Abnormalities detection in serial computed tomography brain images using multi-level segmentation approach

Wan Mimi Diyana Wan Zaki, M. Faizal A Fauzi, Rosli Besar, W. Siti Haimatul Munirah W Ahmad

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

Segmentation, where pixels are categorized by tissue types, is essential in medical image processing. This paper proposes a multi-level Fuzzy C-Means method to extract an intracranial from its background and skull. Then, a two-level Otsu multi-thresholding method is applied to segment the intracranial structure into cerebrospinal fluid, brain matters and other homogenous regions. Based on symmetrical properties in the intracranial structures, the left-half and right-half segmented intracranial regions are quantitatively compared with respect to the intracranial midline. The segmented regions are found to be very useful in providing information regarding normal and abnormal structures in the intracranial because any asymmetry that is detected would indicate a high probability of abnormalities. Additionally, pixel intensity information such as standard deviation and the maximum value of the pixels of the segmented regions are used to distinguish abnormalities such as bleeding and calcification from normal cases. This experimental work uses a medical image database consisting of 519 normal and 201 abnormal serial computed tomography (CT) brain images from 31 patients. The proposed multi-level segmentation approach proved to effectively isolate important homogenous regions in CT brain images. The extracted features of the regions would provide a strong basis for the application of content-based medical image retrieval (CMBIR).

Original languageEnglish
Pages (from-to)321-340
Number of pages20
JournalMultimedia Tools and Applications
Volume54
Issue number2
DOIs
Publication statusPublished - Aug 2011

Fingerprint

Tomography
Brain
Pixels
Medical image processing
Cerebrospinal fluid
Image retrieval
Tissue

Keywords

  • Content-based medical image retrieval
  • CT brain images
  • Fuzzy C-Means
  • Multi-level segmentation
  • Otsu thresholding

ASJC Scopus subject areas

  • Media Technology
  • Hardware and Architecture
  • Computer Networks and Communications
  • Software

Cite this

Abnormalities detection in serial computed tomography brain images using multi-level segmentation approach. / Wan Zaki, Wan Mimi Diyana; Fauzi, M. Faizal A; Besar, Rosli; Ahmad, W. Siti Haimatul Munirah W.

In: Multimedia Tools and Applications, Vol. 54, No. 2, 08.2011, p. 321-340.

Research output: Contribution to journalArticle

Wan Zaki, Wan Mimi Diyana ; Fauzi, M. Faizal A ; Besar, Rosli ; Ahmad, W. Siti Haimatul Munirah W. / Abnormalities detection in serial computed tomography brain images using multi-level segmentation approach. In: Multimedia Tools and Applications. 2011 ; Vol. 54, No. 2. pp. 321-340.
@article{2a889259ef114bb3aee7bec9314f4630,
title = "Abnormalities detection in serial computed tomography brain images using multi-level segmentation approach",
abstract = "Segmentation, where pixels are categorized by tissue types, is essential in medical image processing. This paper proposes a multi-level Fuzzy C-Means method to extract an intracranial from its background and skull. Then, a two-level Otsu multi-thresholding method is applied to segment the intracranial structure into cerebrospinal fluid, brain matters and other homogenous regions. Based on symmetrical properties in the intracranial structures, the left-half and right-half segmented intracranial regions are quantitatively compared with respect to the intracranial midline. The segmented regions are found to be very useful in providing information regarding normal and abnormal structures in the intracranial because any asymmetry that is detected would indicate a high probability of abnormalities. Additionally, pixel intensity information such as standard deviation and the maximum value of the pixels of the segmented regions are used to distinguish abnormalities such as bleeding and calcification from normal cases. This experimental work uses a medical image database consisting of 519 normal and 201 abnormal serial computed tomography (CT) brain images from 31 patients. The proposed multi-level segmentation approach proved to effectively isolate important homogenous regions in CT brain images. The extracted features of the regions would provide a strong basis for the application of content-based medical image retrieval (CMBIR).",
keywords = "Content-based medical image retrieval, CT brain images, Fuzzy C-Means, Multi-level segmentation, Otsu thresholding",
author = "{Wan Zaki}, {Wan Mimi Diyana} and Fauzi, {M. Faizal A} and Rosli Besar and Ahmad, {W. Siti Haimatul Munirah W}",
year = "2011",
month = "8",
doi = "10.1007/s11042-010-0524-0",
language = "English",
volume = "54",
pages = "321--340",
journal = "Multimedia Tools and Applications",
issn = "1380-7501",
publisher = "Springer Netherlands",
number = "2",

}

TY - JOUR

T1 - Abnormalities detection in serial computed tomography brain images using multi-level segmentation approach

AU - Wan Zaki, Wan Mimi Diyana

AU - Fauzi, M. Faizal A

AU - Besar, Rosli

AU - Ahmad, W. Siti Haimatul Munirah W

PY - 2011/8

Y1 - 2011/8

N2 - Segmentation, where pixels are categorized by tissue types, is essential in medical image processing. This paper proposes a multi-level Fuzzy C-Means method to extract an intracranial from its background and skull. Then, a two-level Otsu multi-thresholding method is applied to segment the intracranial structure into cerebrospinal fluid, brain matters and other homogenous regions. Based on symmetrical properties in the intracranial structures, the left-half and right-half segmented intracranial regions are quantitatively compared with respect to the intracranial midline. The segmented regions are found to be very useful in providing information regarding normal and abnormal structures in the intracranial because any asymmetry that is detected would indicate a high probability of abnormalities. Additionally, pixel intensity information such as standard deviation and the maximum value of the pixels of the segmented regions are used to distinguish abnormalities such as bleeding and calcification from normal cases. This experimental work uses a medical image database consisting of 519 normal and 201 abnormal serial computed tomography (CT) brain images from 31 patients. The proposed multi-level segmentation approach proved to effectively isolate important homogenous regions in CT brain images. The extracted features of the regions would provide a strong basis for the application of content-based medical image retrieval (CMBIR).

AB - Segmentation, where pixels are categorized by tissue types, is essential in medical image processing. This paper proposes a multi-level Fuzzy C-Means method to extract an intracranial from its background and skull. Then, a two-level Otsu multi-thresholding method is applied to segment the intracranial structure into cerebrospinal fluid, brain matters and other homogenous regions. Based on symmetrical properties in the intracranial structures, the left-half and right-half segmented intracranial regions are quantitatively compared with respect to the intracranial midline. The segmented regions are found to be very useful in providing information regarding normal and abnormal structures in the intracranial because any asymmetry that is detected would indicate a high probability of abnormalities. Additionally, pixel intensity information such as standard deviation and the maximum value of the pixels of the segmented regions are used to distinguish abnormalities such as bleeding and calcification from normal cases. This experimental work uses a medical image database consisting of 519 normal and 201 abnormal serial computed tomography (CT) brain images from 31 patients. The proposed multi-level segmentation approach proved to effectively isolate important homogenous regions in CT brain images. The extracted features of the regions would provide a strong basis for the application of content-based medical image retrieval (CMBIR).

KW - Content-based medical image retrieval

KW - CT brain images

KW - Fuzzy C-Means

KW - Multi-level segmentation

KW - Otsu thresholding

UR - http://www.scopus.com/inward/record.url?scp=79959549585&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79959549585&partnerID=8YFLogxK

U2 - 10.1007/s11042-010-0524-0

DO - 10.1007/s11042-010-0524-0

M3 - Article

VL - 54

SP - 321

EP - 340

JO - Multimedia Tools and Applications

JF - Multimedia Tools and Applications

SN - 1380-7501

IS - 2

ER -