Authors : Mahin Montasir Afif; A. F. Faizur Rahman; A. M. Rafinul Huq; Abdullah Al Noman; Kazi Abdullah Jarif

Volume/Issue : Volume 10 - 2025, Issue 7 - July

Google Scholar : https://tinyurl.com/2k6v5fc8

DOI : https://doi.org/10.38124/ijisrt/25jul042

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Note : Google Scholar may take 30 to 40 days to display the article.

Abstract : Accurate and interpretable tumor classification remains a critical challenge in medical image analysis. In this study, we conduct a comprehensive evaluation of ten state-of-the-art convolutional neural network (CNN) architectures, including InceptionV3, Xception, MobileNetV2, DenseNet121, NASNetMobile, VGG16, VGG19, ResNet50, ResNet101, and EfficientNetB0, on a curated dataset of tumorous and nontumorous images. Each model’s performance was rigorously assessed using standard classification metrics: accuracy, precision, recall, and F1-score. InceptionV3 emerged as the top- performing model with an accuracy of 97.75%, while EfficientNetB0 showed the lowest at 56.50%. Beyond raw performance, we prioritized model transparency by applying five explainable AI (XAI) methods—Grad-CAM, Saliency Maps, Integrated Gradients, Vanilla Gradients, and SmoothGrad—to visualize and interpret the models’ decision-making processes. These visualizations revealed critical insights into model attention and class-specific feature relevance, reinforcing the importance of explainability in medical diagnostics. The results not only highlight the superiority of modern CNNs in medical imaging tasks but also emphasize the value of interpretability tools for building trust and accountability in clinical AI applications.

References :

1. M. A. Abid and K. Munir, “A systematic review on deep learning implementation in brain tumor segmentation, classification and prediction,” Multimedia Tools and Applications, 2025. [Online]. Available: https://doi.org/10.1007/s11042-025-20706-4
2. H. Sadr, M. Nazari, S. Yousefzadeh-Chabok, H. Emami, R. Rabiei, and A. Ashraf, “Enhancing brain tumor classification in MRI images: A deep learning-based approach for accurate diagnosis,” Image and Vision Computing, vol. 159, p. 105555, 2025. [Online]. Available: https://doi.org/10.1016/j.imavis.2025.105555
3. Z. Rasheed, Y.-K. Ma, I. Ullah, Y. Y. Ghadi, M. Z. Khan, M. A. Khan, A. Abdusalomov, F. Alqahtani, and A. M. Shehata, “Brain tumor classification from MRI using image enhancement and convolutional neural network techniques,” Brain Sciences, vol. 13, no. 9, p. 1320, 2023. [Online]. Available: https://doi.org/10.3390/brainsci13091320
4. S. Arora and M. Sharma, “Deep learning for brain tumor classification from MRI images,” in Proc. Int. Conf. Image Inf. Process. (ICIIP), Shimla, India, 2021, pp. 409–412. doi: 10.1109/ICIIP53038.2021.9702609.
5. M. Vimala, S. Palanisamy, S. Guizani, and H. Hamam, “Efficient GDD feature approximation based brain tumour classification and survival analysis model using deep learning,” Egyptian Informatics Journal, vol. 28, p. 100577, 2024. [Online]. Available: https://doi.org/10.1016/j.eij.2024.100577
6. R. Vankdothu, M. A. Hameed, and H. Fatima, “A brain tumor identification and classification using deep learning based on CNN-LSTM method,” Computers and Electrical Engineering, vol. 101, p. 107960, 2022. [Online]. Available: https://doi.org/10.1016/j.compeleceng.2022.107960
7. Z. Rasheed, Y.-K. Ma, I. Ullah, M. Al-Khasawneh, S. S. Almutairi, and M. Abohashrh, “Integrating convolutional neural networks with attention mechanisms for magnetic resonance imagingbased classification of brain tumors,” Bioengineering, vol. 11, no. 7, p. 701, 2024. [Online]. Available: https://doi.org/10.3390/bioengineering11070701
8. S. Ahmmed, P. Podder, M. R. H. Mondal, S. M. A. Rahman, S. Kannan, M. J. Hasan, A. Rohan, and A. E. Prosvirin, “Enhancing brain tumor classification with transfer learning across multiple classes: An in-depth analysis,” BioMedInformatics, vol. 3, no. 4, pp. 1124–1144, 2023. [Online]. Available: https://doi.org/10.3390/biomedinformatics3040068
9. P. Priyadarshini, P. Kanungo, and T. Kar, “Multigrade brain tumor classification in MRI images using finetuned EfficientNet,” e-Prime – Advances in Electrical Engineering, Electronics and Energy, vol. 8, p. 100498, 2024. [Online]. Available: https://doi.org/10.1016/j.prime.2024.100498
10. M. H. Al-Jammas, E. A. Al-Sabawi, A. M. Yassin, and A. H. Abdulrazzaq, “Brain tumors recognition based on deep learning,” e-Prime – Advances in Electrical Engineering, Electronics and Energy, vol. 8, 2024, Art. no. 100500. [Online]. Available: https://doi.org/10.1016/j.prime.2024.100500
11. A. Akter, N. Nosheen, S. Ahmed, M. Hossain, M. A. Yousuf, M. A. A. Almoyad, K. F. Hasan, and M. A. Moni, “Robust clinical applicable CNN and U-Net based algorithm for MRI classification and segmentation for brain tumor,” Expert Systems with Applications, vol. 238, 2024, Art. no. 122347. [Online]. Available: https://doi.org/10.1016/j.eswa.2023.122347
12. Y. Xie, F. Zaccagna, L. Rundo, C. Testa, R. Agati, R. Lodi, D. N. Manners, and C. Tonon, “Convolutional neural network techniques for brain tumor classification (from 2015 to 2022): Review, challenges, and future perspectives,” Diagnostics, vol. 12, no. 8, p. 1850, 2022. doi: 10.3390/diagnostics12081850.
13. M. Saradha, V. Agil, M. Danesha, and M. Vignesh, “A literature review on brain tumor classification using deep learning,” Int. J. Res. Appl. Sci. Eng. Technol. (IJRASET), vol. 12, no. 3, pp. 284, Mar. 2024. doi: 10.22214/ijraset.2024.58808
14. M. Nazir, S. Shakil, and K. Khurshid, “Role of deep learning in brain tumor detection and classification (2015 to 2020): A review,” Computerized Medical Imaging and Graphics, vol. 91, p. 101940, 2021. doi: 10.1016/j.compmedimag.2021.101940
15. T. R. Mahesh, M. Gupta, A. T. A. Anupama, V. Kumar, O. Geman, and V. D. Kumar, “An XAI-enhanced EfficientNetB0 framework for precision brain tumor detection in MRI imaging,” J. Neurosci. Methods, vol. 410, p. 110227, 2024. doi: 10.1016/j.jneumeth.2024.110227
16. M. M. Afif, A. A. Noman, K. M. Kabir, M. M. Ahmmed, M. M. Rahman, M. Mahmud, and M. A.
17. Babu, “Proportional Sensitivity in Generative Adversarial Network (GAN)-Augmented Brain Tumor Classification Using Convolutional Neural Network,” arXiv preprint arXiv:2506.17165, 2025. [Online]. Available: https://arxiv.org/abs/2506.17165
18. J. G. Melekoodappattu, C. K. Puthiyapurayil, A. Vylala, and A. S. Dhas, “Brain cancer classification based on multistage ensemble generative adversarial network and convolutional neural network,” Cell Biochemistry and Function, vol. 41, no. 8, pp. 1357–1369, 2023. doi: 10.1002/cbf.3870
19. N. Thenmoezhi, B. Perumal, and A. Lakshmi, “Multi-view image fusion using ensemble deep learning algorithm for MRI and CT images,” ACM Trans. Asian Low-Resour. Lang. Inf. Process., vol. 23, no. 3, Art. no. 40, pp. 1–24, Mar. 2024. doi: 10.1145/3640811
20. S. N. Eity, M. M. Afif, T. Fairooz, M. M. Ahmmed, and M. S. Miah, “DGG-XNet: A hybrid deep learning framework for multi-class brain disease classification with explainable AI,” arXiv preprint arXiv:2506.14367, 2025. [Online]. Available: https://arxiv.org/abs/2506.14367
21. M. M. Ahmmed, A. A. Noman, M. M. Afif, K. M. T. Kabir, M. M. Rahman, and M. Mahmud, “A model-mediated stacked ensemble approach for depression prediction among professionals,” arXiv preprint arXiv:2506.14459, 2025. [Online]. Available: https://arxiv.org/abs/2506.14459
22. M. M. Afif, K. M. T. Kabir, A. A. Noman, M. E. A. Islam, and M. M. Ahmmed, “Forecasting wind energy potential in Chattogram, Bangladesh: Statistical modeling incorporating Rayleigh and Weibull distributions,” in *Proc. Undergraduate Conf. on Intelligent Computing and Systems (UCICS)*, Varendra University, Rajshahi, Bangladesh, Feb. 2025. [Online]. Available: https://www.researchgate.net/publication/389589352
23. M. E. A. Islam, K. M. T. Kabir, M. M. Afif, A. A. Noman, and M. M. Ahmmed, “Biomedical engineering for sustainable health: A qualitative study on advancing SDG 3 in Bangladesh,” in *Proc. Undergraduate Conf. on Intelligent Computing and Systems (UCICS)*, Varendra University, Rajshahi, Bangladesh, Feb. 2025. [Online]. Available: https://www.researchgate.net/publication/389588995
24. M. M. Afif, A. A. Noman, M. E. A. Islam, and M. M. Ahmmed, “Losing the night: A comprehensive analysis of trends in artificial light pollution patterns in Bangladesh using VIIRS data,” in *Proc. Int. Conf. Electronics and Informatics (ICEI)*, 2024. [Online]. Available: https://www.researchgate.net/publication/387488597
25. A. A. Noman, M. M. Afif, A. M. R. Huq, A. F. Faizur Rahman, and M. E. A. Islam, “Blockchain-driven halal supply chains: Enhancing transparency and efficiency while ensuring Shariah adherence,” *International Journal of Innovative Science and Research Technology*, vol. 10, no. 4, pp. [page numbers if available], Apr. 2025, doi: 10.38124/ijisrt/25apr1001. [Online]. Available: https://tinyurl.com/pz7ymvs2
26. A. Shoeibi, M. Khodatars, M. Jafari, N. Ghassemi, D. Sadeghi, P. Moridian, A. Khadem, R. Alizadehsani, S. Hussain, A. Zare, Z. A. Sani, F. Khozeimeh, S. Nahavandi, U. R. Acharya, and J. M. Gorriz, “Automated detection and forecasting of COVID-19 using deep learning techniques: A review,” Neurocomputing, vol. 577, p. 127317, 2024, doi: https://doi.org/10.1016/j.neucom.2024.12731710.1016/j.neucom.2024.127317.
27. T. Hulsen, “Explainable Artificial Intelligence (XAI): Concepts and Challenges in Healthcare,” AI, vol. 4, no. 3, pp. 652–666, 2023, doi: https://doi.org/10.3390/ai403003410.3390/ai4030034.
28. M. Shrivastava and L. Ye, “Neuroimaging and artificial intelligence for assessment of chronic painful temporomandibular disorders—a comprehensive review,” Int. J. Oral Sci., vol. 15, no. 1, p. 58, Dec. 2023, doi: https://doi.org/10.1038/s41368-023-00254-z10.1038/s41368-023-00254-z.
29. S. Zolfaghari, S. Suravee, D. Riboni, and K. Yordanova, “Sensor-Based Locomotion Data Mining for Supporting the Diagnosis of Neurodegenerative Disorders: A Survey,” ACM Comput. Surv., vol. 56, no. 1, Art. no. 10, pp. 1–36, Aug. 2023, doi: https://doi.org/10.1145/360349510.1145/3603495.
30. J. Chaki and G. Deshpande, “Brain Disorder Detection and Diagnosis using Machine Learning and Deep Learning – A Bibliometric Analysis,” Current Pharmaceutical Design, vol. 22, no. 13, pp. 2191–2216, May 2024, doi: 10.2174/1570159X22999240531160344.
31. S. Lee and K.-S. Lee, “Predictive and Explainable Artificial Intelligence for Neuroimaging Applications,” Diagnostics, vol. 14, no. 21, p. 2394, 2024, doi: https://doi.org/10.3390/diagnostics1421239410.3390/diagnostics14212394.
32. R. Gupta, S. Kumari, A. Senapati, R. K. Ambasta, and P. Kumar, “New era of artificial intelligence and machine learning-based detection, diagnosis, and therapeutics in Parkinson’s disease,” Ageing Res. Rev., vol. 90, p. 102013, 2023, doi: https://doi.org/10.1016/j.arr.2023.10201310.1016/j.arr.2023.102013.
33. Y. Maeda et al., “Rewiring the primary somatosensory cortex in carpal tunnel syndrome with acupuncture,” Brain, vol. 140, no. 4, pp. 914–927, Apr. 2017, doi: https://doi.org/10.1093/brain/awx01510.1093/brain/awx015.