Brain lesion segmentation of Diffusion-weighted MRI using gray level co-occurrence matrix

Norhashimah Mohd Saad, S. A R Abu-Bakar, Sobri Muda, M. M. Mokji, Lizawati Salahuddin

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

6 Citations (Scopus)

Abstract

This paper presents an automated segmentation of brain lesion from Diffusion-weighted magnetic resonance images (DW-MRI or DWI) based on region and boundary information in gray level co-occurrence matrix (GLCM). The lesions are hyperintense lesion from tumour, acute infarction, haemorrhage and abscess, and hypointense lesion from chronic infarction and haemorrhage. Pre-processing is applied to the DWI for intensity normalization, background removal and intensity enhancement. Then, GLCM is computed to segment the lesions. Different peaks from the GLCM cross-section indicate the present of normal brain region, cerebral spinal fluid (CSF), hyperintense or hypointense lesions. Minimum and maximum threshold values are computed from the GLCM cross-section. Region and boundary information from the GLCM are introduced as the statistical features for segmentation of hyperintense and hypointense lesions. The proposed method provides very good segmentation results even in a small brain lesion.

Original languageEnglish
Title of host publication2011 IEEE International Conference on Imaging Systems and Techniques, IST 2011 - Proceedings
Pages284-289
Number of pages6
DOIs
Publication statusPublished - 2011
Event2011 IEEE International Conference on Imaging Systems and Techniques, IST 2011 - Batu Ferringhi, Penang
Duration: 17 May 201118 May 2011

Other

Other2011 IEEE International Conference on Imaging Systems and Techniques, IST 2011
CityBatu Ferringhi, Penang
Period17/5/1118/5/11

Fingerprint

Magnetic resonance imaging
Brain
Magnetic resonance
Tumors
Fluids
Processing

Keywords

  • Diffusion-weighted MRI
  • GLCM
  • Segmentation

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Mohd Saad, N., Abu-Bakar, S. A. R., Muda, S., Mokji, M. M., & Salahuddin, L. (2011). Brain lesion segmentation of Diffusion-weighted MRI using gray level co-occurrence matrix. In 2011 IEEE International Conference on Imaging Systems and Techniques, IST 2011 - Proceedings (pp. 284-289). [5962179] https://doi.org/10.1109/IST.2011.5962179

Brain lesion segmentation of Diffusion-weighted MRI using gray level co-occurrence matrix. / Mohd Saad, Norhashimah; Abu-Bakar, S. A R; Muda, Sobri; Mokji, M. M.; Salahuddin, Lizawati.

2011 IEEE International Conference on Imaging Systems and Techniques, IST 2011 - Proceedings. 2011. p. 284-289 5962179.

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

Mohd Saad, N, Abu-Bakar, SAR, Muda, S, Mokji, MM & Salahuddin, L 2011, Brain lesion segmentation of Diffusion-weighted MRI using gray level co-occurrence matrix. in 2011 IEEE International Conference on Imaging Systems and Techniques, IST 2011 - Proceedings., 5962179, pp. 284-289, 2011 IEEE International Conference on Imaging Systems and Techniques, IST 2011, Batu Ferringhi, Penang, 17/5/11. https://doi.org/10.1109/IST.2011.5962179
Mohd Saad N, Abu-Bakar SAR, Muda S, Mokji MM, Salahuddin L. Brain lesion segmentation of Diffusion-weighted MRI using gray level co-occurrence matrix. In 2011 IEEE International Conference on Imaging Systems and Techniques, IST 2011 - Proceedings. 2011. p. 284-289. 5962179 https://doi.org/10.1109/IST.2011.5962179
Mohd Saad, Norhashimah ; Abu-Bakar, S. A R ; Muda, Sobri ; Mokji, M. M. ; Salahuddin, Lizawati. / Brain lesion segmentation of Diffusion-weighted MRI using gray level co-occurrence matrix. 2011 IEEE International Conference on Imaging Systems and Techniques, IST 2011 - Proceedings. 2011. pp. 284-289
@inproceedings{d0b276d544f842889481cc075a3c4869,
title = "Brain lesion segmentation of Diffusion-weighted MRI using gray level co-occurrence matrix",
abstract = "This paper presents an automated segmentation of brain lesion from Diffusion-weighted magnetic resonance images (DW-MRI or DWI) based on region and boundary information in gray level co-occurrence matrix (GLCM). The lesions are hyperintense lesion from tumour, acute infarction, haemorrhage and abscess, and hypointense lesion from chronic infarction and haemorrhage. Pre-processing is applied to the DWI for intensity normalization, background removal and intensity enhancement. Then, GLCM is computed to segment the lesions. Different peaks from the GLCM cross-section indicate the present of normal brain region, cerebral spinal fluid (CSF), hyperintense or hypointense lesions. Minimum and maximum threshold values are computed from the GLCM cross-section. Region and boundary information from the GLCM are introduced as the statistical features for segmentation of hyperintense and hypointense lesions. The proposed method provides very good segmentation results even in a small brain lesion.",
keywords = "Diffusion-weighted MRI, GLCM, Segmentation",
author = "{Mohd Saad}, Norhashimah and Abu-Bakar, {S. A R} and Sobri Muda and Mokji, {M. M.} and Lizawati Salahuddin",
year = "2011",
doi = "10.1109/IST.2011.5962179",
language = "English",
isbn = "9781612848969",
pages = "284--289",
booktitle = "2011 IEEE International Conference on Imaging Systems and Techniques, IST 2011 - Proceedings",

}

TY - GEN

T1 - Brain lesion segmentation of Diffusion-weighted MRI using gray level co-occurrence matrix

AU - Mohd Saad, Norhashimah

AU - Abu-Bakar, S. A R

AU - Muda, Sobri

AU - Mokji, M. M.

AU - Salahuddin, Lizawati

PY - 2011

Y1 - 2011

N2 - This paper presents an automated segmentation of brain lesion from Diffusion-weighted magnetic resonance images (DW-MRI or DWI) based on region and boundary information in gray level co-occurrence matrix (GLCM). The lesions are hyperintense lesion from tumour, acute infarction, haemorrhage and abscess, and hypointense lesion from chronic infarction and haemorrhage. Pre-processing is applied to the DWI for intensity normalization, background removal and intensity enhancement. Then, GLCM is computed to segment the lesions. Different peaks from the GLCM cross-section indicate the present of normal brain region, cerebral spinal fluid (CSF), hyperintense or hypointense lesions. Minimum and maximum threshold values are computed from the GLCM cross-section. Region and boundary information from the GLCM are introduced as the statistical features for segmentation of hyperintense and hypointense lesions. The proposed method provides very good segmentation results even in a small brain lesion.

AB - This paper presents an automated segmentation of brain lesion from Diffusion-weighted magnetic resonance images (DW-MRI or DWI) based on region and boundary information in gray level co-occurrence matrix (GLCM). The lesions are hyperintense lesion from tumour, acute infarction, haemorrhage and abscess, and hypointense lesion from chronic infarction and haemorrhage. Pre-processing is applied to the DWI for intensity normalization, background removal and intensity enhancement. Then, GLCM is computed to segment the lesions. Different peaks from the GLCM cross-section indicate the present of normal brain region, cerebral spinal fluid (CSF), hyperintense or hypointense lesions. Minimum and maximum threshold values are computed from the GLCM cross-section. Region and boundary information from the GLCM are introduced as the statistical features for segmentation of hyperintense and hypointense lesions. The proposed method provides very good segmentation results even in a small brain lesion.

KW - Diffusion-weighted MRI

KW - GLCM

KW - Segmentation

UR - http://www.scopus.com/inward/record.url?scp=80052156207&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80052156207&partnerID=8YFLogxK

U2 - 10.1109/IST.2011.5962179

DO - 10.1109/IST.2011.5962179

M3 - Conference contribution

SN - 9781612848969

SP - 284

EP - 289

BT - 2011 IEEE International Conference on Imaging Systems and Techniques, IST 2011 - Proceedings

ER -