Archives


International Journal of Zoology and Applied Biosciences Research Article

Advanced brain tumor detection through MRI image fusion and SVM-based segmentation

Rajeswari M, Sindhu D, Swathi T, Tehseen Javed and Linisha N M

Year : 2025 | Pages: 527-530

doi: https://doi.org/10.55126/ijzab.2025.v10.i06.SP107

Received on: 26/09/2025

Revised on: 23/10/2025

Accepted on: 24/11/2025

Published on: 01/12/2025

  • Rajeswari M, Sindhu D, Swathi T, Tehseen Javed and Linisha N M( 2025).

    Advanced brain tumor detection through MRI image fusion and SVM-based segmentation

    . International Journal of Zoology and Applied Biosciences, 10( 6), 527-530.

  • click to view the cite format


Abstract

Medical image fusion has become an essential technique in clinical diagnosis, particularly for detecting brain tumors. Fusion integrates complementary information from multiple medical images into a single enhanced image, improving visibility, reducing uncertainty, and retaining diagnostically significant features. In this study, two MRI images with different characteristics are fused to obtain a more informative composite image. Texture and wavelet features extracted from the fused image are used to train and test a Support Vector Machine (SVM) classifier for tumor identification. Preprocessing, median filtering, feature extraction using K-means clustering, and threshold-based segmentation are employed to refine tumor regions. The proposed method effectively discriminates between benign and malignant tumors, achieving 80.48% sensitivity, 99.9% specificity, and 99.69% classification accuracy. Experimental results demonstrate that the introduced fusion and SVM-based segmentation approach outperforms conventional fusion techniques and provides superior diagnostic support for radiologists.

Keywords

Brain tumor detection, MRI fusion, Image segmentation, SVM classifier, K-means clustering.

  • Full Article PDF ( 9)

  • View HTML Article
  • Copy Rights

    © The Author(s) 2025. This article is published by International Journal of Zoology and Applied Biosciences under the terms of the Creative Commons Attribution 4.0 International License (creativecommons.org), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.