Open Access

ARTICLE

An Efficient Explainable AI Model for Accurate Brain Tumor Detection Using MRI Images

Fatma M. Talaat^1,2,*, Mohamed Salem¹, Mohamed Shehata^3,4,*, Warda M. Shaban⁵

1 Faculty of Artificial Intelligence, Kafrelsheikh University, Kafrelsheikh, 33516, Egypt
2 Faculty of Computer Science & Engineering, New Mansoura University, Gamasa, 35712, Egypt
3 Department of Bioengineering, Speed School of Engineering, University of Louisville, Louisville, KY 40292, USA
4 Computers and Control Systems Engineering Department, Faculty of Engineering, Mansoura University, Mansoura, 35516, Egypt
5 Communications and Electronics Engineering Department, Nile Higher Institute for Engineering and Technology, Mansoura, 35511, Egypt

* Corresponding Authors: Fatma M. Talaat. Email: ; Mohamed Shehata. Email:

(This article belongs to the Special Issue: Recent Advances in Signal Processing and Computer Vision)

Computer Modeling in Engineering & Sciences 2025, 144(2), 2325-2358. https://doi.org/10.32604/cmes.2025.067195

Received 27 April 2025; Accepted 08 July 2025; Issue published 31 August 2025

Abstract

The diagnosis of brain tumors is an extended process that significantly depends on the expertise and skills of radiologists. The rise in patient numbers has substantially elevated the data processing volume, making conventional methods both costly and inefficient. Recently, Artificial Intelligence (AI) has gained prominence for developing automated systems that can accurately diagnose or segment brain tumors in a shorter time frame. Many researchers have examined various algorithms that provide both speed and accuracy in detecting and classifying brain tumors. This paper proposes a new model based on AI, called the Brain Tumor Detection (BTD) model, based on brain tumor Magnetic Resonance Images (MRIs). The proposed BTC comprises three main modules: (i) Image Processing Module (IPM), (ii) Patient Detection Module (PDM), and (iii) Explainable AI (XAI). In the first module (i.e., IPM), the used dataset is preprocessed through two stages: feature extraction and feature selection. At first, the MRI is preprocessed, then the images are converted into a set of features using several feature extraction methods: gray level co-occurrence matrix, histogram of oriented gradient, local binary pattern, and Tamura feature. Next, the most effective features are selected from these features separately using Improved Gray Wolf Optimization (IGWO). IGWO is a hybrid methodology that consists of the Filter Selection Step (FSS) using information gain ratio as an initial selection stage and Binary Gray Wolf Optimization (BGWO) to make the proposed method better at detecting tumors by further optimizing and improving the chosen features. Then, these features are fed to PDM using several classifiers, and the final decision is based on weighted majority voting. Finally, through Local Interpretable Model-agnostic Explanations (LIME) XAI, the interpretability and transparency in decision-making processes are provided. The experiments are performed on a publicly available Brain MRI dataset that consists of 98 normal cases and 154 abnormal cases. During the experiments, the dataset was divided into 70% (177 cases) for training and 30% (75 cases) for testing. The numerical findings demonstrate that the BTD model outperforms its competitors in terms of accuracy, precision, recall, and F-measure. It introduces 98.8% accuracy, 97% precision, 97.5% recall, and 97.2% F-measure. The results demonstrate the potential of the proposed model to revolutionize brain tumor diagnosis, contribute to better treatment strategies, and improve patient outcomes.

---

Keywords

---