Title: Hybrid kernel fuzzy C-means clustering segmentation algorithm for content based medical image retrieval application

Authors: Lakshmana; Sunil Kumar S. Manvi; K.G. Karibasappa

Addresses: Department of Computer Science and Engineering, Reva University, Bengaluru, Karnataka, 560064, India ' School of Computing and Information Technology, Reva University, Bengaluru, Karnataka, 560064, India ' School of Computer Science and Engineering, KLE Technological University, Hubballi, Karnataka, 580031, India

Abstract: Nowadays, many therapeutic images are generated highly because of a number of patients' daily medical activities. Retrieving these images from the huge dataset is a challenging task, hence content based medical image retrieval (CBMIR) system is used. Clustering based segmentation for diagnosing the query image was proposed by existing retrieval system. In this research paper, Hybrid Bee Colony and Cuckoo Search (HBCCS) based Kernel Fuzzy C-Means clustering (KFCM) is proposed to segment the images. But, the major drawback of the conventional KFCM is initialisation of centroids random that leads to rise of execution time for the optimal solution. Therefore, HBCSS is utilised to initialise the centroids of required clusters. The number of iterations and processing of HBCCS technique takes least value while contrasted with conventional KFCM. The proposed technique is efficient and faster than existing KFCM for segmenting the images in terms of 55.27% specificity, 99.41% sensitivity and 96% accuracy.

Keywords: bee colony; centroids; clustering; cuckoo search; diagnosing; execution time; fuzzy C-means; medical image retrieval; segmentation; therapeutic images.

DOI: 10.1504/IJBRA.2021.120534

International Journal of Bioinformatics Research and Applications, 2021 Vol.17 No.6, pp.496 - 511

Received: 15 Apr 2019
Accepted: 13 Sep 2019
Published online: 25 Jan 2022 *

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