International Conference on Pattern Recognition",

}

Amamoto, DY, Kasturi, R & Mamourian, A 1990, Tissue-type discrimination in magnetic resonance images. in Proceedings - International Conference on Pattern Recognition. Proceedings - International Conference on Pattern Recognition, vol. 1, Publ by IEEE, pp. 603-607, Proceedings of the 10th International Conference on Pattern Recognition, Atlantic City, NJ, USA, 6/16/90.

Tissue-type discrimination in magnetic resonance images. / Amamoto, David Y.; Kasturi, Rangachar; Mamourian, Alexander.

Proceedings - International Conference on Pattern Recognition. Publ by IEEE, 1990. p. 603-607 (Proceedings - International Conference on Pattern Recognition; Vol. 1).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Tissue-type discrimination in magnetic resonance images

AU - Amamoto, David Y.

AU - Kasturi, Rangachar

AU - Mamourian, Alexander

PY - 1990/12/1

Y1 - 1990/12/1

N2 - A method developed for classifying each location in a set of magnetic resonance (MR) images by tissue type is described. Three MR images of a region of interest are acquired using spin-echo pulse sequences. The sequences used to acquire these images are specifically defined to allow the calculation of MR-related physical parameters from the image intensity data. After preprocessing operators are applied to the original images, the image intensity data are used to calculate three MR-related parameters of each location. Then, in a supervised training environment, this calculated data set is used with the acquired image data set in a minimum-distance classifier to assign a class-specific color or gray level to each location in the image. Following the classification and formation of the tissue-map image, a set of edge detection routines is applied to generate tissue boundary images for all or a selected set of tissue types. Experimental results verify that the method is capable of accurately distinguishing between major tissue types in a region of interest.

AB - A method developed for classifying each location in a set of magnetic resonance (MR) images by tissue type is described. Three MR images of a region of interest are acquired using spin-echo pulse sequences. The sequences used to acquire these images are specifically defined to allow the calculation of MR-related physical parameters from the image intensity data. After preprocessing operators are applied to the original images, the image intensity data are used to calculate three MR-related parameters of each location. Then, in a supervised training environment, this calculated data set is used with the acquired image data set in a minimum-distance classifier to assign a class-specific color or gray level to each location in the image. Following the classification and formation of the tissue-map image, a set of edge detection routines is applied to generate tissue boundary images for all or a selected set of tissue types. Experimental results verify that the method is capable of accurately distinguishing between major tissue types in a region of interest.

UR - http://www.scopus.com/inward/record.url?scp=0025556979&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0025556979&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0025556979

SN - 0818620625

T3 - Proceedings - International Conference on Pattern Recognition

SP - 603

EP - 607

BT - Proceedings - International Conference on Pattern Recognition

PB - Publ by IEEE

ER -

Amamoto DY, Kasturi R, Mamourian A. Tissue-type discrimination in magnetic resonance images. In Proceedings - International Conference on Pattern Recognition. Publ by IEEE. 1990. p. 603-607. (Proceedings - International Conference on Pattern Recognition).