An Advanced XAI Framework for MRI-Based Glioma Classification Using Vision Transformer and CNN-Based Approaches

Hana Charaabi; Ridha El Hamdi; Mohamed Njah; Rachid Jennane; Fatma Kolsi; Mohamed Zaher Boudawara

doi:10.48084/etasr.13716

Authors

Hana Charaabi Laboratory of Advanced Technologies for Medicine and Signals, National Engineering School of Sfax, University of Sfax, Tunisia | Digital Research Center of Sfax, Technopole of Sfax, Tunisia
Ridha El Hamdi Laboratory of Advanced Technologies for Medicine and Signals, National Engineering School of Sfax, University of Sfax, Tunisia | Digital Research Center of Sfax, Technopole of Sfax, Tunisia
Mohamed Njah Laboratory of Advanced Technologies for Medicine and Signals, National Engineering School of Sfax, University of Sfax, Tunisia | Digital Research Center of Sfax, Technopole of Sfax, Tunisia
Rachid Jennane Denis Poisson Institute UMRS CNRS 7013, University of Orleans, Orleans, France
Fatma Kolsi Department of Neurosurgery, Habib Bourguiba University Hospitals, Sfax, Tunisia
Mohamed Zaher Boudawara Department of Neurosurgery, Habib Bourguiba University Hospitals, Sfax, Tunisia

Volume: 15 | Issue: 6 | Pages: 29796-29802 | December 2025 | https://doi.org/10.48084/etasr.13716

Received: 31 July 2025 | Revised: 9 September 2025 | Accepted: 19 September 2025 | Online: 19 November 2025

Corresponding author: Ridha El Hamdi

Abstract

This paper presents an advanced eXplainable Artificial Intelligence (XAI) framework for Magnetic Resonance Imaging (MRI)-based glioma classification, designed to bridge the gap between high-performing Deep Learning (DL) models and interpretability in clinical diagnostics. The proposed framework leverages three Convolutional Neural Network (CNN) models (ResNet50V2, EfficientNet-B6, and Xception) and a Vision Transformer (ViT) model to differentiate between Low-Grade Gliomas (LGG) and High-Grade Gliomas (HGG). A Max-Voting strategy integrates the predictions of these models to enhance classification reliability. To promote transparency, the framework incorporates four XAI methods (LIME, SHAP, Integrated Gradients, and GradCAM), providing interpretive insights by highlighting salient features and regions within the MRI scans. Experiments using the BraTS2019 dataset demonstrate that the suggested framework achieves a high classification accuracy of 98.89%, while also offering visual attention maps and interpretative information flow visualizations that support radiologists in clinical decision-making. This work not only advances accurate glioma classification but also emphasizes the role of transparency in AI, highlighting how explainable AI has the potential to revolutionize medical imaging.

Keywords:

explainable artificial intelligence (XAI), XAI evaluation metrics, deep transfer learning, vision transformer (ViT), brain tumor diagnosis, MRI, max-voting

Downloads

Download data is not yet available.

References

M. Weller et al., ''EANO guidelines on the diagnosis and treatment of diffuse gliomas of adulthood,'' Nature Reviews Clinical Oncology, vol. 18, no. 3, pp. 170–186, Mar. 2021. DOI: https://doi.org/10.1038/s41571-020-00447-z

M. Zhou et al., ''Radiomics in Brain Tumor: Image Assessment, Quantitative Feature Descriptors, and Machine-Learning Approaches,'' American Journal of Neuroradiology, vol. 39, no. 2, pp. 208–216, Feb. 2018. DOI: https://doi.org/10.3174/ajnr.A5391

M. Rasool, A. Noorwali, H. Ghandorh, N. A. Ismail, and W. M. S. Yafooz, “Brain Tumor Classification using Deep Learning: A State-of-the-Art Review,” Engineering, Technology & Applied Science Research, vol. 14, no. 5, pp. 16586–16594, Oct. 2024. DOI: https://doi.org/10.48084/etasr.8298

Z. C. Lipton, ''The Mythos of Model Interpretability: In machine learning, the concept of interpretability is both important and slippery.,'' Queue, vol. 16, no. 3, pp. 31–57, June 2018. DOI: https://doi.org/10.1145/3236386.3241340

Q. Xue and M. C. Chuah, ''Explainable deep learning based medical diagnostic system,'' Smart Health, vol. 13, Aug. 2019, Art. no. 100068. DOI: https://doi.org/10.1016/j.smhl.2019.03.002

R. A. Zeineldin et al., ''Explainability of deep neural networks for MRI analysis of brain tumors,'' International Journal of Computer Assisted Radiology and Surgery, vol. 17, no. 9, pp. 1673–1683, Sept. 2022. DOI: https://doi.org/10.1007/s11548-022-02619-x

A. Jabbar, S. Naseem, T. Mahmood, T. Saba, F. S. Alamri, and A. Rehman, ''Brain Tumor Detection and Multi-Grade Segmentation Through Hybrid Caps-VGGNet Model,'' IEEE Access, vol. 11, pp. 72518–72536, 2023. DOI: https://doi.org/10.1109/ACCESS.2023.3289224

S. Chatterjee, F. A. Nizamani, A. Nürnberger, and O. Speck, ''Classification of brain tumours in MR images using deep spatiospatial models,'' Scientific Reports, vol. 12, no. 1, Jan. 2022, Art. no. 1505. DOI: https://doi.org/10.1038/s41598-022-05572-6

Z. Khazaee, M. Langarizadeh, and M. E. S. Ahmadabadi, ''Developing an Artificial Intelligence Model for Tumor Grading and Classification, Based on MRI Sequences of Human Brain Gliomas,'' International Journal of Cancer Management, Research, Oct. 2021, Art. no. 15. DOI: https://doi.org/10.5812/ijcm.120638

M. I. Sharif, M. A. Khan, M. Alhussein, K. Aurangzeb, and M. Raza, ''A decision support system for multimodal brain tumor classification using deep learning,'' Complex & Intelligent Systems, vol. 8, no. 4, pp. 3007–3020, Aug. 2022. DOI: https://doi.org/10.1007/s40747-021-00321-0

Q. U. Ain, I. Duaa, K. Haroon, F. Amin, and M. Z. ur Rehman, ''MRI Based Glioma Detection and Classification into Low-grade and High-Grade Gliomas,'' in 15th International Conference on Open Source Systems and Technologies (ICOSST), Sept. 2021, pp. 1–5. DOI: https://doi.org/10.1109/ICOSST53930.2021.9683838

H. E. Hamdaoui et al., ''High precision brain tumor classification model based on deep transfer learning and stacking concepts,'' Indonesian Journal of Electrical Engineering and Computer Science, vol. 24, no. 1, Oct. 2021, Art. no. 167. DOI: https://doi.org/10.11591/ijeecs.v24.i1.pp167-177

S. Bakas et al., ''Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation, Progression Assessment, and Overall Survival Prediction in the BRATS Challenge.'' arXiv, Apr. 23, 2019.

K. H. Kim and H. W. Park, ''A fast progressive method of maximum intensity projection,'' Computerized Medical Imaging and Graphics, vol. 25, no. 5, pp. 433–441, Sept. 2001. DOI: https://doi.org/10.1016/S0895-6111(01)00003-9

F. Chollet, “Xception: Deep Learning with Depthwise Separable Convolutions,” in 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA July 2017, pp. 1800–1807. DOI: https://doi.org/10.1109/CVPR.2017.195

A. U. I. Rafid, S. Sanjana, M. B. Munir, and N. Sharmin, ''An early-stage diagnosis of diabetic retinopathy based on ensemble framework,'' Signal, Image and Video Processing, vol. 18, no. 1, pp. 735–749, Feb. 2024. DOI: https://doi.org/10.1007/s11760-023-02796-5

K. He, X. Zhang, S. Ren, and J. Sun, ''Identity Mappings in Deep Residual Networks,'' in Computer Vision – ECCV 2016, 2016, vol. 4, pp. 630–645. DOI: https://doi.org/10.1007/978-3-319-46493-0_38

A. Dosovitskiy et al., “An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale,” presented at the International Conference on Learning Representations, 2021.

G. S. Tandel, A. Tiwari, and O. G. Kakde, ''Performance optimisation of deep learning models using majority voting algorithm for brain tumour classification,'' Computers in Biology and Medicine, vol. 135, Aug. 2021, Art. no. 104564. DOI: https://doi.org/10.1016/j.compbiomed.2021.104564

H. Charaabi, H. Mzoughi, R. Hamdi, and M. Njah, ''EXplainable Artificial Intelligence (XAI) for MRI brain tumor diagnosis: A survey,'' in 2023 International Conference on Cyberworlds (CW), July 2023, Sousse, Tunisia, pp. 171–178. DOI: https://doi.org/10.1109/CW58918.2023.00033

M. Sundararajan, A. Taly, and Q. Yan, ''Axiomatic Attribution for Deep Networks,'' in Proceedings of the 34th International Conference on Machine Learning, July 2017, pp. 3319–3328.

R. R. Selvaraju, M. Cogswell, A. Das, R. Vedantam, D. Parikh, and D. Batra, “Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization,” in 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy, Oct. 2017, pp. 618–626. DOI: https://doi.org/10.1109/ICCV.2017.74

M. T. Ribeiro, S. Singh, and C. Guestrin, ''‘Why Should I Trust You?’: Explaining the Predictions of Any Classifier,'' in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA, May 2016, pp. 1135–1144. DOI: https://doi.org/10.1145/2939672.2939778

S. M. Lundberg and S. I. Lee, ''A Unified Approach to Interpreting Model Predictions,'' in Advances in Neural Information Processing Systems, 2017, vol. 30, pp. 4765–4774.