Automated assessment of midline shift in head injury patients

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

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

Objectives: Midline shift (MLS) is an important quantitative feature for evaluating severity of brain compression by various pathologies, including traumatic intracranial hematomas. In this study, we sought to determine the accuracy and the prognostic value of our computer algorithm that automatically measures the MLS of the brain on computed tomography (CT) images in patients with head injury. Patients and methods: Modelling the deformed midline into three segments, we had designed an algorithm to estimate the MLS automatically. We retrospectively applied our algorithm to the initial CT images of 53 patients with head injury to determine the automated MLS (aMLS) and validated it against that measured by human (hMLS). Both measurements were separately used to predict the neurological outcome of the patients. Results: The hMLS ranged from 0 to 30 mm. It was greater than 5 mm in images of 17 patients (32%). In 49 images (92%), the difference between hMLS and aMLS was 5 mm, our algorithm achieved sensitivity of 94% and specificity of 100%. For mortality prediction, aMLS was no worse than hMLS. Conclusion: In summary, automated MLS was accurate and predicted outcome as well as that measured manually. This approach might be useful in constructing a fully automated computer-assisted diagnosis system.

Original languageEnglish
Pages (from-to)785-790
Number of pages6
JournalClinical Neurology and Neurosurgery
Volume112
Issue number9
DOIs
Publication statusPublished - Nov 2010

Fingerprint

Craniocerebral Trauma
Traumatic Intracranial Hemorrhage
Computer-Assisted Diagnosis
Tomography
Brain
Pathology
Sensitivity and Specificity
Mortality

Keywords

  • Computer-aided assessment
  • CT scanning
  • Head trauma
  • Midline shift
  • Other tools of modern imaging
  • Outcome

ASJC Scopus subject areas

  • Clinical Neurology
  • Surgery

Cite this

Xiao, F., Liao, C. C., Huang, K. C., Chiang, I. J., & Wong, J. M. (2010). Automated assessment of midline shift in head injury patients. Clinical Neurology and Neurosurgery, 112(9), 785-790. https://doi.org/10.1016/j.clineuro.2010.06.020

Automated assessment of midline shift in head injury patients. / Xiao, Furen; Liao, Chun Chih; Huang, Ke Chun; Chiang, I. Jen; Wong, Jau Min.

In: Clinical Neurology and Neurosurgery, Vol. 112, No. 9, 11.2010, p. 785-790.

Research output: Contribution to journalArticle

Xiao, Furen ; Liao, Chun Chih ; Huang, Ke Chun ; Chiang, I. Jen ; Wong, Jau Min. / Automated assessment of midline shift in head injury patients. In: Clinical Neurology and Neurosurgery. 2010 ; Vol. 112, No. 9. pp. 785-790.
@article{ca849fdccced4ec3aedac59be4512850,
title = "Automated assessment of midline shift in head injury patients",
abstract = "Objectives: Midline shift (MLS) is an important quantitative feature for evaluating severity of brain compression by various pathologies, including traumatic intracranial hematomas. In this study, we sought to determine the accuracy and the prognostic value of our computer algorithm that automatically measures the MLS of the brain on computed tomography (CT) images in patients with head injury. Patients and methods: Modelling the deformed midline into three segments, we had designed an algorithm to estimate the MLS automatically. We retrospectively applied our algorithm to the initial CT images of 53 patients with head injury to determine the automated MLS (aMLS) and validated it against that measured by human (hMLS). Both measurements were separately used to predict the neurological outcome of the patients. Results: The hMLS ranged from 0 to 30 mm. It was greater than 5 mm in images of 17 patients (32{\%}). In 49 images (92{\%}), the difference between hMLS and aMLS was 5 mm, our algorithm achieved sensitivity of 94{\%} and specificity of 100{\%}. For mortality prediction, aMLS was no worse than hMLS. Conclusion: In summary, automated MLS was accurate and predicted outcome as well as that measured manually. This approach might be useful in constructing a fully automated computer-assisted diagnosis system.",
keywords = "Computer-aided assessment, CT scanning, Head trauma, Midline shift, Other tools of modern imaging, Outcome",
author = "Furen Xiao and Liao, {Chun Chih} and Huang, {Ke Chun} and Chiang, {I. Jen} and Wong, {Jau Min}",
year = "2010",
month = "11",
doi = "10.1016/j.clineuro.2010.06.020",
language = "English",
volume = "112",
pages = "785--790",
journal = "Clinical Neurology and Neurosurgery",
issn = "0303-8467",
publisher = "Elsevier",
number = "9",

}

TY - JOUR

T1 - Automated assessment of midline shift in head injury patients

AU - Xiao, Furen

AU - Liao, Chun Chih

AU - Huang, Ke Chun

AU - Chiang, I. Jen

AU - Wong, Jau Min

PY - 2010/11

Y1 - 2010/11

N2 - Objectives: Midline shift (MLS) is an important quantitative feature for evaluating severity of brain compression by various pathologies, including traumatic intracranial hematomas. In this study, we sought to determine the accuracy and the prognostic value of our computer algorithm that automatically measures the MLS of the brain on computed tomography (CT) images in patients with head injury. Patients and methods: Modelling the deformed midline into three segments, we had designed an algorithm to estimate the MLS automatically. We retrospectively applied our algorithm to the initial CT images of 53 patients with head injury to determine the automated MLS (aMLS) and validated it against that measured by human (hMLS). Both measurements were separately used to predict the neurological outcome of the patients. Results: The hMLS ranged from 0 to 30 mm. It was greater than 5 mm in images of 17 patients (32%). In 49 images (92%), the difference between hMLS and aMLS was 5 mm, our algorithm achieved sensitivity of 94% and specificity of 100%. For mortality prediction, aMLS was no worse than hMLS. Conclusion: In summary, automated MLS was accurate and predicted outcome as well as that measured manually. This approach might be useful in constructing a fully automated computer-assisted diagnosis system.

AB - Objectives: Midline shift (MLS) is an important quantitative feature for evaluating severity of brain compression by various pathologies, including traumatic intracranial hematomas. In this study, we sought to determine the accuracy and the prognostic value of our computer algorithm that automatically measures the MLS of the brain on computed tomography (CT) images in patients with head injury. Patients and methods: Modelling the deformed midline into three segments, we had designed an algorithm to estimate the MLS automatically. We retrospectively applied our algorithm to the initial CT images of 53 patients with head injury to determine the automated MLS (aMLS) and validated it against that measured by human (hMLS). Both measurements were separately used to predict the neurological outcome of the patients. Results: The hMLS ranged from 0 to 30 mm. It was greater than 5 mm in images of 17 patients (32%). In 49 images (92%), the difference between hMLS and aMLS was 5 mm, our algorithm achieved sensitivity of 94% and specificity of 100%. For mortality prediction, aMLS was no worse than hMLS. Conclusion: In summary, automated MLS was accurate and predicted outcome as well as that measured manually. This approach might be useful in constructing a fully automated computer-assisted diagnosis system.

KW - Computer-aided assessment

KW - CT scanning

KW - Head trauma

KW - Midline shift

KW - Other tools of modern imaging

KW - Outcome

UR - http://www.scopus.com/inward/record.url?scp=77957778128&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77957778128&partnerID=8YFLogxK

U2 - 10.1016/j.clineuro.2010.06.020

DO - 10.1016/j.clineuro.2010.06.020

M3 - Article

VL - 112

SP - 785

EP - 790

JO - Clinical Neurology and Neurosurgery

JF - Clinical Neurology and Neurosurgery

SN - 0303-8467

IS - 9

ER -