Browse By Repository:


Automated Region Growing for Segmentation of Brain Lesion in Diffusion-weighted MRI

Mohd Saad, Norhashimah and Abdullah, Abdul Rahim (2012) Automated Region Growing for Segmentation of Brain Lesion in Diffusion-weighted MRI. In: International MultiConference of Engineers and Computer Scientists 2012, 14-16 March 2012, Hong Kong.

[img] PDF
2012_Paper_Automated_Region_Growing_for_Segmentation.pdf - Published Version

Download (644Kb)


This paper presents an automatic segmentation of brain lesions from diffusion-weighted magnetic resonance imaging (DW-MRI or DWI) using region growing approach. The lesions are acute infarction, haemorrhage, tumour and abscess. Region splitting and merging is used to detect the lesion region. Then, histogram thresholding technique is applied to automate the seeds selection. The region is iteratively grown by comparing all unallocated neighbour pixels to the seeds. The difference between pixel’s intensity value and the region’s mean is used as the similarity measure. Evaluation is made for performance comparison between automatic and manual seeds selection. Overall, automated region growing algorithm provides comparable results with the semi-automatic segmentation.

Item Type: Conference or Workshop Item (Speech)
Subjects: T Technology > TK Electrical engineering. Electronics Nuclear engineering
Divisions: Faculty of Electronics and Computer Engineering > Department of Computer Engineering
Depositing User: Dr Abdul Rahim Abdullah
Date Deposited: 23 Aug 2013 07:52
Last Modified: 28 May 2015 04:04

Actions (login required)

View Item View Item


Downloads per month over past year