Semi-automated extraction of brain contours from MRI

H. T. Ong; J. Tieman; M. Albert; F. Jolesz; T. Sandor

doi:10.1007/s002340050508

Semi-automated extraction of brain contours from MRI

H. T. Ong, J. Tieman, M. Albert, F. Jolesz, T. Sandor

Research output: Contribution to journal › Article › peer-review

2 Scopus citations

Abstract

We compared brain volumes computed by trained operators using the BRAIN-MAP algorithm, which automatically extracts the contours of the brain from gradient-echo magnetic resonance images. The images of 19 subjects randomly selected from a group of normals and a group of patients with dementia were included. BRAIN-MAP found brain perimeters that were on the average ca. 3% tighter than those obtained by two experienced operators. Between-operator and within-operator reproducibility of the analyses were also estimated and found to be (-0.13 ± 0.51)% and (-0.63 ± 0.08)%, respectively. Replicate volume measurement by the computer alone provided a reproducibility of (0.44 ± 0.46)%.

Original language	English (US)
Pages (from-to)	797-803
Number of pages	7
Journal	Neuroradiology
Volume	39
Issue number	11
DOIs	https://doi.org/10.1007/s002340050508
State	Published - 1997
Externally published	Yes

Keywords

Brain volume measurement
Contour extraction
Image processing
Magnetic resonance imaging

ASJC Scopus subject areas

Radiology Nuclear Medicine and imaging
Clinical Neurology
Cardiology and Cardiovascular Medicine

Access to Document

10.1007/s002340050508

Cite this

@article{b3df51c6e4c44e6b9b2d0bc21feea100,

title = "Semi-automated extraction of brain contours from MRI",

abstract = "We compared brain volumes computed by trained operators using the BRAIN-MAP algorithm, which automatically extracts the contours of the brain from gradient-echo magnetic resonance images. The images of 19 subjects randomly selected from a group of normals and a group of patients with dementia were included. BRAIN-MAP found brain perimeters that were on the average ca. 3% tighter than those obtained by two experienced operators. Between-operator and within-operator reproducibility of the analyses were also estimated and found to be (-0.13 ± 0.51)% and (-0.63 ± 0.08)%, respectively. Replicate volume measurement by the computer alone provided a reproducibility of (0.44 ± 0.46)%.",

keywords = "Brain volume measurement, Contour extraction, Image processing, Magnetic resonance imaging",

author = "Ong, {H. T.} and J. Tieman and M. Albert and F. Jolesz and T. Sandor",

note = "Funding Information: Acknowledgements It is a pleasure to acknowledge valuable discussions with Drs. Mark Moss and Ronald Killiany and the help provided by Steven Beck, Lynne McConchie and Henry Kwan in the analysis of the data. This study was supported in part by NIA grant P01-AG04953 and the Unicare foundation. Copyright: Copyright 2007 Elsevier B.V., All rights reserved.",

year = "1997",

doi = "10.1007/s002340050508",

language = "English (US)",

volume = "39",

pages = "797--803",

journal = "Neuroradiology",

issn = "0028-3940",

publisher = "Springer Verlag",

number = "11",

}

TY - JOUR

T1 - Semi-automated extraction of brain contours from MRI

AU - Ong, H. T.

AU - Tieman, J.

AU - Albert, M.

AU - Jolesz, F.

AU - Sandor, T.

N1 - Funding Information: Acknowledgements It is a pleasure to acknowledge valuable discussions with Drs. Mark Moss and Ronald Killiany and the help provided by Steven Beck, Lynne McConchie and Henry Kwan in the analysis of the data. This study was supported in part by NIA grant P01-AG04953 and the Unicare foundation. Copyright: Copyright 2007 Elsevier B.V., All rights reserved.

PY - 1997

Y1 - 1997

N2 - We compared brain volumes computed by trained operators using the BRAIN-MAP algorithm, which automatically extracts the contours of the brain from gradient-echo magnetic resonance images. The images of 19 subjects randomly selected from a group of normals and a group of patients with dementia were included. BRAIN-MAP found brain perimeters that were on the average ca. 3% tighter than those obtained by two experienced operators. Between-operator and within-operator reproducibility of the analyses were also estimated and found to be (-0.13 ± 0.51)% and (-0.63 ± 0.08)%, respectively. Replicate volume measurement by the computer alone provided a reproducibility of (0.44 ± 0.46)%.

AB - We compared brain volumes computed by trained operators using the BRAIN-MAP algorithm, which automatically extracts the contours of the brain from gradient-echo magnetic resonance images. The images of 19 subjects randomly selected from a group of normals and a group of patients with dementia were included. BRAIN-MAP found brain perimeters that were on the average ca. 3% tighter than those obtained by two experienced operators. Between-operator and within-operator reproducibility of the analyses were also estimated and found to be (-0.13 ± 0.51)% and (-0.63 ± 0.08)%, respectively. Replicate volume measurement by the computer alone provided a reproducibility of (0.44 ± 0.46)%.

KW - Brain volume measurement

KW - Contour extraction

KW - Image processing

KW - Magnetic resonance imaging

UR - http://www.scopus.com/inward/record.url?scp=0030690505&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030690505&partnerID=8YFLogxK

U2 - 10.1007/s002340050508

DO - 10.1007/s002340050508

M3 - Article

C2 - 9406206

AN - SCOPUS:0030690505

SN - 0028-3940

VL - 39

SP - 797

EP - 803

JO - Neuroradiology

JF - Neuroradiology

IS - 11

ER -

Semi-automated extraction of brain contours from MRI

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this