Title: Brain tumour segmentation using weighted k-means based on particle swarm optimisation

Authors: Naresh Pal

Addresses: Computer Science and Engineering Department, University du Québec en Outaouais, Gatineau, Quebec, Canada

Abstract: In medical science, image segmentation (IS) is a challenging task, it subdivides the image into mutually exclusive regions. An IS is the most fundamental and essential process of classification, description and visualisation of the region of interest in several medical images. In the medical field, diagnosis of brain and other medical images are using magnetic resonance imaging (MRI), which is a very helpful diagnostic tool. The traditional technique using MRI brain tumour segmentation (BTS) is extremely time consuming task. This research paper concentrates on the improved medical IS method based on hybrid clustering methods. This hybrid technique is a combination of weighted k-means and fuzzy C-means (WKFCM), K-means and particle swarm optimisation (KPSO). The proposed techniques, identify the brain tumour accurately with less execution time. An experimental result demonstrated that proposed hybrid clustering technique performance is better than the earlier methods like FCM, KM, mean shift (MS), expectation maximisation, and PSO in three different benchmark brain databases.

Keywords: weighted K-means; fuzzy C-means; image segmentation.

DOI: 10.1504/IJAIP.2024.139955

International Journal of Advanced Intelligence Paradigms, 2024 Vol.28 No.1/2, pp.128 - 142

Received: 14 Apr 2018
Accepted: 02 Jun 2018
Published online: 15 Jul 2024 *

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