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%.
%0 Journal Article
%1 wedad_abdul_khuder_naser_2021_5011609
%A Naser, Wedad Abdul Khuder
%A Kadim, Eman Abdulmunem
%A Abbas, Safana Hyder
%D 2021
%J Global Journal of Engineering and Technology Advances
%K Brain tumors
%N 2
%P 026-036
%R 10.30574/gjeta.2021.7.2.0065
%T SVM Kernels comparison for brain tumor diagnosis using MRI
%U https://gjeta.com/content/svm-kernels-comparison-brain-tumor-diagnosis-using-mri
%V 7
%X 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%.
@article{wedad_abdul_khuder_naser_2021_5011609,
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%.},
added-at = {2021-06-25T05:38:18.000+0200},
author = {Naser, Wedad Abdul Khuder and Kadim, Eman Abdulmunem and Abbas, Safana Hyder},
biburl = {https://www.bibsonomy.org/bibtex/2f28aa46cce46aa80d7f4cc0be27993ec/gjetajournal},
doi = {10.30574/gjeta.2021.7.2.0065},
interhash = {3835476c8e0f8ba726dfb1ee705976a8},
intrahash = {f28aa46cce46aa80d7f4cc0be27993ec},
issn = {2582-5003},
journal = {{Global Journal of Engineering and Technology Advances}},
keywords = {Brain tumors},
month = may,
number = 2,
pages = {026-036},
timestamp = {2021-06-25T05:38:18.000+0200},
title = {SVM Kernels comparison for brain tumor diagnosis using MRI},
url = {https://gjeta.com/content/svm-kernels-comparison-brain-tumor-diagnosis-using-mri},
volume = 7,
year = 2021
}