Indonesian Journal of Electrical Engineering and Computer Science Vol. 32, No. 1, October 2023, pp. 216~226 ISSN: 2502-4752, DOI: 10.11591/ijeecs.v32.i1.pp216-226  216 Journal homepage: http://ijeecs.iaescore.com Segmentation of brain tissue using improved kernelized rough- fuzzy c-means technique Hiyam Hatem Jabbar, Raed Majeed Muttasher, Ali Fattah Dakhil Department of Information System, Collage of Computer Science and Information Technology, University of Sumer, DhiQaar, Iraq Article Info ABSTRACT Article history: Received Nov 13, 2022 Revised Apr 17, 2023 Accepted Jun 17, 2023 Brain magnetic resonance imaging (MRI) data is a hot topic in the domains of biomedical engineering and machine learning. Without locating anomalies, such as tumors and edema, radiologists and other medical experts cannot effectively recommend or administer therapy for patients. Having three different magnetic resonance techniques (T1 weighted, T2 weighted, and T3 weighted), MRI can produce detailed multimodal scans of different human brain tissues with varying contrast, which can help pinpoint the source of any abnormalities. The cerebrospinal fluid (CSF), white matter (WM), and grey matter (GM) are all components of the brain, and their boundaries are sometimes hazy and difficult to nail down. In light of the problems above, this paper makes an effort to tackle issues like: i) the noise that exists in the brain datasets for MRI, ii) the fuzziness, uncertainty, overlap, indiscernibility of complex brain tissue regions, iii) the inability of traditional unsupervised methods to reliably distinguish between various brain tissue locations, and iv) ineffective performance. We propose some robust techniques by utilise spatial contextual data, a rough set, a fuzzy set, and ultimately a fuzzy set to steer the clustering process in a better direction, allowing it to deal with likely noise, outliers, and other artifacts. Keywords: Brain MRI Brain tumor Fuzzy set Image segmentation KRFCM algorithm Spatial information This is an open access article under the CC BY-SA license. Corresponding Author: Hiyam Hatem Jabbar Department of Information System, Collage of Computer Science and Information Technology University of Sumer DhiQaar, Iraq Email: hiamhatim2005@gmail.com 1. INTRODUCTION The segmentation of brain tissue is a crucial step in medical image analysis, allowing for the detection and diagnosis of various neurological disorders. However, accurate segmentation of brain tissue from the difficulty of magnetic resonance imaging (MRI) is attributed to tissue heterogeneity and the presence of noise, bias fields, and partial volume effects [1]. Automated segmentation methods can improve accuracy and efficiency, but there is a need for further improvement in their performance. The brain, or cerebrum, consists of two hemispheres, the left and right, as seen in Figure 1. The cerebellum’s primary roles are in motor control and equilibrium [2]. The cerebrum is responsible for most mental processes, including vision, hearing, interpretation, and learning, emotion, reasoning, and speaking [3]. The cerebellum is a small brainstem-like structure located just below the cerebral cortex. In contrast, white matters (WM) are the network of long nerve cells that link the various regions of the brain. Cerebrospinal fluid (CSF) is a transparent fluid that constantly circulates through the brain and spinal cord. Protecting the brain from harm, CSF also transports glucose, oxygen, and other substances from the blood [4]. The WM is the primary signalling system for bidirectional information transfer across the brain hemispheres. The human brain is vertically divided into front and rear in the plane of the face as show in Figure 2, a split known as the coronal