Segmentation of MRI brain scans into gray matter, white matter and CSF

Tamas Sandor, Hoo Tee Ong, Vladimir I. Valtchinov, Marilyn Albert, Ferenc A. Jolesz

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

Abstract

An algorithm is described that can separate gray matter, white matter and CSF in brain scans taken with 3DFFT T1-weighted gradient echo magnetic resonance imaging. Although the algorithm is fully automated, it requires brain contours as input that utilize user-defined features. The inter- and intra-operator errors stemming from the variability of the contour definition and affecting the segmentation were assessed by using coronal brain scans of 19 subjects. The inter-operator errors were (1.61±2.38)% (P=0.01) for gray matter, (0.31±2.06)% (P=0.53) for white matter and (0.28±3.84)% (P=0.76) for cerebrospinal fluid (CSF). the intra-operator error was (0.28±0.55)% (P > 0.04) for gray matter, (0.40±0.37)% (P=0.0002) for white matter and (0.26±1.31)% (P=0.39) for CSF.

Original languageEnglish (US)
Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
Pages10-18
Number of pages9
Volume3034
DOIs
StatePublished - 1997
Externally publishedYes
EventMedical Imaging 1997: Image Processing - Newport Beach, CA, United States
Duration: Feb 25 1997Feb 25 1997

Other

OtherMedical Imaging 1997: Image Processing
CountryUnited States
CityNewport Beach, CA
Period2/25/972/25/97

Fingerprint

cerebrospinal fluid
Cerebrospinal fluid
Magnetic resonance imaging
brain
Brain
Segmentation
Fluid
Operator
operators
Magnetic resonance
Magnetic Resonance Imaging
Imaging techniques
Gradient
magnetic resonance
echoes
gradients

Keywords

  • Brain
  • CSF
  • Gray matter
  • Image processing
  • MRI
  • Segmentation
  • White matter

ASJC Scopus subject areas

  • Applied Mathematics
  • Computer Science Applications
  • Electrical and Electronic Engineering
  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics

Cite this

Sandor, T., Ong, H. T., Valtchinov, V. I., Albert, M., & Jolesz, F. A. (1997). Segmentation of MRI brain scans into gray matter, white matter and CSF. In Proceedings of SPIE - The International Society for Optical Engineering (Vol. 3034, pp. 10-18) https://doi.org/10.1117/12.274106

Segmentation of MRI brain scans into gray matter, white matter and CSF. / Sandor, Tamas; Ong, Hoo Tee; Valtchinov, Vladimir I.; Albert, Marilyn; Jolesz, Ferenc A.

Proceedings of SPIE - The International Society for Optical Engineering. Vol. 3034 1997. p. 10-18.

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

Sandor, T, Ong, HT, Valtchinov, VI, Albert, M & Jolesz, FA 1997, Segmentation of MRI brain scans into gray matter, white matter and CSF. in Proceedings of SPIE - The International Society for Optical Engineering. vol. 3034, pp. 10-18, Medical Imaging 1997: Image Processing, Newport Beach, CA, United States, 2/25/97. https://doi.org/10.1117/12.274106
Sandor T, Ong HT, Valtchinov VI, Albert M, Jolesz FA. Segmentation of MRI brain scans into gray matter, white matter and CSF. In Proceedings of SPIE - The International Society for Optical Engineering. Vol. 3034. 1997. p. 10-18 https://doi.org/10.1117/12.274106
Sandor, Tamas ; Ong, Hoo Tee ; Valtchinov, Vladimir I. ; Albert, Marilyn ; Jolesz, Ferenc A. / Segmentation of MRI brain scans into gray matter, white matter and CSF. Proceedings of SPIE - The International Society for Optical Engineering. Vol. 3034 1997. pp. 10-18
@inproceedings{0fa7e54423ee4435881e8e199a2a042f,
title = "Segmentation of MRI brain scans into gray matter, white matter and CSF",
abstract = "An algorithm is described that can separate gray matter, white matter and CSF in brain scans taken with 3DFFT T1-weighted gradient echo magnetic resonance imaging. Although the algorithm is fully automated, it requires brain contours as input that utilize user-defined features. The inter- and intra-operator errors stemming from the variability of the contour definition and affecting the segmentation were assessed by using coronal brain scans of 19 subjects. The inter-operator errors were (1.61±2.38){\%} (P=0.01) for gray matter, (0.31±2.06){\%} (P=0.53) for white matter and (0.28±3.84){\%} (P=0.76) for cerebrospinal fluid (CSF). the intra-operator error was (0.28±0.55){\%} (P > 0.04) for gray matter, (0.40±0.37){\%} (P=0.0002) for white matter and (0.26±1.31){\%} (P=0.39) for CSF.",
keywords = "Brain, CSF, Gray matter, Image processing, MRI, Segmentation, White matter",
author = "Tamas Sandor and Ong, {Hoo Tee} and Valtchinov, {Vladimir I.} and Marilyn Albert and Jolesz, {Ferenc A.}",
year = "1997",
doi = "10.1117/12.274106",
language = "English (US)",
volume = "3034",
pages = "10--18",
booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",

}

TY - GEN

T1 - Segmentation of MRI brain scans into gray matter, white matter and CSF

AU - Sandor, Tamas

AU - Ong, Hoo Tee

AU - Valtchinov, Vladimir I.

AU - Albert, Marilyn

AU - Jolesz, Ferenc A.

PY - 1997

Y1 - 1997

N2 - An algorithm is described that can separate gray matter, white matter and CSF in brain scans taken with 3DFFT T1-weighted gradient echo magnetic resonance imaging. Although the algorithm is fully automated, it requires brain contours as input that utilize user-defined features. The inter- and intra-operator errors stemming from the variability of the contour definition and affecting the segmentation were assessed by using coronal brain scans of 19 subjects. The inter-operator errors were (1.61±2.38)% (P=0.01) for gray matter, (0.31±2.06)% (P=0.53) for white matter and (0.28±3.84)% (P=0.76) for cerebrospinal fluid (CSF). the intra-operator error was (0.28±0.55)% (P > 0.04) for gray matter, (0.40±0.37)% (P=0.0002) for white matter and (0.26±1.31)% (P=0.39) for CSF.

AB - An algorithm is described that can separate gray matter, white matter and CSF in brain scans taken with 3DFFT T1-weighted gradient echo magnetic resonance imaging. Although the algorithm is fully automated, it requires brain contours as input that utilize user-defined features. The inter- and intra-operator errors stemming from the variability of the contour definition and affecting the segmentation were assessed by using coronal brain scans of 19 subjects. The inter-operator errors were (1.61±2.38)% (P=0.01) for gray matter, (0.31±2.06)% (P=0.53) for white matter and (0.28±3.84)% (P=0.76) for cerebrospinal fluid (CSF). the intra-operator error was (0.28±0.55)% (P > 0.04) for gray matter, (0.40±0.37)% (P=0.0002) for white matter and (0.26±1.31)% (P=0.39) for CSF.

KW - Brain

KW - CSF

KW - Gray matter

KW - Image processing

KW - MRI

KW - Segmentation

KW - White matter

UR - http://www.scopus.com/inward/record.url?scp=57649174446&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=57649174446&partnerID=8YFLogxK

U2 - 10.1117/12.274106

DO - 10.1117/12.274106

M3 - Conference contribution

AN - SCOPUS:57649174446

VL - 3034

SP - 10

EP - 18

BT - Proceedings of SPIE - The International Society for Optical Engineering

ER -