Brain lesion segmentation of diffusion-weighted MRI using thresholding technique

N. Mohd Saad, L. Salahuddin, S. A R Abu-Bakar, S. Muda, M. M. Mokji

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

Abstract

This paper presents brain lesion segmentation of diffusion-weighted magnetic resonance images (DW-MRI or DWI) based on thresholding technique. The lesions are solid tumor, acute infarction, haemorrhage, and abscess. Pre-processing is applied to the DWI for normalization, background removal and enhancement. Two different techniques which are Gamma-law transformation and contrast stretching are applied for the enhancement. For the image segmentation process, the DWI is divided by 8 x 8 regions. Then image histogram is calculated at each region to find the maximum number of pixels for each intensity level. The optimal threshold is determined by comparing normal and lesion regions. By using Gamma-law transformation, 0.48 is found as the optimal thresholding value whereas 0.28 for the contrast stretching. The proposed technique has been validated by using area overlap (AO), false positive rate (FPR), and false negative rate (FNR). Thresholding with gamma-law transformation algorithm provides better segmentation results compared to contrast stretching technique. The proposed technique provides good brain lesion segmentation results even though the simplest segmentation technique is used.

Original languageEnglish
Title of host publicationIFMBE Proceedings
Pages604-610
Number of pages7
Volume35 IFMBE
DOIs
Publication statusPublished - 2011
Event5th Kuala Lumpur International Conference on Biomedical Engineering, BIOMED 2011, Held in Conjunction with the 8th Asian Pacific Conference on Medical and Biological Engineering, APCMBE 2011 - Kuala Lumpur, Malaysia
Duration: 20 Jun 201123 Jun 2011

Other

Other5th Kuala Lumpur International Conference on Biomedical Engineering, BIOMED 2011, Held in Conjunction with the 8th Asian Pacific Conference on Medical and Biological Engineering, APCMBE 2011
CountryMalaysia
CityKuala Lumpur
Period20/6/1123/6/11

Fingerprint

Magnetic resonance imaging
Stretching
Brain
Magnetic resonance
Image segmentation
Tumors
Pixels
Processing

Keywords

  • DWI
  • Gamma-law and contrast stretching
  • segmentation
  • thresholding

ASJC Scopus subject areas

  • Biomedical Engineering
  • Bioengineering

Cite this

Mohd Saad, N., Salahuddin, L., Abu-Bakar, S. A. R., Muda, S., & Mokji, M. M. (2011). Brain lesion segmentation of diffusion-weighted MRI using thresholding technique. In IFMBE Proceedings (Vol. 35 IFMBE, pp. 604-610) https://doi.org/10.1007/978-3-642-21729-6_150

Brain lesion segmentation of diffusion-weighted MRI using thresholding technique. / Mohd Saad, N.; Salahuddin, L.; Abu-Bakar, S. A R; Muda, S.; Mokji, M. M.

IFMBE Proceedings. Vol. 35 IFMBE 2011. p. 604-610.

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

Mohd Saad, N, Salahuddin, L, Abu-Bakar, SAR, Muda, S & Mokji, MM 2011, Brain lesion segmentation of diffusion-weighted MRI using thresholding technique. in IFMBE Proceedings. vol. 35 IFMBE, pp. 604-610, 5th Kuala Lumpur International Conference on Biomedical Engineering, BIOMED 2011, Held in Conjunction with the 8th Asian Pacific Conference on Medical and Biological Engineering, APCMBE 2011, Kuala Lumpur, Malaysia, 20/6/11. https://doi.org/10.1007/978-3-642-21729-6_150
Mohd Saad N, Salahuddin L, Abu-Bakar SAR, Muda S, Mokji MM. Brain lesion segmentation of diffusion-weighted MRI using thresholding technique. In IFMBE Proceedings. Vol. 35 IFMBE. 2011. p. 604-610 https://doi.org/10.1007/978-3-642-21729-6_150
Mohd Saad, N. ; Salahuddin, L. ; Abu-Bakar, S. A R ; Muda, S. ; Mokji, M. M. / Brain lesion segmentation of diffusion-weighted MRI using thresholding technique. IFMBE Proceedings. Vol. 35 IFMBE 2011. pp. 604-610
@inproceedings{e0728cb96b7041039eb6369c369675cc,
title = "Brain lesion segmentation of diffusion-weighted MRI using thresholding technique",
abstract = "This paper presents brain lesion segmentation of diffusion-weighted magnetic resonance images (DW-MRI or DWI) based on thresholding technique. The lesions are solid tumor, acute infarction, haemorrhage, and abscess. Pre-processing is applied to the DWI for normalization, background removal and enhancement. Two different techniques which are Gamma-law transformation and contrast stretching are applied for the enhancement. For the image segmentation process, the DWI is divided by 8 x 8 regions. Then image histogram is calculated at each region to find the maximum number of pixels for each intensity level. The optimal threshold is determined by comparing normal and lesion regions. By using Gamma-law transformation, 0.48 is found as the optimal thresholding value whereas 0.28 for the contrast stretching. The proposed technique has been validated by using area overlap (AO), false positive rate (FPR), and false negative rate (FNR). Thresholding with gamma-law transformation algorithm provides better segmentation results compared to contrast stretching technique. The proposed technique provides good brain lesion segmentation results even though the simplest segmentation technique is used.",
keywords = "DWI, Gamma-law and contrast stretching, segmentation, thresholding",
author = "{Mohd Saad}, N. and L. Salahuddin and Abu-Bakar, {S. A R} and S. Muda and Mokji, {M. M.}",
year = "2011",
doi = "10.1007/978-3-642-21729-6_150",
language = "English",
isbn = "9783642217289",
volume = "35 IFMBE",
pages = "604--610",
booktitle = "IFMBE Proceedings",

}

TY - GEN

T1 - Brain lesion segmentation of diffusion-weighted MRI using thresholding technique

AU - Mohd Saad, N.

AU - Salahuddin, L.

AU - Abu-Bakar, S. A R

AU - Muda, S.

AU - Mokji, M. M.

PY - 2011

Y1 - 2011

N2 - This paper presents brain lesion segmentation of diffusion-weighted magnetic resonance images (DW-MRI or DWI) based on thresholding technique. The lesions are solid tumor, acute infarction, haemorrhage, and abscess. Pre-processing is applied to the DWI for normalization, background removal and enhancement. Two different techniques which are Gamma-law transformation and contrast stretching are applied for the enhancement. For the image segmentation process, the DWI is divided by 8 x 8 regions. Then image histogram is calculated at each region to find the maximum number of pixels for each intensity level. The optimal threshold is determined by comparing normal and lesion regions. By using Gamma-law transformation, 0.48 is found as the optimal thresholding value whereas 0.28 for the contrast stretching. The proposed technique has been validated by using area overlap (AO), false positive rate (FPR), and false negative rate (FNR). Thresholding with gamma-law transformation algorithm provides better segmentation results compared to contrast stretching technique. The proposed technique provides good brain lesion segmentation results even though the simplest segmentation technique is used.

AB - This paper presents brain lesion segmentation of diffusion-weighted magnetic resonance images (DW-MRI or DWI) based on thresholding technique. The lesions are solid tumor, acute infarction, haemorrhage, and abscess. Pre-processing is applied to the DWI for normalization, background removal and enhancement. Two different techniques which are Gamma-law transformation and contrast stretching are applied for the enhancement. For the image segmentation process, the DWI is divided by 8 x 8 regions. Then image histogram is calculated at each region to find the maximum number of pixels for each intensity level. The optimal threshold is determined by comparing normal and lesion regions. By using Gamma-law transformation, 0.48 is found as the optimal thresholding value whereas 0.28 for the contrast stretching. The proposed technique has been validated by using area overlap (AO), false positive rate (FPR), and false negative rate (FNR). Thresholding with gamma-law transformation algorithm provides better segmentation results compared to contrast stretching technique. The proposed technique provides good brain lesion segmentation results even though the simplest segmentation technique is used.

KW - DWI

KW - Gamma-law and contrast stretching

KW - segmentation

KW - thresholding

UR - http://www.scopus.com/inward/record.url?scp=79959947545&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79959947545&partnerID=8YFLogxK

U2 - 10.1007/978-3-642-21729-6_150

DO - 10.1007/978-3-642-21729-6_150

M3 - Conference contribution

AN - SCOPUS:79959947545

SN - 9783642217289

VL - 35 IFMBE

SP - 604

EP - 610

BT - IFMBE Proceedings

ER -