Hybrid kernel fuzzy C-means clustering segmentation algorithm for content based medical image retrieval application
by Lakshmana; Sunil Kumar S. Manvi; K.G. Karibasappa
International Journal of Bioinformatics Research and Applications (IJBRA), Vol. 17, No. 6, 2021

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.

Online publication date: Tue, 25-Jan-2022

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 Bioinformatics Research and Applications (IJBRA):
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