Archives
International Journal of Zoology and Applied Biosciences Review Article
Support vector machine based approaches for MRI image segmentation: A systematic review
Jeeva V, Rubala Nancy J, Devasena B, Madhumitha N and Linisha NM
Year : 2025 | Pages: 576-580
Received on: 27/09/2025
Revised on: 22/10/2025
Accepted on: 25/11/2025
Published on: 01/12/2025
-
Jeeva V, Rubala Nancy J, Devasena B, Madhumitha N and Linisha NM( 2025).
Support vector machine based approaches for MRI image segmentation: A systematic review
. International Journal of Zoology and Applied Biosciences, 10( 6), 576-580.
-
click to view the cite format
Abstract
Magnetic Resonance Imaging (MRI) segmentation plays a pivotal role in computer-aided diagnosis, surgical planning, and disease monitoring. Despite the rise of deep learning–based methods, Support Vector Machine (SVM) models continue to be widely adopted due to their strong generalization ability, robustness with limited training data, and effectiveness in high-dimensional feature spaces. This systematic review presents a comprehensive analysis of SVM-based approaches used for MRI image segmentation across various medical applications, including brain tumor detection, multiple sclerosis lesion identification, tissue classification, and organ delineation. Relevant studies published over the past decade were examined to assess preprocessing techniques, feature engineering strategies, kernel functions, optimization methods, evaluation metrics, and comparative performance. The findings indicate that hybrid SVM models combining wavelet features, texture descriptors, probabilistic frameworks, and evolutionary optimization consistently outperform classical SVM variants. Moreover, SVM remains highly competitive in scenarios with limited annotated datasets and complex multimodal MRI sequences. The review highlights existing challenges such as feature dependency, computational overhead, and lack of standardized datasets, while emphasizing future research directions including automated feature extraction, kernel adaptation, and integration with deep learning architectures. Overall, this study provides an organized understanding of SVM-centered MRI segmentation strategies, enabling researchers to identify suitable approaches for clinical and research applications.
Keywords
Support Vector Machine (SVM), MRI Image Segmentation, Medical Image Processing.
-
Full Article PDF (
26)
- 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.
