Volumetric tumour detection using improved region grow algorithm
by Shitala Prasad; Shikha Gupta
International Journal of Computational Systems Engineering (IJCSYSE), Vol. 4, No. 2/3, 2018

Abstract: This paper works on segmentation of brain pathological tissues (tumour, edema and narcotic core) and visualise it in 3D for their better physiological understanding. We propose a novel approach which combines threshold and region grow algorithm for tumour detection. In this proposed system, FLAIR and T2 modalities of MRI are used due to their unique ability to detect the high and low contrast lesions with great accuracy. In this approach, first the tumour is segmented from an image which is a combination of FLAIR and T2 image using a threshold value, selected automatically based on the intensity variance of tumour and normal tissues in 3D MR images. Then the tumour part is extracted from the actual 3D MRI of brain by selecting the largest connected volume. To correctly detect tumour 26 connected neighbours are used. The method is evaluated using a publically available BRAT dataset of 80 different patients having gliomas tumours. The accuracy in terms of detection is reached to 97.5% which is best compared to other state-of-the-art in given time frame. The algorithm takes 4-5 minutes for generating the 3D visualisation for final output.

Online publication date: Mon, 30-Apr-2018

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Computational Systems Engineering (IJCSYSE):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com