SVM Kernels comparison for brain tumor diagnosis using MRI

Wedad Abdul Khuder Naser; Eman Abdulmunem Kadim; Safana Hyder Abbas

doi:10.30574/gjeta.2021.7.2.0065

Research & review articles are invited for publication in September 2026 (Vol. 28, Issue 3) || Submission: up to 28^th September || Editorial decision: within 48 hrs.

SVM Kernels comparison for brain tumor diagnosis using MRI

Wedad Abdul Khuder Naser ^*, Eman Abdulmunem Kadim and Safana Hyder Abbas

Department of computer science, University Al Mustansiriyah, Baghdad, Iraq.

Research Article

Global Journal of Engineering and Technology Advances, 2021, 07(02), 026-036.

Article DOI: 10.30574/gjeta.2021.7.2.0065

DOI url: https://doi.org/10.30574/gjeta.2021.7.2.0065

Publication history

Received on 30 March 2021; revised on 02 May 2021; accepted on 05 May 2021

Abstract

Magnetic Resonance Image (MRI) brain images have an essential role in medical analysis and cancer identification .In this paper multi kernel SVM algorithm is used for MRI brain tumor detection. The proposed work is involving the following stages: image acquisition, image preprocessing, feature extraction and tumor classification. An automatic threshold selection region based segmentation method called Otsu is used for thresholding during preprocessing stage. SVM classification algorithm with four different kernels are used to determine the normal and abnormal images. SVM with quadratic kernel results in best classification accuracy of 86.5%.

Keywords

Brain tumors; Support vector machine; Kernels; Image processing; Magnetic Resonance Image (MRI)

Download Article PDF

https://gjeta.com/sites/default/files/fulltext_pdf/GJETA-2021-0065.pdf

Preview Article PDF

How to cite this article

Wedad Abdul Khuder Naser, Eman Abdulmunem Kadim and Safana Hyder Abbas. SVM Kernels comparison for brain tumor diagnosis using MRI. Global Journal of Engineering and Technology Advances, 2021, 7(2), 026-036. Article DOI: https://doi.org/10.30574/gjeta.2021.7.2.0065

Copyright © Author(s). All rights reserved. This article is published under the terms of the Creative Commons Attribution 4.0 International License (CC BY 4.0), which permits use, sharing, adaptation, distribution, and reproduction in any medium or format, as long as appropriate credit is given to the original author(s) and source, a link to the license is provided, and any changes made are indicated.

All statements, opinions, and data contained in this publication are solely those of the individual author(s) and contributor(s). The journal, editors, reviewers, and publisher disclaim any responsibility or liability for the content, including accuracy, completeness, or any consequences arising from its use.