Enhanced N-Cut and Watershed based Model for Brain MRI Segmentation 
Naresh Ghorpade1, H. R. Bhapkar2
1Naresh Ghorpade*, Department of Mathematics, MIT School of Engineering, MITADT University, Loni Kalbhor, Pune – 412201, Maharashtra, India.
2H. R. Bhapkar, Department of Mathematics, MIT School of Engineering, MITADT University, Loni Kalbhor, Pune, Maharashtra, India.
Manuscript received on April 11, 2020. | Revised Manuscript received on May 25, 2020. | Manuscript published on June 30, 2020. | PP: 346-351 | Volume-9 Issue-5, June 2020. | Retrieval Number: E9535069520/2020©BEIESP | DOI: 10.35940/ijeat.E9535.069520
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Segmentation of an image is most important and essential task in medical image processing, specifically while analyzing magnetic resonance (MR) image of brain clinically. during the clinical investigation of brain MRI images. Lot of research has been carried out for MRI segmentation but still it is challenging task. Hybrid approach which uses enhanced normalized cut and watershed transform to segment brain MRI images is developed in this paper. Watershed transform is used for the initial partitioning of the MRI, which creates primitive regions. In the next stage these primitive regions resembled for graph depiction and then the normalized cut method is used for segmenting an image. Variety of simulated and actual MR images are being segmented by using proposed algorithm to test its efficiency, in addition to it segmentation results are also compared with the other available techniques of brain MRI segmentation.
Keywords: Brain MRI Segmentation, Watershed Transform, Graph Partitioning, Normalized Cut.