• C.KIRUBAKARAN
• N.SENTHILKUMARAN

Medical imaging is uniting of the most complicated and challenging applications of image processing domain. Magnetic Resonance Images (MRI) carry on a notable role in the identification of the disease using computerized examination. The Segmentation process is detection and extraction of an abnormal area of MRI brain image significant. But the process is accurate and time-consuming when the radiologist has more experience in the relevant field. To resolve these complexities, a computerized analysis is required. An efficient tumor extraction method is proposed in this work to improve the performance. The proposed method worked Susan interest point detection for region growing and optimization of the region based on the intensity based regions optimization of the tumor. Modified Median filter, contrast stretching and skull stripping are employed as the preprocessing for the proposed work. The experimental results of proposed technique have been evaluated and validated for performance on magnetic resonance brain images, based on Similarity, Hausdorff distance, Dice and Jaccard. The experimental results achieved better shows the improvement in abnormal tissues, among given MRI images in terms of Segmentation, extraction is compared with existing methods.

MRI, interest point detection, region growing, Hausdorff distance, tumor extraction.

"MENINGIOMA BRAIN TUMOR EXTRACTION IN MRI IMAGE USING INTEREST POINT GENERATION AND REGION OPTIMIZATION", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 5, page no.12-21, May-2019, Available :http://www.jetir.org/papers/JETIRBM06003.pdf

"MENINGIOMA BRAIN TUMOR EXTRACTION IN MRI IMAGE USING INTEREST POINT GENERATION AND REGION OPTIMIZATION", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 5, page no. pp12-21, May-2019, Available at : http://www.jetir.org/papers/JETIRBM06003.pdf