Brain Tumor Classification from MRI Images: A Hybrid Approach with Pre-processing and Feature Extraction

DOI

10.2991/978-94-6239-674-6_27How to use a DOI?

Keywords

Brain Tumor Classification; CNN; RFC; hybrid model CNN-RFC; MRI

Abstract

The article proposes a framework of CNN and RFC to classify brain tumors by using MRI images, which combines CNN (Convolution Neural Networks) and RFC (Random forest classification). Pre-processing, Feature bring-out, and Categorization are the three phases of the proposed framework. We use the Gaussian Filter Method on the dataset then we combine the original dataset with processed data in parallel. The feature extraction of magnetic resonance imaging was performed automatically by CNN in the second step. Several classification algorithms, including RFC, KNN, D, SVM and NB, are used in theend. The extracted features from the CNN model are given to the classifier algorithms, which predict Glioma, Pituitary, Meningioma tumors, and no tumor as a result of the testing dataset. Experiments are carried out on an open dataset of images selected for classification from the Kaggle databases. A separate CSV file is maintained that contains testing images name and their specification. The proposed approach is able to achieve 99.61% accuracy on the training dataset, 92.16% on the validation data, and 71.2% on the CSV/testing data.

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  - Satyam Singh
AU  - Praveen Kumar Mohane
PY  - 2026
DA  - 2026/05/28
TI  - Brain Tumor Classification from MRI Images: A Hybrid Approach with Pre-processing and Feature Extraction
BT  - Proceedings of the International Conference on Sustainable Computing and Artificial Intelligence (ICSCAI 2025)
PB  - Atlantis Press
SP  - 313
EP  - 324
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6239-674-6_27
DO  - 10.2991/978-94-6239-674-6_27
ID  - Singh2026
ER  -