The PDF file you selected should load here if your Web browser has a PDF reader plug-in installed (for example, a recent version of Adobe Acrobat Reader).

If you would like more information about how to print, save, and work with PDFs, Highwire Press provides a helpful Frequently Asked Questions about PDFs.

Alternatively, you can download the PDF file directly to your computer, from where it can be opened using a PDF reader. To download the PDF, click the Download link above.

Fullscreen Fullscreen Off

Objectives: The objective of this work is to study denoising and segmentation methods to extract brain tumor area from the MRI image, implemented using MATLAB2013b and to examine its performance metrics. Methods/Statistical Analysis: As preprocessing stage is essential for better segmentation as it removes noise that makes images having similar qualities so that tumor area can be shown and extracted with great accuracy. An anisotropic diffusion filter with 8-connected neighborhood is employed for noise removal and Fast Bounding Box (FBB) for exactly showing tumor area on MRI images. Finally Support vector machine classifies the boundary and extracts the tumor from the MRI image. Findings: Brain tumor is the major cause of cancer deaths in human which is due to uncontrollable cells growth in brain portion. Prior detection, diagnosis and accurate healing of brain tumor are the primary work to prevent human death. Image segmentation can also be done in several approaches like thresholding, region growing, watersheds and contours. Specialists with their basic knowledge do manual segmentation, which is time consuming process, where this limitation can be overcome by our fully automatic proposed method. Employing of an isotropic diffusion filter with 8-connected neighborhood compare to 4-connected neighborhood results in considerable improvements in terms of lower identical error rates. Our proposed Fast Bounding Box (FBB) method is applied that exactly shows tumor area on MRI images and its central region is selected judiciously to have sample points required for functionality of one class SVM classifier training. To achieve optimal classification level there is necessity of SVM with optimum efficiency, so that we adapted Support vector machine that immediately stops its operation once all the points are separated. Application/Improvements: Segmented tumor obtained with precision are very useful for radiologists and specialists to had good idea of estimating tumor position and size with great dealt with ease and without any prior information.


Brain Tumor, Feature Extraction, Fast Bounding Box, MRI, Support Vector Machine, Tumor Extraction.