Neural network approach to segmentation of magnetic resonance head images

Koichi Oshio, Manbir Singh

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

A novel image segmentation scheme based on a neural network has been implemented to segment magnetic resonance head images. A three-layer perceptron-type neural network, trained with backward error propagation algorithm was used. The scheme utilizes first-echo intensity and computed T2 values to construct a two-parameter space for classification. After training on a selected slice, the method successfully segments all slices for a given subject without any further human interaction.

Original languageEnglish
Pages (from-to)130-134
Number of pages5
JournalInternational Journal of Imaging Systems and Technology
Volume4
Issue number2
Publication statusPublished - 1992 Jun
Externally publishedYes

Fingerprint

Magnetic resonance
magnetic resonance
Neural networks
self organizing systems
echoes
education
Image segmentation
propagation
interactions

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering
  • Atomic and Molecular Physics, and Optics

Cite this

Neural network approach to segmentation of magnetic resonance head images. / Oshio, Koichi; Singh, Manbir.

In: International Journal of Imaging Systems and Technology, Vol. 4, No. 2, 06.1992, p. 130-134.

Research output: Contribution to journalArticle

@article{23f4d05163d343f1aeea045850192c61,
title = "Neural network approach to segmentation of magnetic resonance head images",
abstract = "A novel image segmentation scheme based on a neural network has been implemented to segment magnetic resonance head images. A three-layer perceptron-type neural network, trained with backward error propagation algorithm was used. The scheme utilizes first-echo intensity and computed T2 values to construct a two-parameter space for classification. After training on a selected slice, the method successfully segments all slices for a given subject without any further human interaction.",
author = "Koichi Oshio and Manbir Singh",
year = "1992",
month = "6",
language = "English",
volume = "4",
pages = "130--134",
journal = "International Journal of Imaging Systems and Technology",
issn = "0899-9457",
publisher = "John Wiley and Sons Inc.",
number = "2",

}

TY - JOUR

T1 - Neural network approach to segmentation of magnetic resonance head images

AU - Oshio, Koichi

AU - Singh, Manbir

PY - 1992/6

Y1 - 1992/6

N2 - A novel image segmentation scheme based on a neural network has been implemented to segment magnetic resonance head images. A three-layer perceptron-type neural network, trained with backward error propagation algorithm was used. The scheme utilizes first-echo intensity and computed T2 values to construct a two-parameter space for classification. After training on a selected slice, the method successfully segments all slices for a given subject without any further human interaction.

AB - A novel image segmentation scheme based on a neural network has been implemented to segment magnetic resonance head images. A three-layer perceptron-type neural network, trained with backward error propagation algorithm was used. The scheme utilizes first-echo intensity and computed T2 values to construct a two-parameter space for classification. After training on a selected slice, the method successfully segments all slices for a given subject without any further human interaction.

UR - http://www.scopus.com/inward/record.url?scp=0026871543&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0026871543&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0026871543

VL - 4

SP - 130

EP - 134

JO - International Journal of Imaging Systems and Technology

JF - International Journal of Imaging Systems and Technology

SN - 0899-9457

IS - 2

ER -