Automatic diagnosis of intracranial hematoma on brain CT using knowledge discovery techniques: Is finer resolution better?

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

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Computed tomography (CT) of the brain is the study of choice for neurological emergencies. Physicians use CT to diagnose various types of intracranial hematomas, including epidural, subdural, and intracerebral hematomas according to their locations and shapes. We have proposed a novel method that can automatically diagnose intracranial hematomas by combining machine vision and knowledge discovery techniques. In this paper, we attempted segmentation of intracranial hematomas in multiple resolutions using image pyramids. The features of the segmented hematoma and the diagnoses made by physicians were used by C4.5 algorithm to construct a decision tree. The algorithm was evaluated on 48 pathological images treated in a single institute. The two discovered rules in all resolutions closely resembled those used by human experts, and were able to make correct diagnoses in all cases. Results of tenfold cross-validation were also satisfactory.

Original languageEnglish
Pages (from-to)401-408
Number of pages8
JournalBiomedical Engineering - Applications, Basis and Communications
Volume20
Issue number6
DOIs
Publication statusPublished - Dec 2008

Fingerprint

Hematoma
Tomography
Data mining
Brain
Cranial Epidural Hematoma
Physicians
Subdural Hematoma
Decision Trees
Image resolution
Decision trees
Computer vision
Emergencies

Keywords

  • Computed tomography
  • Image pyramids
  • Image segmentation
  • Intracranial hematoma
  • Knowledge discovery and data mining

ASJC Scopus subject areas

  • Biophysics
  • Biomedical Engineering
  • Bioengineering

Cite this

Automatic diagnosis of intracranial hematoma on brain CT using knowledge discovery techniques : Is finer resolution better? / Xiao, Furen; Liao, Chun Chih; Wong, Jau Min; Chiang, I. Jen.

In: Biomedical Engineering - Applications, Basis and Communications, Vol. 20, No. 6, 12.2008, p. 401-408.

Research output: Contribution to journalArticle

@article{b5277bf701c3430eb8fe627af9e35f63,
title = "Automatic diagnosis of intracranial hematoma on brain CT using knowledge discovery techniques: Is finer resolution better?",
abstract = "Computed tomography (CT) of the brain is the study of choice for neurological emergencies. Physicians use CT to diagnose various types of intracranial hematomas, including epidural, subdural, and intracerebral hematomas according to their locations and shapes. We have proposed a novel method that can automatically diagnose intracranial hematomas by combining machine vision and knowledge discovery techniques. In this paper, we attempted segmentation of intracranial hematomas in multiple resolutions using image pyramids. The features of the segmented hematoma and the diagnoses made by physicians were used by C4.5 algorithm to construct a decision tree. The algorithm was evaluated on 48 pathological images treated in a single institute. The two discovered rules in all resolutions closely resembled those used by human experts, and were able to make correct diagnoses in all cases. Results of tenfold cross-validation were also satisfactory.",
keywords = "Computed tomography, Image pyramids, Image segmentation, Intracranial hematoma, Knowledge discovery and data mining",
author = "Furen Xiao and Liao, {Chun Chih} and Wong, {Jau Min} and Chiang, {I. Jen}",
year = "2008",
month = "12",
doi = "10.4015/S101623720800101X",
language = "English",
volume = "20",
pages = "401--408",
journal = "Journal of Chinese Corrosion Engineering",
issn = "1016-2372",
publisher = "World Scientific Publishing Co. Pte Ltd",
number = "6",

}

TY - JOUR

T1 - Automatic diagnosis of intracranial hematoma on brain CT using knowledge discovery techniques

T2 - Is finer resolution better?

AU - Xiao, Furen

AU - Liao, Chun Chih

AU - Wong, Jau Min

AU - Chiang, I. Jen

PY - 2008/12

Y1 - 2008/12

N2 - Computed tomography (CT) of the brain is the study of choice for neurological emergencies. Physicians use CT to diagnose various types of intracranial hematomas, including epidural, subdural, and intracerebral hematomas according to their locations and shapes. We have proposed a novel method that can automatically diagnose intracranial hematomas by combining machine vision and knowledge discovery techniques. In this paper, we attempted segmentation of intracranial hematomas in multiple resolutions using image pyramids. The features of the segmented hematoma and the diagnoses made by physicians were used by C4.5 algorithm to construct a decision tree. The algorithm was evaluated on 48 pathological images treated in a single institute. The two discovered rules in all resolutions closely resembled those used by human experts, and were able to make correct diagnoses in all cases. Results of tenfold cross-validation were also satisfactory.

AB - Computed tomography (CT) of the brain is the study of choice for neurological emergencies. Physicians use CT to diagnose various types of intracranial hematomas, including epidural, subdural, and intracerebral hematomas according to their locations and shapes. We have proposed a novel method that can automatically diagnose intracranial hematomas by combining machine vision and knowledge discovery techniques. In this paper, we attempted segmentation of intracranial hematomas in multiple resolutions using image pyramids. The features of the segmented hematoma and the diagnoses made by physicians were used by C4.5 algorithm to construct a decision tree. The algorithm was evaluated on 48 pathological images treated in a single institute. The two discovered rules in all resolutions closely resembled those used by human experts, and were able to make correct diagnoses in all cases. Results of tenfold cross-validation were also satisfactory.

KW - Computed tomography

KW - Image pyramids

KW - Image segmentation

KW - Intracranial hematoma

KW - Knowledge discovery and data mining

UR - http://www.scopus.com/inward/record.url?scp=58149152754&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=58149152754&partnerID=8YFLogxK

U2 - 10.4015/S101623720800101X

DO - 10.4015/S101623720800101X

M3 - Article

AN - SCOPUS:58149152754

VL - 20

SP - 401

EP - 408

JO - Journal of Chinese Corrosion Engineering

JF - Journal of Chinese Corrosion Engineering

SN - 1016-2372

IS - 6

ER -