Automatic measurement of midline shift on deformed brains using multiresolution binary level set method and Hough transform

Furen Xiao, I. Jen Chiang, Jau Min Wong, Yi Hsin Tsai, Ke Chun Huang, Chun Chih Liao

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

Midline shift (MLS) is an important quantitative feature clinicians use to evaluate the severity of brain compression by various pathologies. The midline consists of many anatomical structures including the septum pellucidum (SP), a thin membrane between the frontal horns (FH) of the lateral ventricles. We proposed a procedure that can measure MLS by recognizing the SP within the given CT study. The FH region is selected from all ventricular regions by expert rules and the multiresolution binary level set method. The SP is recognized using Hough transform, weighted by repeated morphological erosion. Our system is tested on images from 80 patients admitted to the neurosurgical intensive care unit. The results are evaluated by human experts. The mean difference between automatic and manual MLS measurements is 0.23±0.52 mm. Our method is robust and can be applied in emergency and routine settings.

Original languageEnglish
Pages (from-to)756-762
Number of pages7
JournalComputers in Biology and Medicine
Volume41
Issue number9
DOIs
Publication statusPublished - Sep 2011

Fingerprint

Septum Pellucidum
Intensive care units
Hough transforms
Pathology
Erosion
Brain
Horns
Membranes
Lateral Ventricles
Intensive Care Units
Emergencies

Keywords

  • Brain deformation
  • Computed tomography
  • Hough transform
  • Level set
  • Medical informatics
  • Midline shift
  • Pathological images

ASJC Scopus subject areas

  • Computer Science Applications
  • Health Informatics

Cite this

Automatic measurement of midline shift on deformed brains using multiresolution binary level set method and Hough transform. / Xiao, Furen; Chiang, I. Jen; Wong, Jau Min; Tsai, Yi Hsin; Huang, Ke Chun; Liao, Chun Chih.

In: Computers in Biology and Medicine, Vol. 41, No. 9, 09.2011, p. 756-762.

Research output: Contribution to journalArticle

Xiao, Furen ; Chiang, I. Jen ; Wong, Jau Min ; Tsai, Yi Hsin ; Huang, Ke Chun ; Liao, Chun Chih. / Automatic measurement of midline shift on deformed brains using multiresolution binary level set method and Hough transform. In: Computers in Biology and Medicine. 2011 ; Vol. 41, No. 9. pp. 756-762.
@article{dec39c23ebb047a58dd83402dc6cec84,
title = "Automatic measurement of midline shift on deformed brains using multiresolution binary level set method and Hough transform",
abstract = "Midline shift (MLS) is an important quantitative feature clinicians use to evaluate the severity of brain compression by various pathologies. The midline consists of many anatomical structures including the septum pellucidum (SP), a thin membrane between the frontal horns (FH) of the lateral ventricles. We proposed a procedure that can measure MLS by recognizing the SP within the given CT study. The FH region is selected from all ventricular regions by expert rules and the multiresolution binary level set method. The SP is recognized using Hough transform, weighted by repeated morphological erosion. Our system is tested on images from 80 patients admitted to the neurosurgical intensive care unit. The results are evaluated by human experts. The mean difference between automatic and manual MLS measurements is 0.23±0.52 mm. Our method is robust and can be applied in emergency and routine settings.",
keywords = "Brain deformation, Computed tomography, Hough transform, Level set, Medical informatics, Midline shift, Pathological images",
author = "Furen Xiao and Chiang, {I. Jen} and Wong, {Jau Min} and Tsai, {Yi Hsin} and Huang, {Ke Chun} and Liao, {Chun Chih}",
year = "2011",
month = "9",
doi = "10.1016/j.compbiomed.2011.06.011",
language = "English",
volume = "41",
pages = "756--762",
journal = "Computers in Biology and Medicine",
issn = "0010-4825",
publisher = "Elsevier Limited",
number = "9",

}

TY - JOUR

T1 - Automatic measurement of midline shift on deformed brains using multiresolution binary level set method and Hough transform

AU - Xiao, Furen

AU - Chiang, I. Jen

AU - Wong, Jau Min

AU - Tsai, Yi Hsin

AU - Huang, Ke Chun

AU - Liao, Chun Chih

PY - 2011/9

Y1 - 2011/9

N2 - Midline shift (MLS) is an important quantitative feature clinicians use to evaluate the severity of brain compression by various pathologies. The midline consists of many anatomical structures including the septum pellucidum (SP), a thin membrane between the frontal horns (FH) of the lateral ventricles. We proposed a procedure that can measure MLS by recognizing the SP within the given CT study. The FH region is selected from all ventricular regions by expert rules and the multiresolution binary level set method. The SP is recognized using Hough transform, weighted by repeated morphological erosion. Our system is tested on images from 80 patients admitted to the neurosurgical intensive care unit. The results are evaluated by human experts. The mean difference between automatic and manual MLS measurements is 0.23±0.52 mm. Our method is robust and can be applied in emergency and routine settings.

AB - Midline shift (MLS) is an important quantitative feature clinicians use to evaluate the severity of brain compression by various pathologies. The midline consists of many anatomical structures including the septum pellucidum (SP), a thin membrane between the frontal horns (FH) of the lateral ventricles. We proposed a procedure that can measure MLS by recognizing the SP within the given CT study. The FH region is selected from all ventricular regions by expert rules and the multiresolution binary level set method. The SP is recognized using Hough transform, weighted by repeated morphological erosion. Our system is tested on images from 80 patients admitted to the neurosurgical intensive care unit. The results are evaluated by human experts. The mean difference between automatic and manual MLS measurements is 0.23±0.52 mm. Our method is robust and can be applied in emergency and routine settings.

KW - Brain deformation

KW - Computed tomography

KW - Hough transform

KW - Level set

KW - Medical informatics

KW - Midline shift

KW - Pathological images

UR - http://www.scopus.com/inward/record.url?scp=80051664378&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80051664378&partnerID=8YFLogxK

U2 - 10.1016/j.compbiomed.2011.06.011

DO - 10.1016/j.compbiomed.2011.06.011

M3 - Article

VL - 41

SP - 756

EP - 762

JO - Computers in Biology and Medicine

JF - Computers in Biology and Medicine

SN - 0010-4825

IS - 9

ER -