A novel enhancement-based rapid kernel-induced intuitionistic fuzzy c-means clustering for brain tumor image

Soft clustering techniques are extensively used for segmenting medical images, and in particular, fuzzy c-means (FCM) clustering is employed to cluster the distinctive regions of the medical image. Specifically, a special attention is needed for the segmentation of brain tumor MR images, since it ha...

Full description

Saved in:
Bibliographic Details
Published in:Soft computing (Berlin, Germany) Germany), 2024-05, Vol.28 (9-10), p.6657-6670
Main Authors: Lavanya, K. G., Dhanalakshmi, P., Nandhini, M.
Format: Article
Language:English
Subjects:
Accuracy
Algorithms
Application of Soft Computing
Artificial Intelligence
Brain
Brain cancer
Clustering
Computational Intelligence
Control
Engineering
Experiments
Fuzzy sets
Image enhancement
Image reconstruction
Image segmentation
Magnetic resonance imaging
Mathematical Logic and Foundations
Mechatronics
Medical imaging
Medical research
Robotics
Tumors
Uncertainty
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Soft clustering techniques are extensively used for segmenting medical images, and in particular, fuzzy c-means (FCM) clustering is employed to cluster the distinctive regions of the medical image. Specifically, a special attention is needed for the segmentation of brain tumor MR images, since it has more uncertainties. To cope with this impreciseness, intuitionistic fuzzy c-means (IFCM) clustering is utilized which improves the accuracy in segmentation. In this framework, a new approach of clustering brain tumor MR image is proposed to segment brain tumor image. Initially, a novel intuitionistic fuzzy generator (IFG) is derived and the input image is enhanced using it to remove uncertainties. Then, kernel distance-based intuitionistic fuzzy c-means clustering is executed for gray-level histogram of the morphologically reconstructed intuitionistic fuzzy image (IFI). Finally, extensive experiment is conducted for the proposed method and other state-of-the-art methods in clustering to show the efficacy of the proposed method.
ISSN:1432-7643
1433-7479
DOI:10.1007/s00500-023-09533-7