Authors: S.V. Aruna Kumar; B.S. Harish; P. Shivakumara
Addresses: Department of Information Science and Engineering, Sri Jayachamarajendra College of Engineering, Mysuru, India ' Department of Information Science and Engineering, Sri Jayachamarajendra College of Engineering, Mysuru, India ' Faculty of Computer Science and Information Technology, University of Malaya, Kuala Lumpur, Malaysia
Abstract: Segmenting region of interest in medical images is challenging because medical image suffers from noise, degradation due to environment influence and low resolution due to devices, etc. In this paper, we have developed a novel idea based on weighted spatial kernel FCM clustering for segmenting region of interest in the medical images. Unlike traditional methods which ignore spatial information, we propose a new robust system that explores spatial information to remove uncertainty in identifying accurate region in the medical images. Furthermore, the proposed method estimates the weights for spatial information to derive precise membership function to segment the region based on Gaussian kernel as distance metric. We conducted experiments on standard datasets, namely MRI Brian image dataset and evaluated performance of the proposed method using recall, precision and f-measure. Experimental results reveal that, the proposed method performs better compared to existing methods.
Keywords: clustering; fuzzy C-means; medical images; segmentation.
International Journal of Computational Intelligence Studies, 2018 Vol.7 No.1, pp.33 - 66
Received: 03 Nov 2016
Accepted: 26 Jun 2017
Published online: 22 Feb 2018 *