A simple genetic algorithm for tracing the deformed midline on a single slice of brain CT using quadratic Bézier curves

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

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

11 Citations (Scopus)

Abstract

Midline shift (MLS) is one of the most important quantitative features clinicians use to evaluate the severity of brain compression. It can be recognized by modeling brain deformation according to the estimated biomechanical properties of the brain structures. This paper proposes a novel method to identify the deformed midline by decomposing it into three segments: the upper and the lower straight segments representing parts of the tough meninges separating two brain hemispheres, and the central curved segment formed by a quadratic Bézier curve, representing the intervening soft brain tissue. The deformed midline is obtained by minimizing the summed square of the differences across all midline points, applying a genetic algorithm. Our algorithm was evaluated on images containing various pathologies from 81 consecutive patients treated in a single institute over one-year period. The deformed midlines were evaluated by human experts, and the values of midline shift were accurate in 95%.

Original languageEnglish
Title of host publicationProceedings - IEEE International Conference on Data Mining, ICDM
Pages463-467
Number of pages5
Publication statusPublished - 2006
Event6th IEEE International Conference on Data Mining - Workshops, ICDM 2006 - Hong Kong, China
Duration: Dec 18 2006Dec 18 2006

Other

Other6th IEEE International Conference on Data Mining - Workshops, ICDM 2006
CountryChina
CityHong Kong
Period12/18/0612/18/06

Fingerprint

Brain
Genetic algorithms
Pathology
Tissue

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Liao, C. C., Xiao, F., Wong, J. M., & Chiang, I-J. (2006). A simple genetic algorithm for tracing the deformed midline on a single slice of brain CT using quadratic Bézier curves. In Proceedings - IEEE International Conference on Data Mining, ICDM (pp. 463-467). [4063672]

A simple genetic algorithm for tracing the deformed midline on a single slice of brain CT using quadratic Bézier curves. / Liao, Chun Chih; Xiao, Furen; Wong, Jau Min; Chiang, I-Jen.

Proceedings - IEEE International Conference on Data Mining, ICDM. 2006. p. 463-467 4063672.

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

Liao, CC, Xiao, F, Wong, JM & Chiang, I-J 2006, A simple genetic algorithm for tracing the deformed midline on a single slice of brain CT using quadratic Bézier curves. in Proceedings - IEEE International Conference on Data Mining, ICDM., 4063672, pp. 463-467, 6th IEEE International Conference on Data Mining - Workshops, ICDM 2006, Hong Kong, China, 12/18/06.
Liao CC, Xiao F, Wong JM, Chiang I-J. A simple genetic algorithm for tracing the deformed midline on a single slice of brain CT using quadratic Bézier curves. In Proceedings - IEEE International Conference on Data Mining, ICDM. 2006. p. 463-467. 4063672
Liao, Chun Chih ; Xiao, Furen ; Wong, Jau Min ; Chiang, I-Jen. / A simple genetic algorithm for tracing the deformed midline on a single slice of brain CT using quadratic Bézier curves. Proceedings - IEEE International Conference on Data Mining, ICDM. 2006. pp. 463-467
@inproceedings{784544934b474568956eeaaf9037517e,
title = "A simple genetic algorithm for tracing the deformed midline on a single slice of brain CT using quadratic B{\'e}zier curves",
abstract = "Midline shift (MLS) is one of the most important quantitative features clinicians use to evaluate the severity of brain compression. It can be recognized by modeling brain deformation according to the estimated biomechanical properties of the brain structures. This paper proposes a novel method to identify the deformed midline by decomposing it into three segments: the upper and the lower straight segments representing parts of the tough meninges separating two brain hemispheres, and the central curved segment formed by a quadratic B{\'e}zier curve, representing the intervening soft brain tissue. The deformed midline is obtained by minimizing the summed square of the differences across all midline points, applying a genetic algorithm. Our algorithm was evaluated on images containing various pathologies from 81 consecutive patients treated in a single institute over one-year period. The deformed midlines were evaluated by human experts, and the values of midline shift were accurate in 95{\%}.",
author = "Liao, {Chun Chih} and Furen Xiao and Wong, {Jau Min} and I-Jen Chiang",
year = "2006",
language = "English",
isbn = "0769527027",
pages = "463--467",
booktitle = "Proceedings - IEEE International Conference on Data Mining, ICDM",

}

TY - GEN

T1 - A simple genetic algorithm for tracing the deformed midline on a single slice of brain CT using quadratic Bézier curves

AU - Liao, Chun Chih

AU - Xiao, Furen

AU - Wong, Jau Min

AU - Chiang, I-Jen

PY - 2006

Y1 - 2006

N2 - Midline shift (MLS) is one of the most important quantitative features clinicians use to evaluate the severity of brain compression. It can be recognized by modeling brain deformation according to the estimated biomechanical properties of the brain structures. This paper proposes a novel method to identify the deformed midline by decomposing it into three segments: the upper and the lower straight segments representing parts of the tough meninges separating two brain hemispheres, and the central curved segment formed by a quadratic Bézier curve, representing the intervening soft brain tissue. The deformed midline is obtained by minimizing the summed square of the differences across all midline points, applying a genetic algorithm. Our algorithm was evaluated on images containing various pathologies from 81 consecutive patients treated in a single institute over one-year period. The deformed midlines were evaluated by human experts, and the values of midline shift were accurate in 95%.

AB - Midline shift (MLS) is one of the most important quantitative features clinicians use to evaluate the severity of brain compression. It can be recognized by modeling brain deformation according to the estimated biomechanical properties of the brain structures. This paper proposes a novel method to identify the deformed midline by decomposing it into three segments: the upper and the lower straight segments representing parts of the tough meninges separating two brain hemispheres, and the central curved segment formed by a quadratic Bézier curve, representing the intervening soft brain tissue. The deformed midline is obtained by minimizing the summed square of the differences across all midline points, applying a genetic algorithm. Our algorithm was evaluated on images containing various pathologies from 81 consecutive patients treated in a single institute over one-year period. The deformed midlines were evaluated by human experts, and the values of midline shift were accurate in 95%.

UR - http://www.scopus.com/inward/record.url?scp=38549108110&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=38549108110&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:38549108110

SN - 0769527027

SN - 9780769527024

SP - 463

EP - 467

BT - Proceedings - IEEE International Conference on Data Mining, ICDM

ER -