Indian Journal of Science and Technology

Abstract

Background/Objectives: In recent years, medical imaging plays an important role to detect diseases. Especially, Magnetic Resonance Imaging (MRI) images are indispensable for tumor detection. In medical image processing, the Region Based Segmentation (RBS) algorithms have attained an essentially significance to detect the tumor and are utilized for optimum results with the segregation of tumor part in the MRI image. The aim of the work is to provide effective algorithm to extract tumor and size, the process of de-noising technique, segmentation and extraction is the best way for this. At first, the enhanced de-noising method helps to enhance the MRI image to extract the tumor alone. Methods/Statistical Analysis: In image processing, automatic image segmentation plays a vital role and for RBS, the selection of seed has to done automatically to achieve this. Even if this technique is well performed with noises, the images are difficult to segment due to pixel similarity and the presence of noise. The noises can be removed by the combinations of median and Stationary Wavelet Transform (SWT) before preceding this, contrast enhancement is needed. In this paper, the combined features of de-noising technique are used for minimizing the effect of noises in the MRI brain images. After the process of denoising, the segmented results will be a better one than non-de-noise (i.e. Original) images. The extracted tumor results are compared by the various quality metrics as MSE, PSNR, NCC, AD, NAE, SE etc. with the ground truth image. This enhanced de-noising technique is used to test 50 images and is performance evaluated based on their MSE and PSNR. Findings: The enhanced de-noising technique gives better result than existing de-noising technique. Thus, the tumor extraction can be done easily. Improvements/Applications: This technique is used mainly for medical imaging applications. 

Keywords: Image De-noising, Image Segmentation, Median Filter, MRI, Region Based Segmentation, Stationary Wavelet Transform