Intelligent Brain Tumor Diagnosis from MRI Images via Transfer Learning and Advance Feature Optimization Techniques

DOI

10.2991/978-94-6239-697-5_27How to use a DOI?

Keywords

Brain Tumor Classification; Magnetic Resonance Imaging (MRI); Transfer Learning; Deep Learning; Feature Optimization; Particle Swarm Optimization (PSO); Support Vector Machine (SVM); Medical Image Analysis; Computer-Aided Diagnosis (CAD); Convolutional Neural Networks (CNN)

Abstract

The accurate and timely detection of brain tumors is vital in enhancing the survival rate of patients suffering from these diseases. Manual analysis of brain Magnetic Resonance Imaging (MRI) data is tedious and may result in bias, particularly in resource-constrained environments. The current paper introduces an intelligent hybrid framework for effective brain tumor classification using deep transfer learning and feature optimization techniques. Convolutional neural networks, namely VGG16 and ResNet50, are applied to extract deep feature representations from contrast-enhanced T1-weighted MRI images of different classes of brain tumors. To avoid overfitting and optimize performance, Particle Swarm Optimization (PSO) is applied to select the most discriminative features from the deep feature representation. These features are then classified by applying a Support Vector Machine classifier to obtain 92.75% classification accuracy, enhanced precision, and ROC-AUC for different classes of brain tumors, namely glioma, meningioma, pituitary tumor, and absence of tumor. The suggested framework exhibits high performance in comparison to baseline frameworks that use unfiltered deep features for classification. The framework is also computationally efficient and may be applied in real-time environments for efficient and accurate diagnosis of brain tumors using MRI images.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Jastej Singh
AU  - Mandeep Kaur
AU  - Jobanpreet Singh
PY  - 2026
DA  - 2026/06/04
TI  - Intelligent Brain Tumor Diagnosis from MRI Images via Transfer Learning and Advance Feature Optimization Techniques
BT  - Proceedings of the Conference on Bridging Engineering Disciplines with AI and Machine Learning (BEDAIML 2026)
PB  - Atlantis Press
SP  - 323
EP  - 337
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6239-697-5_27
DO  - 10.2991/978-94-6239-697-5_27
ID  - Singh2026
ER  -