Supervised Classification Approaches for Brain Tumour Classification Using Fused Wavelet Features

Authors

  • Shailendra Kumar Mishra
  • Hiran Kumar Singh

DOI:

https://doi.org/10.37506/ijfmt.v15i2.14943

Keywords:

Brain tumour, wavelet transforms, supervised classification, k-nearest neighbourand naive Bayes.

Abstract

In this study, an efficient pattern recognition technique is developed for Brain Image Classification (BIC) into
normal or abnormal. Wavelet transform features with supervised classification have a potential role to play
in bringing Magnetic resonance Images (MRI) of the brain into practical clinical use.The developed pattern
recognition technique uses Discrete Wavelet Transform (DWT), Dual tree M-band Wavelet Transform
(DMWT), and Stationary Wavelet Transform (SWT) for feature extraction, k-Nearest Neighbour (kNN)
and Naive Bayes (NB) for classification and is considered as an effective and accurate tool for brain image
analysis for cancer classification. Also, the predominant coefficients are chosen from the combined feature
space by rank features of statistical feature selection approach. Results show that the proposed system acts
as a pre-treatment predictor for BIC with an accuracy of 88.5% for kNN and 95.5% for NB classification.

Author Biographies

  • Shailendra Kumar Mishra

    Research Scholar

  • Hiran Kumar Singh

    Associate professor, Department of Electronics and Communication Engineerin , VelTech
    Rangarajan Dr. Sagunthala R&D Institute of Science and Technology, Chennai, Tamil Nadu, India

Downloads

Published

2021-03-24

How to Cite

Supervised Classification Approaches for Brain Tumour Classification Using Fused Wavelet Features. (2021). Indian Journal of Forensic Medicine & Toxicology, 15(2), 3659-3664. https://doi.org/10.37506/ijfmt.v15i2.14943