Explainable CNN for Brain Tumor Detection and Classification
DOI:
https://doi.org/10.68337/cpsm.v1.i2.2026-024Keywords:
AI, LIME, machine learning, XAIAbstract
Image analysis is an important part of medical decision-making, where it helps clinicians to reach a diagnosis and plan treatment. Artificial intelligence (AI) and machine learning (ML) methods for medical image analysis have grown rapidly. Explainable artificial intelligence (XAI) methods aim to make AI applications more usable and trustworthy by showing how a model reaches its decisions. This paper reviews recent XAI methods and their use in medical image analysis, including rule-based systems, attention mechanisms, and feature visualization. A convolutional neural network (CNN) was used to classify brain magnetic resonance imaging (MRI) scans by tumor type, and an XAI model explains how the network uses the images to reach each prediction. Of the 15,030 images, 13,563 were used for training and 1,467 for validation and testing. The model reached an accuracy of 80.55%. Local Interpretable Model-Agnostic Explanations (LIME) is used as the example XAI model.
References
[1] Brij B. Gupta, Akshat Gaurav, and Varsha Arya, "Deep CNN based brain tumor detection in intelligent systems," Int. J. Intell. Netw., vol. 5, pp. 30-37, 2024, doi: 10.1016/j.ijin.2023.12.001.
[2] Mahmoud Khaled Abd-Ellah, Ali Ismail Awad, Ashraf A. M. Khalaf, and Amira Mofreh Ibraheem, "Automatic brain-tumor diagnosis using cascaded deep convolutional neural networks with symmetric U-Net and asymmetric residual-blocks," Sci. Rep., vol. 14, no. 1, Art. no. 9501, 2024, doi: 10.1038/s41598-024-59566-7.
[3] J. Seetha and S. Selvakumar Raja, "Brain tumor classification using convolutional neural networks," Biomed. Pharmacol. J., vol. 11, no. 3, pp. 1457-1461, 2018, doi: 10.13005/bpj/1511.
[4] Wadhah Ayadi, Wajdi Elhamzi, Imen Charfi, and Mohamed Atri, "Deep CNN for brain tumor classification," Neural Process. Lett., vol. 53, no. 1, pp. 671-700, 2021, doi: 10.1007/s11063-020-10398-2.
[5] J. Ricardo McFaline-Figueroa and Eudocia Q. Lee, "Brain tumors," Am. J. Med., vol. 131, no. 8, pp. 874-882, 2018, doi: 10.1016/j.amjmed.2017.12.039.
[6] Radius Tanone, Li-Hua Li, and Shoffan Saifullah, "ViT-CB: Integrating hybrid vision transformer and CatBoost to enhanced brain tumor detection with SHAP," Biomed. Signal Process. Control, vol. 100, Art. no. 107027, 2025, doi: 10.1016/j.bspc.2024.107027.
[7] Mohamed Musthafa M, Mahesh T. R., Vinoth Kumar V, and Suresh Guluwadi, "Enhancing brain tumor detection in MRI images through explainable AI using Grad-CAM with Resnet 50," BMC Med. Imaging, vol. 24, no. 1, Art. no. 107, 2024, doi: 10.1186/s12880-024-01292-7.
[8] Krishan Kumar and Kiran Jyoti, "Recent advancements in Grad-CAM and variants: Enhancing brain tumor detection, segmentation, and classification," Research Square preprint, 2024, doi: 10.21203/rs.3.rs-5485128/v1.
[9] Huong Hoang Luong and Triet Minh Nguyen, "Improving chicken disease classification based on vision transformer and combine with integrated gradients explanation," Int. J. Adv. Comput. Sci. Appl., vol. 15, no. 4, 2024, doi: 10.14569/IJACSA.2024.01504124.
[10] K. Usha Rupni and P. Aruna Priya, "Local interpretable model-agnostic explanations guided brain magnetic resonance imaging classification for identifying attention deficit hyperactivity disorder subtypes," J. Ambient Intell. Humaniz. Comput., vol. 16, no. 2-3, pp. 361-374, 2025, doi: 10.1007/s12652-024-04950-4.
[11] Fei Yan, Yunqing Chen, Yiwen Xia, Zhiliang Wang, and Ruoxiu Xiao, "An explainable brain tumor detection framework for MRI analysis," Appl. Sci., vol. 13, no. 6, Art. no. 3438, 2023, doi: 10.3390/app13063438.
[12] Morteza Esmaeili, Riyas Vettukattil, Hasan Banitalebi, Nina R. Krogh, and Jonn Terje Geitung, "Explainable artificial intelligence for human-machine interaction in brain tumor localization," J. Pers. Med., vol. 11, no. 11, Art. no. 1213, 2021, doi: 10.3390/jpm11111213.
[13] Zubaira Naz, Muhammad Usman Ghani Khan, Tanzila Saba, Amjad Rehman, Haitham Nobanee, and Saeed Ali Bahaj, "An explainable AI-enabled framework for interpreting pulmonary diseases from chest radiographs," Cancers, vol. 15, no. 1, Art. no. 314, 2023, doi: 10.3390/cancers15010314.
[14] Matthias Eder, Emanuel Moser, Andreas Holzinger, Claire Jean-Quartier, and Fleur Jeanquartier, "Interpretable machine learning with brain image and survival data," BioMedInformatics, vol. 2, no. 3, pp. 492-510, 2022, doi: 10.3390/biomedinformatics2030031.
[15] Christian Meske, Enrico Bunde, Johannes Schneider, and Martin Gersch, "Explainable artificial intelligence: Objectives, stakeholders, and future research opportunities," Inf. Syst. Manag., vol. 39, no. 1, pp. 53-63, 2022, doi: 10.1080/10580530.2020.1849465.
[16] Amitojdeep Singh, Sourya Sengupta, and Vasudevan Lakshminarayanan, "Explainable deep learning models in medical image analysis," J. Imaging, vol. 6, no. 6, Art. no. 52, 2020, doi: 10.3390/jimaging6060052.
[17] Rawan Ghnemat, Sawsan Alodibat, and Qasem Abu Al-Haija, "Explainable artificial intelligence (XAI) for deep learning based medical imaging classification," J. Imaging, vol. 9, no. 9, Art. no. 177, 2023, doi: 10.3390/jimaging9090177.
[18] Ramy A. Zeineldin, Mohamed E. Karar, Ziad Elshaer, Jan Coburger, Christian R. Wirtz, Oliver Burgert, and Franziska Mathis-Ullrich, "Explainability of deep neural networks for MRI analysis of brain tumors," Int. J. Comput. Assist. Radiol. Surg., vol. 17, no. 9, pp. 1673-1683, 2022, doi: 10.1007/s11548-022-02619-x.
Downloads
Published
Data Availability Statement
The MRI images used in this study come from a publicly available Kaggle dataset that combines the figshare, SARTAJ, and Br35H collections.Conference Proceedings Volume
Section
Categories
License
Copyright (c) 2026 The Authors
This work is licensed under a Creative Commons Attribution 4.0 International License.
Articles published in Conference Proceedings in Science and Management are made available under the Creative Commons Attribution 4.0 International License (CC BY 4.0). Authors retain copyright in their work and grant the journal first publication rights. Readers are free to share and adapt the published material for any purpose, including commercial use, provided appropriate credit is given to the author, a link to the license is provided, and any changes are indicated.
