Enhanced Classification of Brain MRI Images for Tumor Detection Using Transfer Learning and Grad-CAM-Based Explainable Convolutional Neural Network (CNN)
DOI:
https://doi.org/10.56313/jictas.v4i2.454Keywords:
Brain MRI, Convolutional Neural Network (CNN), Grad-CAM, Explainable AI, EfficientNet-B0Abstract
Accurate and explainable classification of brain Magnetic Resonance Imaging (MRI) is crucial for the early detection and treatment of brain tumors. This study introduces an enhanced deep learning framework that integrates transfer learning with Grad-CAM-based explainable Convolutional Neural Network (CNN) for tumor classification. The proposed approach utilizes a fine-tuned EfficientNet-B0 architecture with an optimized preprocessing pipeline consisting of Contrast Limited Adaptive Histogram Equalization (CLAHE), normalization, and multi-variant augmentation (rotation, flipping, and zoom). The model was trained on a publicly available brain MRI dataset comprising 3,000 images classified into four categories: glioma, meningioma, pituitary tumor, and non-tumor. Evaluation metrics include accuracy, precision, recall, F1-score, and AUC. Experimental results demonstrate that the proposed model achieves an accuracy of 94.2% and an AUC of 0.965, outperforming baseline CNN models by a significant margin. The use of Grad-CAM visualization provides interpretability by localizing tumor regions within MRI scans, thereby increasing the model’s clinical transparency. This study highlights the potential of explainable deep learning models to enhance diagnostic reliability in automated brain tumor detection systems.
References
D. F. Bramantyo, D. O. Ariyanto, K. T. Prihastomo, R. Ardhini, M. Murtadho, and C. H. N. Prihharsanti, “Radiotherapy Protocol of Central Neurocytoma for Resource-limited Settings in the Absence of Official Guidelines: A Case Report and Review of the Literature,” Open Access Maced J Med Sci, vol. 10, no. B, 2022, doi: 10.3889/oamjms.2022.10381.
R. G. Malueka et al., “Association of Hormonal Contraception with Meningioma Location in Indonesian Patients,” Asian Pacific Journal of Cancer Prevention, vol. 23, no. 3, 2022, doi: 10.31557/APJCP.2022.23.3.1047.
N. A. Anandito and D. Ardiansyah, “Clinical and radiological profiles of metastatic brain tumor in Indonesia: A study at Dr. Soetomo Hospital, Surabaya,” Bali Medical Journal, vol. 11, no. 1, 2022, doi: 10.15562/bmj.v11i1.3222.
A. Dian Deva, F. Firdaus, S. Hasyim, B. Yanto, and R. Mai Candra, “Klasifikasi Prediksi Penyakit Paru-Paru Normal dengan Pneumonia berdasarkan Citra Image X-ray dengan Optimasi Adam Convolutional Neural Network (CNN),” Riau Journal of Computer Science, vol. 10, no. 2, pp. 146–155, 2024.
M. A. Mukti, A. T. Kurniawan, S. Bahri, N. Husin, B. Yanto, and F. Asmen, “Akurasi 12 Layer Convolutional Neural Network (CNN) Untuk Jenis Tumor Otak Dari Hasil Citra MRI Dengan Google Colab Dan Dataset Kaggle,” Riau Journal of Computer Science, vol. 10, no. 2, pp. 135–145, 2024.
E. Ribka Meganta, B. Yanto, and E. R. Meganta, “Optimized Detection of Red Devil Fish in Low-Quality Underwater Images from Lake Toba Using a Hybrid CNN and Transfer Learning Approach,” Journal of ICT Aplication and System (JICTAS, vol. 4, no. 1, pp. 7–15, 2025, doi: 10.56313/jictas.v1i1.4i1.
E. Prasiwiningrum and Adyanata Lubis, “Classification Of Palm Oil Maturity Using CNN (Convolution Neural Network) Modelling RestNet 50,” Decode: Jurnal Pendidikan Teknologi Informasi, vol. 4, no. 3, pp. 983–999, 2024, doi: 10.51454/decode.v4i3.822.
E. Oktafanda, A. Lubis, and E. Prasiwiningrum, “Detection of Oil Palm Seedling Disease Based on Leaf Images Using the MobileNetV2-CNN Architecture,” International Journal of Informatics and Computation (IJICOM), vol. 7, no. 1, p. 2025, 2025, doi: 10.35842/ijicom.
V. V. P. Wibowo, Z. Rustam, and J. Pandelaki, “Classification of Brain Tumor Using K-Nearest Neighbor-Genetic Algorithm and Support Vector Machine-Genetic Algorithm Methods,” in 2021 International Conference on Decision Aid Sciences and Application, DASA 2021, 2021. doi: 10.1109/DASA53625.2021.9682341.
A. D. Dariansyah, W. Suryaningtyas, and M. A. Parenrengi, “Tuberculoma mimicking postoperative vp shunt seeding of craniopharyngioma: A rare case report,” Surg Neurol Int, vol. 12, 2021, doi: 10.25259/SNI_606_2021.
R. Mulyadi, A. A. Islam, B. Murtala, J. Tammase, M. Hatta, and M. Firdaus, “Diagnostic yield of the combined magnetic resonance imaging and magnetic resonance spectroscopy to predict malignant brain tumor,” Bali Medical Journal, vol. 9, no. 1, 2020, doi: 10.15562/bmj.v9i1.1486.
G. Habib and S. Qureshi, “Biomedical Image Classification using CNN by Exploiting Deep Domain Transfer Learning,” International Journal of Computing and Digital Systems, vol. 10, no. 1, 2021, doi: 10.12785/ijcds/100197.
M. Osadebey, Q. Liu, E. Fuster-Garcia, and K. E. Emblem, “Interpreting deep learning models for glioma survival classification using visualization and textual explanations,” BMC Med Inform Decis Mak, vol. 23, no. 1, 2023, doi: 10.1186/s12911-023-02320-2.
S. Akça, F. Atban, Z. Garip, and E. Ekinci, “XAI in the hybrid classification of brain MRI tumor images,” in Explainable Artificial Intelligence for Biomedical Applications, 2023. doi: 10.1201/9781032629353-16.
K. Pikulkaew, “Enhancing Brain Tumor Detection with Gradient-Weighted Class Activation Mapping and Deep Learning Techniques,” in Proceedings of JCSSE 2023 - 20th International Joint Conference on Computer Science and Software Engineering, 2023. doi: 10.1109/JCSSE58229.2023.10202020.
J. Zhang et al., “EFF_D_SVM: a robust multi-type brain tumor classification system,” Front Neurosci, vol. 17, 2023, doi: 10.3389/fnins.2023.1269100.
F. A. Özbay and E. Özbay, “Brain tumor detection with mRMR-based multimodal fusion of deep learning from MR images using Grad-CAM,” Iran Journal of Computer Science, vol. 6, no. 3, 2023, doi: 10.1007/s42044-023-00137-w.
R. Kalantar et al., “Deep Learning Framework with Multi-Head Dilated Encoders for Enhanced Segmentation of Cervical Cancer on Multiparametric Magnetic Resonance Imaging,” Diagnostics, vol. 13, no. 21, 2023, doi: 10.3390/diagnostics13213381.
B. Babu Vimala, S. Srinivasan, S. K. Mathivanan, Mahalakshmi, P. Jayagopal, and G. T. Dalu, “Detection and classification of brain tumor using hybrid deep learning models,” Sci Rep, vol. 13, no. 1, 2023, doi: 10.1038/s41598-023-50505-6.
F. Zulfiqar, U. Ijaz Bajwa, and Y. Mehmood, “Multi-class classification of brain tumor types from MR images using EfficientNets,” Biomed Signal Process Control, vol. 84, 2023, doi: 10.1016/j.bspc.2023.104777.
T. Hussain and H. Shouno, “Explainable Deep Learning Approach for Multi-Class Brain Magnetic Resonance Imaging Tumor Classification and Localization Using Gradient-Weighted Class Activation Mapping,” Information (Switzerland), vol. 14, no. 12, 2023, doi: 10.3390/info14120642.
G. T. Mgbejime, M. A. Hossin, G. U. Nneji, H. N. Monday, and F. Ekong, “Parallelistic Convolution Neural Network Approach for Brain Tumor Diagnosis,” Diagnostics, vol. 12, no. 10, 2022, doi: 10.3390/diagnostics12102484.
S. Aulia and D. Rahmat, “Brain Tumor Identification Based on VGG-16 Architecture and CLAHE Method,” International Journal on Informatics Visualization, vol. 6, no. 1, 2022, doi: 10.30630/joiv.6.1.864.
A. Chattopadhyay and M. Maitra, “MRI-based brain tumour image detection using CNN based deep learning method,” 2022. doi: 10.1016/j.neuri.2022.100060.
M. A. Gómez-Guzmán et al., “Classifying Brain Tumors on Magnetic Resonance Imaging by Using Convolutional Neural Networks,” Electronics (Switzerland), vol. 12, no. 4, 2023, doi: 10.3390/electronics12040955.
T. A. T. K. Azaharan, A. K. Mahamad, S. Saon, Muladi, and S. W. Mudjanarko, “Investigation of VGG-16, ResNet-50 and AlexNet Performance for Brain Tumor Detection,” International journal of online and biomedical engineering, vol. 19, no. 8, 2023, doi: 10.3991/ijoe.v19i08.38619.
C. Srinivas et al., “Deep Transfer Learning Approaches in Performance Analysis of Brain Tumor Classification Using MRI Images,” J Healthc Eng, vol. 2022, 2022, doi: 10.1155/2022/3264367.
M. F. Alanazi et al., “Brain Tumor/Mass Classification Framework Using Magnetic?Resonance?Imaging?Based Isolated and Developed Transfer Deep?Learning Model,” Sensors, vol. 22, no. 1, 2022, doi: 10.3390/s22010372.
S. Vidyadharan, B. V. V. S. N. Prabhakar Rao, Y. Perumal, K. Chandrasekharan, and V. Rajagopalan, “Deep Learning Classifies Low- and High-Grade Glioma Patients with High Accuracy, Sensitivity, and Specificity Based on Their Brain White Matter Networks Derived from Diffusion Tensor Imaging,” Diagnostics, vol. 12, no. 12, 2022, doi: 10.3390/diagnostics12123216.
S. Dasanayaka, V. Shantha, S. Silva, D. Meedeniya, and T. Ambegoda, “Interpretable machine learning for brain tumour analysis using MRI and whole slide images,” Software Impacts, vol. 13, 2022, doi: 10.1016/j.simpa.2022.100340.
J. Tagnamas, H. Ramadan, A. Yahyaouy, and H. Tairi, “Correction to: Multi-task approach based on combined CNN-transformer for efficient segmentation and classification of breast tumors in ultrasound images (Visual Computing for Industry, Biomedicine, and Art, (2024), 7, 1, (2), 10.1186/s42492-024-00155-w),” 2024. doi: 10.1186/s42492-024-00156-9.
S. Tripathy, R. Singh, and M. Ray, “Automation of Brain Tumor Identification using EfficientNet on Magnetic Resonance Images,” in Procedia Computer Science, 2022. doi: 10.1016/j.procs.2023.01.133.
M. K. U. Ahamed et al., “DTLCx: An Improved ResNet Architecture to Classify Normal and Conventional Pneumonia Cases from COVID-19 Instances with Grad-CAM-Based Superimposed Visualization Utilizing Chest X-ray Images,” Diagnostics, vol. 13, no. 3, 2023, doi: 10.3390/diagnostics13030551.
Published
How to Cite
Issue
Section
Copyright (c) 2025 Journal of ICT Aplications and System
This work is licensed under a Creative Commons Attribution 4.0 International License.
