Segmentation of brain tissue using improved kernelized rough-fuzzy c-means technique

<p><span>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 edema, radiologists other medical experts cannot effectively recommend or administer therapy for patients. Having three different techniques (T1 weighted, T2 T3 weighted), MRI can produce detailed multimodal scans human brain tissues with varying contrast, which help pinpoint source any abnormalities. The cerebrospinal fluid (CSF), white matter (WM), grey (GM) are all components brain, their boundaries sometimes hazy difficult to nail down. In light problems above, this paper makes an effort tackle issues like: i) noise that exists datasets MRI, ii) fuzziness, uncertainty, overlap, indiscernibility complex tissue regions, iii) inability traditional unsupervised methods reliably distinguish between various locations, iv) ineffective performance. We propose some robust by utilise spatial contextual data, rough set, fuzzy ultimately set steer clustering process better direction, allowing it deal likely noise, outliers, artifacts.</span></p>