Segmenting ECG and MRI data using ant colony optimisation
by C.K. Roopa; B.S. Harish; S.V. Aruna Kumar
International Journal of Artificial Intelligence and Soft Computing (IJAISC), Vol. 7, No. 1, 2019

Abstract: This paper proposes efficient medical data segmentation using ant colony optimisation (ACO) and modified intuitionistic fuzzy C-means (MIFCM) clustering. MIFCM is a variant of intuitionistic fuzzy C-means which uses modified Hausdorff distance measure to compute the distance between voxels and cluster centres. MIFCM handles uncertainty to a better extent compared to fuzzy C-means and its variants. However, MIFCM possesses the limitation that it initialises the cluster centre randomly, which makes the algorithm converge to local optimal solution rather than global solution. Thus, ant colony optimisation is proposed in this paper in order to overcome this. In this method, cluster centres are initialised based on ant colony optimisation. To check the efficacy of the proposed method, the experiments are conducted on standard MRI brain tissue dataset and ECG arrhythmia dataset. The results of MRI brain tissue segmentation are evaluated in terms of dice coefficient (DC) and those of ECG arrhythmia segmentation are evaluated based on accuracy. Results are then compared with state-of-the art methods. Experimental results show that the proposed method performs better compared to other existing methods.

Online publication date: Mon, 10-Feb-2020

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 Artificial Intelligence and Soft Computing (IJAISC):
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