Article: Segmenting ECG and MRI data using ant colony optimisation Journal: International Journal of Artificial Intelligence and Soft Computing (IJAISC) 2019 Vol.7 No.1 pp.46 - 58 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. Inderscience Publishers - linking academia, business and industry through research

Title: Segmenting ECG and MRI data using ant colony optimisation

Authors: C.K. Roopa; B.S. Harish; S.V. Aruna Kumar

Addresses: Department of Information Science and Engineering, JSS Research Foundation, JSS TI Campus, Mysuru, India ' Department of Information Science and Engineering, JSS Research Foundation, JSS TI Campus, Mysuru, India ' Socia-lab University Beira Interior, Convento de Sto. Antonio, Covilha, Portugal

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.

Keywords: segmentation; ECG; MRI; intuitionistic fuzzy C-means; ant colony optimisation; ACO.

DOI: 10.1504/IJAISC.2019.105020

International Journal of Artificial Intelligence and Soft Computing, 2019 Vol.7 No.1, pp.46 - 58

Received: 28 Jan 2019
Accepted: 08 Aug 2019
Published online: 10 Feb 2020 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

Title: Segmenting ECG and MRI data using ant colony optimisation

Keep up-to-date