期刊名称:International Journal of Innovative Research in Computer and Communication Engineering
印刷版ISSN:2320-9798
电子版ISSN:2320-9801
出版年度:2016
卷号:4
期号:3
页码:3385
DOI:10.15680/IJIRCCE.2016.0403118
出版社:S&S Publications
摘要:Functional magnetic resonance imaging (fMRI) provides the potential to study brain function in a non - invasive way. Massive in volume and complex in terms of the information content, fMRI data requires effective and efficient data mining techniques. This paper describes the approach for detection and extraction brain tumour from fMRI scan images of brain. To understand the complex interaction patterns, among brain regions we propose a novel clustering called interact ion K - means (IKM), an efficient algorithm for partitioning clustering. The segmentation based on F - transform (Fuzzy - Transform) and morphological operations are performed to delineating the brain tumour boundaries and to calculate the area of the tumour. Th e F - transform is a professional intelligent method to handle uncertain information and to extract the salient edges and morphological operation helps to find the size of tumour and hence the severity can be diagnosed. The experimental results showed that t he proposed algorithm produces perfectly accurate performance to brain tumour detection for fMRI brain images