Title: Performance evaluation of optimised SVM for classification of brain tumour

Authors: Arun Kumar; M.A. Ansari; Alaknanda Ashok

Addresses: Department of Computer Science and Engineering, Uttrakhand Technical University, Dehradun, India ' Department of Electrical Engineering, Gautam Buddha University, Greater Noida, Uttar Pradesh, India ' G.B. Pant University of Agriculture and Technology, Pantnagar, Uttarakhand, India

Abstract: In today's scenario, machine learning tools are most widely used for the classification of images in the field of medical science. Support vector machine (SVM) is one of the most popular and highly used for such classifications. Further, such classifications are highly related to the number of features selected from any medical image. The computation time and the memory required for the successful implementation of any classification tool is directly dependent on the number of features. So, in order to get the more accurate classification results, the features of the medical image must be optimised. The present study mainly aims on the development of an improved classification technique by combining some optimisation approaches. In this study, SVM is implemented for the classification of the brain tumour by optimising the features of the magnetic resonance imaging (MRI) using three different optimisation approaches namely, particle swarm optimisation, grey wolf optimisation and firefly algorithm. The results obtained from this study depict that SVM along with the grey wolf optimisation provides more accurate classification of the brain tumour with an accuracy of 96.8% ± 2 in comparison to particle swarm optimisation and firefly optimisation with an accuracy of 93% ± 2 and 85% ± 5 respectively.

Keywords: brain tumour; magnetic resonance image; MRI; classification; feature optimisation; SVM.

DOI: 10.1504/IJMEI.2022.125317

International Journal of Medical Engineering and Informatics, 2022 Vol.14 No.5, pp.439 - 453

Received: 17 Aug 2020
Accepted: 06 Dec 2020

Published online: 07 Sep 2022 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article