Automatic recognition of midline shift on brain CT images

Chun Chih Liao, Furen Xiao, Jau Min Wong, I-Jen Chiang

Research output: Contribution to journalArticle

20 Citations (Scopus)

Abstract

Midline shift is one of the most important quantitative features clinicians use to evaluate the severity of brain compression by various pathologies. It can be recognized by modeling brain deformation according to the estimated biomechanical properties of the brain and the cerebrospinal fluid spaces. This paper proposes a novel method to identify the deformed midline according to the above hypothesis. In this model, the deformed midline is decomposed into three segments: the upper and the lower straight segments representing parts of the tough dura mater separating two brain hemispheres, and the central curved segment formed by a quadratic Bezier curve, representing the intervening soft brain tissue. The deformed midline is obtained by minimizing the summed square of the differences across all midline pixels, to simulate maximal bilateral symmetry. A genetic algorithm is applied to derive the optimal values of the control points of the Bezier curve. Our algorithm was evaluated on pathological images from 81 consecutive patients treated in a single institute over a period of one year. Our algorithm is able to recognize the deformed midlines in 65 (80%) of the patients with an accuracy of 95%, making it a useful tool for clinical decision-making.

Original languageEnglish
Pages (from-to)331-339
Number of pages9
JournalComputers in Biology and Medicine
Volume40
Issue number3
DOIs
Publication statusPublished - Mar 2010

Fingerprint

Brain
Cerebrospinal fluid
Dura Mater
Pathology
Cerebrospinal Fluid
Genetic algorithms
Decision making
Pixels
Tissue

Keywords

  • Brain deformation
  • Computed tomography
  • Genetic algorithm
  • Medical informatics
  • Midline shift
  • Pathological images
  • Symmetry detection

ASJC Scopus subject areas

  • Computer Science Applications
  • Health Informatics

Cite this

Automatic recognition of midline shift on brain CT images. / Liao, Chun Chih; Xiao, Furen; Wong, Jau Min; Chiang, I-Jen.

In: Computers in Biology and Medicine, Vol. 40, No. 3, 03.2010, p. 331-339.

Research output: Contribution to journalArticle

Liao, Chun Chih ; Xiao, Furen ; Wong, Jau Min ; Chiang, I-Jen. / Automatic recognition of midline shift on brain CT images. In: Computers in Biology and Medicine. 2010 ; Vol. 40, No. 3. pp. 331-339.
@article{de54a334f65d4a9faecc9705b10dc82f,
title = "Automatic recognition of midline shift on brain CT images",
abstract = "Midline shift is one of the most important quantitative features clinicians use to evaluate the severity of brain compression by various pathologies. It can be recognized by modeling brain deformation according to the estimated biomechanical properties of the brain and the cerebrospinal fluid spaces. This paper proposes a novel method to identify the deformed midline according to the above hypothesis. In this model, the deformed midline is decomposed into three segments: the upper and the lower straight segments representing parts of the tough dura mater separating two brain hemispheres, and the central curved segment formed by a quadratic Bezier curve, representing the intervening soft brain tissue. The deformed midline is obtained by minimizing the summed square of the differences across all midline pixels, to simulate maximal bilateral symmetry. A genetic algorithm is applied to derive the optimal values of the control points of the Bezier curve. Our algorithm was evaluated on pathological images from 81 consecutive patients treated in a single institute over a period of one year. Our algorithm is able to recognize the deformed midlines in 65 (80{\%}) of the patients with an accuracy of 95{\%}, making it a useful tool for clinical decision-making.",
keywords = "Brain deformation, Computed tomography, Genetic algorithm, Medical informatics, Midline shift, Pathological images, Symmetry detection",
author = "Liao, {Chun Chih} and Furen Xiao and Wong, {Jau Min} and I-Jen Chiang",
year = "2010",
month = "3",
doi = "10.1016/j.compbiomed.2010.01.004",
language = "English",
volume = "40",
pages = "331--339",
journal = "Computers in Biology and Medicine",
issn = "0010-4825",
publisher = "Elsevier Limited",
number = "3",

}

TY - JOUR

T1 - Automatic recognition of midline shift on brain CT images

AU - Liao, Chun Chih

AU - Xiao, Furen

AU - Wong, Jau Min

AU - Chiang, I-Jen

PY - 2010/3

Y1 - 2010/3

N2 - Midline shift is one of the most important quantitative features clinicians use to evaluate the severity of brain compression by various pathologies. It can be recognized by modeling brain deformation according to the estimated biomechanical properties of the brain and the cerebrospinal fluid spaces. This paper proposes a novel method to identify the deformed midline according to the above hypothesis. In this model, the deformed midline is decomposed into three segments: the upper and the lower straight segments representing parts of the tough dura mater separating two brain hemispheres, and the central curved segment formed by a quadratic Bezier curve, representing the intervening soft brain tissue. The deformed midline is obtained by minimizing the summed square of the differences across all midline pixels, to simulate maximal bilateral symmetry. A genetic algorithm is applied to derive the optimal values of the control points of the Bezier curve. Our algorithm was evaluated on pathological images from 81 consecutive patients treated in a single institute over a period of one year. Our algorithm is able to recognize the deformed midlines in 65 (80%) of the patients with an accuracy of 95%, making it a useful tool for clinical decision-making.

AB - Midline shift is one of the most important quantitative features clinicians use to evaluate the severity of brain compression by various pathologies. It can be recognized by modeling brain deformation according to the estimated biomechanical properties of the brain and the cerebrospinal fluid spaces. This paper proposes a novel method to identify the deformed midline according to the above hypothesis. In this model, the deformed midline is decomposed into three segments: the upper and the lower straight segments representing parts of the tough dura mater separating two brain hemispheres, and the central curved segment formed by a quadratic Bezier curve, representing the intervening soft brain tissue. The deformed midline is obtained by minimizing the summed square of the differences across all midline pixels, to simulate maximal bilateral symmetry. A genetic algorithm is applied to derive the optimal values of the control points of the Bezier curve. Our algorithm was evaluated on pathological images from 81 consecutive patients treated in a single institute over a period of one year. Our algorithm is able to recognize the deformed midlines in 65 (80%) of the patients with an accuracy of 95%, making it a useful tool for clinical decision-making.

KW - Brain deformation

KW - Computed tomography

KW - Genetic algorithm

KW - Medical informatics

KW - Midline shift

KW - Pathological images

KW - Symmetry detection

UR - http://www.scopus.com/inward/record.url?scp=77549088382&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77549088382&partnerID=8YFLogxK

U2 - 10.1016/j.compbiomed.2010.01.004

DO - 10.1016/j.compbiomed.2010.01.004

M3 - Article

C2 - 20132930

AN - SCOPUS:77549088382

VL - 40

SP - 331

EP - 339

JO - Computers in Biology and Medicine

JF - Computers in Biology and Medicine

SN - 0010-4825

IS - 3

ER -