Open Access Open Access  Restricted Access Subscription or Fee Access

Multi Model MRI Brain Image Fusion Techniques and Graph Cut Segmentation

Padmanjali A. Hagargi, D.C Shubhangi


The need for advancement in medical imaging applications for tumor segmentation using fusion and level set segmentation is presented in this paper. The types of Magnetic Resonance Imaging (MRI) images utilized to segment brain tumor are T1 weighted, T2 weighted and proton density (PD) weighted images. These images are filtered (noise removal, if any) by Wiener filter. Image fusion is applied on these images to obtain high spatial and high spectral information in single fused image. Comparison between discrete wavelet transform (DWT) with curvelet transform based fusion and fuzzy based fusion is provided to achieve better results for segmenting tumor region. Fuzzy based fusion is performed by retaining the principal components of images using robust principal component analysis (RPCA) and Quadtree decomposition. Considering the fused image with high peak signal-to-noise ratio (PSNR) value and low root mean square error (RMSE) value, the image will be used for tumor segmentation. The objective of image segmentation is to group the pixels into important image regions i.e. regions matching to distinctive objects, surfaces, or natural parts of objects. Level set method is implemented in the current work to segment the tumor region effectively and reliably.


Brain Tumor, MRI Images, Image Fusion, Level Set Function, Image Segmentation

Full Text:



  • There are currently no refbacks.

Disclaimer/Regarding indexing issue:

We have provided the online access of all issues and papers to the indexing agencies (as given on journal web site). It’s depend on indexing agencies when, how and what manner they can index or not. Hence, we like to inform that on the basis of earlier indexing, we can’t predict the today or future indexing policy of third party (i.e. indexing agencies) as they have right to discontinue any journal at any time without prior information to the journal. So, please neither sends any question nor expects any answer from us on the behalf of third party i.e. indexing agencies.Hence, we will not issue any certificate or letter for indexing issue. Our role is just to provide the online access to them. So we do properly this and one can visit indexing agencies website to get the authentic information.