TELKOMNIKA Telecommunication Computing Electronics and Control
Support vector machine based discrete wavelet transform for magnetic resonance imaging brain tumor classification

TELKOMNIKA Telecommunication Computing Electronics and Control
Support vector machine based discrete wavelet transform for magnetic resonance imaging brain tumor classification

Discrete wavelet transform
Image classification
MRI image
Support vector machine

Here, a brain tumor classification method using the support vector machine
(SVM) algorithm by utilizing discrete wavelet transform (DWT)
transformation and feature extraction of gray-level co-occurrence matrix
(GLCM) and local binary pattern (LBP) has been implemented using the
magnetic resonance imaging (MRI) image belong to the low-grade glioma
(LGG) or high-grade glioma (HGG) group. SVM algorithm used as a
classification method has been widely used in research that raises the topic
of classification. Through the formation of a hyperplane between 2 data
classes, the SVM algorithm can be said to be a reliable method but does not
require complicated computations. The DWT transformation is intended to
provide clearer feature details from the MRI image, so that when the feature
extraction algorithm is applied, it is expected that the extracted features will
differ between benign tumor MRI images and malignant tumor MRI images.
In 1 level DWT using high-low (HL) sub-band yield the highest specificity,
sensitivity, and accuracy than using 3 levels using HL or low-high (LH)
sub-band in LGG MRI image. Compared with another research, our
proposed method is slightly better in terms of accuracy to classify the brain
tumor image with achieved the accuracy of 98.6486%.

Ajib Susanto, Christy Atika Sari, Hidayah Rahmalan, Mohamed A. S. Doheir

http://telkomnika.uad.ac.id

Aug 25, 2021

peri irawan

pdf

english

text