期刊名称：International Journal of Computer Science and Information Technologies
电子版ISSN：0975-9646
出版年度：2012
卷号：3
期号：3
页码：4176-4181
出版社：TechScience Publications
摘要：In this paper, we are present the efficient technique for the segmentation of normal, abnormal with tumor and edema tissues in the MR brain images. The normal brain tissues such as WM (White Matter), GM (Gray Matter) and CSF (Cerebrospinal Fluid) are segmented by using classical approach like gradient and binarization methods. In medical diagnosis it is very important to identify tissues which are infected and same equal importance to the tissues with are going to be damaged in due time like edema tissues. In this process of segmentation preprocessing is applied to eliminate non-cortical tissues using skull stripping with region growing method for a better focus on cortical tissues. The proposed method shows the best cortical tissue segmentation compare with the existing techniques. The same approached can also be used for efficient segment in noisy conditions using non-linear Adaptive Wiener filter. Performance of the proposed approach is compared against the Weiner filter and adaptive Weiner filter in terms of peak-signal-to-noise-ratio (PSNR) and Mean squared error (MSE) on real MR images collected from national brain research centre.
