Edge-based segmentation of 3-D magnetic resonance images

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

The 3-D visualization of MR images of the brain requires that the data set first be segmented into brain and non-brain regions. Most existing segmentation techniques either require multiple-modality data (making high-resolution imaging impractical) or require extensive user interaction (for correction of contours). We present an automated technique for the segmentation of single-modality, 3-D magnetic resonance (MR) images. Computer graphics techniques ace employed to generate 3-D views of the brain's surface from the segmented images. The segmentation algorithm is based on the 3-D difference of Gaussians (DOG) filter. A novel method was developed for the classification of regions found by the DOG filter, as well as an automated correction procedure that detects errors from the DOG filter. Spatial information is also incorporated to help discriminate between tissues. Encouraging results were obtained with an average of less than five percent error in each image.

Original languageEnglish (US)
Article number413440
Pages (from-to)876-880
Number of pages5
JournalProceedings - International Conference on Image Processing, ICIP
Volume1
DOIs
StatePublished - 1994

Fingerprint

Magnetic resonance
Brain
Computer graphics
Visualization
Tissue
Imaging techniques

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Edge-based segmentation of 3-D magnetic resonance images. / Lee, J. L.; Rodriguez, Jeffrey J.

In: Proceedings - International Conference on Image Processing, ICIP, Vol. 1, 413440, 1994, p. 876-880.

Research output: Contribution to journalArticle

@article{bebe420b10024509ad1d856d10ffb0ab,
title = "Edge-based segmentation of 3-D magnetic resonance images",
abstract = "The 3-D visualization of MR images of the brain requires that the data set first be segmented into brain and non-brain regions. Most existing segmentation techniques either require multiple-modality data (making high-resolution imaging impractical) or require extensive user interaction (for correction of contours). We present an automated technique for the segmentation of single-modality, 3-D magnetic resonance (MR) images. Computer graphics techniques ace employed to generate 3-D views of the brain's surface from the segmented images. The segmentation algorithm is based on the 3-D difference of Gaussians (DOG) filter. A novel method was developed for the classification of regions found by the DOG filter, as well as an automated correction procedure that detects errors from the DOG filter. Spatial information is also incorporated to help discriminate between tissues. Encouraging results were obtained with an average of less than five percent error in each image.",
author = "Lee, {J. L.} and Rodriguez, {Jeffrey J}",
year = "1994",
doi = "10.1109/ICIP.1994.413440",
language = "English (US)",
volume = "1",
pages = "876--880",
journal = "Proceedings - International Conference on Image Processing, ICIP",
issn = "1522-4880",

}

TY - JOUR

T1 - Edge-based segmentation of 3-D magnetic resonance images

AU - Lee, J. L.

AU - Rodriguez, Jeffrey J

PY - 1994

Y1 - 1994

N2 - The 3-D visualization of MR images of the brain requires that the data set first be segmented into brain and non-brain regions. Most existing segmentation techniques either require multiple-modality data (making high-resolution imaging impractical) or require extensive user interaction (for correction of contours). We present an automated technique for the segmentation of single-modality, 3-D magnetic resonance (MR) images. Computer graphics techniques ace employed to generate 3-D views of the brain's surface from the segmented images. The segmentation algorithm is based on the 3-D difference of Gaussians (DOG) filter. A novel method was developed for the classification of regions found by the DOG filter, as well as an automated correction procedure that detects errors from the DOG filter. Spatial information is also incorporated to help discriminate between tissues. Encouraging results were obtained with an average of less than five percent error in each image.

AB - The 3-D visualization of MR images of the brain requires that the data set first be segmented into brain and non-brain regions. Most existing segmentation techniques either require multiple-modality data (making high-resolution imaging impractical) or require extensive user interaction (for correction of contours). We present an automated technique for the segmentation of single-modality, 3-D magnetic resonance (MR) images. Computer graphics techniques ace employed to generate 3-D views of the brain's surface from the segmented images. The segmentation algorithm is based on the 3-D difference of Gaussians (DOG) filter. A novel method was developed for the classification of regions found by the DOG filter, as well as an automated correction procedure that detects errors from the DOG filter. Spatial information is also incorporated to help discriminate between tissues. Encouraging results were obtained with an average of less than five percent error in each image.

UR - http://www.scopus.com/inward/record.url?scp=84996844855&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84996844855&partnerID=8YFLogxK

U2 - 10.1109/ICIP.1994.413440

DO - 10.1109/ICIP.1994.413440

M3 - Article

AN - SCOPUS:84996844855

VL - 1

SP - 876

EP - 880

JO - Proceedings - International Conference on Image Processing, ICIP

JF - Proceedings - International Conference on Image Processing, ICIP

SN - 1522-4880

M1 - 413440

ER -