Explainable and Interpretable Model for Brain Tumor Classification with Optimized Transfer Learning

International Journal of Electronics and Communication Engineering

© 2025 by SSRG - IJECE Journal

Volume 12 Issue 4

Year of Publication : 2025

Authors : Sandip Desai, Milind Mushrif

10.14445/23488549/IJECE-V12I4P123

How to Cite?

Sandip Desai, Milind Mushrif, "Explainable and Interpretable Model for Brain Tumor Classification with Optimized Transfer Learning," SSRG International Journal of Electronics and Communication Engineering, vol. 12,  no. 4, pp. 235-250, 2025. Crossref, https://doi.org/10.14445/23488549/IJECE-V12I4P123

Abstract:

Brain neoplasms represent the tenth most prevalent cause of morbidity among all oncological conditions. The manual identification of cerebral neoplasms via Magnetic Resonance Imaging (MRI) is laden with inaccuracies, as disparate radiologists may interpret identical imaging studies in divergent manners. This proposed research showcases an automated system for the identification of brain neoplasm that employs a pretrained Convolutional Neural Network (CNN) architecture and transfer learning techniques to classify brain MRI scans into four categories: glioma, meningioma, pituitary adenoma, and absence of tumor. Pretrained architectures such as ResNet50, EfficientNetB1, Xception, MobileNet, VGG19, InceptionResNetV2, and ConvNeXtLarge were utilized to extract complex features from MRI scans. The models were trained employing three distinct optimization algorithms: Stochastic Gradient Descent (SGD), ADAM, and NADAM. In this study, we implement explainable AI using Grad-CAM to enhance trust in tumor detection mechanisms by highlighting the specific regions in MRI scans that inform decision-making. Empirical findings reveal that the EfficientNetB1 architecture, when paired with the ADAM optimizer, demonstrated improved performance compared to the other models, attaining training and validation accuracies of 95.17% and 89.26%, respectively. The proposed model exhibited remarkable performance metrics, achieving an F1 score, accuracy, recall, and precision value of 100%.

Keywords:

Brain tumor detection, EfficientNetB1, Explainable AI, Grad-CAM, Transfer Learning.

References:

[1] Manon Dubol, I. Sundström-Poromaa, and Erika Comasco, “P.275 Severity of Premenstrual Dysphoric Disorder Symptoms Correlates with Grey Matter Volume and Brain Surface Morphology,” European Neuropsychopharmacology, vol. 40, pp. S157-S158, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Glioma, Johns Hopkins Medicine, 2023. [Online]. Available: https://www.hopkinsmedicine.org/health/conditions-and-diseases/gliomas/
[3] M. Nagabushanam et al., “Detection and Localization of Brain Tumors Using Fractional Hartley Transform and Adaptive Neuro-Fuzzy Inference System Classification Methods,” Journal of Ambient Intelligence and Humanized Computing, vol. 14, pp. 8851-8858, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Brain Ttumor Facts, National Brain Tumor Society, 2022. [Online]. Available: https://braintumor.org/brain-tumors/about-brain tumors/brain-tumor-facts/
[5] Suzan Uysal, Functional Neuroanatomy and Clinical Neuroscience: Foundations for Understanding Disorders of Cognition and Behavior, Oxford University Press, pp. 1-464, 2023.
[Google Scholar] [Publisher Link]
[6] Sakshi Ahuja et al., “Deep Learning-based Computer-aided Diagnosis Tool for Brain Tumor Classification,” 11th International Conference on Cloud Computing, Data Science & Engineering, Noida, India, pp. 854-859, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Paul Summers et al., “Whole-body Magnetic Resonance Imaging: Technique, Guidelines and Key Applications,” Ecancer Medical Sc ience, pp. 1-16, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[8] S. Deepak, and P.M. Ameer, “Brain Tumor Classification using Deep CNN Features via Transfer Learning,” Computers in Biology and Medicine, vol. 111, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Hossam H. Sultan, Nancy M. Salem, and Walid Al-Atabany, “Multi-Classification of Brain Tumor Images Using Deep Neural Network,” IEEE Access, vol. 7, pp. 69215-69225, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Wadhah Ayadi et al., “Brain Tumor Classification Based on Hybrid Approach,” The Visual Computer, vol. 38, pp. 107-117, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Javaria Amin et al., “Brain Tumor Classification based on DWT Fusion of MRI Sequences using Convolutional Neural Network,” Pattern Recognition Letters, vol. 129, pp. 115-122, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Maram Fahaad Almufareh et al., “Automated Brain Tumor Segmentation and Classification in MRI Using YOLO-Based Deep Learning,” IEEE Access, vol. 12, pp. 16189-16207, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Ayesha Jabbar et al., “Brain Tumor Detection and Multi-Grade Segmentation Through Hybrid Caps-VGGNet Model,” IEEE Access, vol. 11, pp. 72518-72536, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Ali Farzamnia et al., “MRI Brain Tumor Detection Methods Using Contourlet Transform Based on Time Adaptive Self-Organizing Map,” IEEE Access, vol. 11, pp. 113480-113492, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Zubair Atha, and Jyotismita Chaki, “SSBTCNet: Semi-Supervised Brain Tumor Classification Network,” IEEE Access, vol. 11, pp. 141485-141499, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Ankit Vidyarthi et al., “Machine Learning Assisted Methodology for Multiclass Classification of Malignant Brain Tumors,” IEEE Access, vol. 10, pp. 50624-60640, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Praveen Kumar Ramtekkar, Anjana Pandey, and Mahesh Kumar Pawar, “Accurate Detection of Brain Tumor using Optimized Feature Selection based on Deep Learning Techniques,” Multimedia Tools and Applications, vol. 82, pp. 44623-44653, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Ardhendu Sekhar et al., “Brain Tumor Classification Using Fine-Tuned GoogLeNet Features and Machine Learning Algorithms: IoMT Enabled CAD System,” IEEE Journal of Biomedical and Health Informatics, vol. 26, no. 3, pp. 983-991, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Shahriar Hossain et al., “Vision Transformers, Ensemble Model, and Transfer Learning Leveraging Explainable AI for Brain Tumor Detection and Classification,” IEEE Journal of Biomedical and Health Informatics, vol. 28, no. 3, pp. 1261-1272, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Mingyang Xu, Limei Guo, and Hsiao-Chun Wu, “Novel Robust Automatic Brain-Tumor Detection and Segmentation Using Magnetic Resonance Imaging,” IEEE Sensors Journal, vol. 24, no. 7, pp. 10957-10964, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Hansen Wijanarko et al., “Tri-VAE: Triplet Variational Autoencoder for Unsupervised Anomaly Detection in Brain Tumor MRI,” IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, Seattle, WA, USA, pp. 3930-3939, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[22] Wenxin Wang et al., “A Two-Stage Generative Model with CycleGAN and Joint Diffusion for MRI-based Brain Tumor Detection,” IEEE Journal of Biomedical and Health Informatics, vol. 28, no. 6, pp. 3534-3544, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[23] Ashly Mathew, and A Christy, “A Comprehensive Study on Various Preprocessing Techniques for Brain MRI Image,” 3rd International Conference on Electronics and Sustainable Communication Systems, Coimbatore, India, pp. 1538-1541, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[24] Mingxing Tan, and Quoc Le, “EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks,” Proceedings of the 36th International Conference on Machine Learning, Long Beach, California, pp. 1-10, 2020.
[Google Scholar] [Publisher Link]
[25] Asmaul Hosna et al., “Transfer Learning: A Friendly Introduction,” Journal of Big Data, vol. 9, pp. 1-19, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[26] Linan Fan, and Zaitian Long, “Optimization of Nadam Algorithm for Image Denoising based on Convolutional Neural Network,” 7th International Conference on Information Science and Control Engineering, Changsha, China, pp. 957-961, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[27] Ramprasaath R. Selvaraju et al., ”Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization,” IEEE International Conference on Computer Vision, Venice, Italy, pp. 618-626, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[28] Md Imran Nazir et al., “Utilizing customized CNN for Brain Tumor Prediction with Explainable AI,” Heliyon, vol. 10, no. 20, pp. 1-16, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[29] R. Lokesh Kumar et al., “Multi-class Brain Tumor Classification using Residual Network and Global Average Pooling,” Multimedia Tools and Applications, vol. 80, no. 9, pp. 13429-13438, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[30] Aman Verma, and Vibhav Prakash Singh, “Design, Analysis and Implementation of Efficient Deep Learning Frameworks for Brain Tumor Classification,” Multimedia Tools and Applications, vol. 81, pp. 37541-37567, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[31] Suganya Athisayamani et al., “Feature Extraction Using a Residual Deep Convolutional Neural Network (ResNet-152) and Optimized Feature Dimension Reduction for MRI Brain Tumor Classification,” Diagnostics, vol. 13, no. 4, pp. 1-20, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[32] Afnan M. Alhassan, and Wan Mohd Nazmee Wan Zainon, “Brain Tumor Classification in Magnetic Resonance Image using Hard Swish based RELU Activation Function-Convolutional Neural Network,” Neural Computing and Applications, vol. 33, pp. 9075-9087, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[33] Zahid Rasheed et al., “Automated Classification of Brain Tumors from Magnetic Resonance Imaging using Deep Learning,” Brain Sciences, vol. 13, no. 4, pp. 1-18, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[34] Prince Priya Malla, Sudhakar Sahu, and Ahmed I. Alutaibi, “Classification of Tumor in Brain MR Images Using Deep Convolutional Neural Network and Global Average Pooling,” Processes, vol. 11, no. 3, pp. 1-17, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[35] Khalid M. Hosny et al., “Explainable Ensemble Deep Learning-based Model for Brain Tumor Detection and Classification,” Neural Computing and Applications, vol. 37, pp. 1289-1306, 2024. [CrossRef] [Google Scholar] [Publisher Link]