Open Access

ARTICLE

Automated Brain Tumor Classification from Magnetic Resonance Images Using Fine-Tuned EfficientNet-B6 with Bayesian Optimization Approach

Sarfaraz Abdul Sattar Natha^1,*, Mohammad Siraj^2,*, Majid Altamimi², Adamali Shah², Maqsood Mahmud³

1 Department of Software Engineering, Sir Syed University of Engineering and Technology, Karachi, 75000, Sindh, Pakistan
2 Electrical Engineering Department, College of Engineering, King Saud University, Riyadh, 11421, Saudi Arabia
3 School of Computing, Queen’s University Belfast, 2-24 York Street, Belfast, BT15 1AP, UK

* Corresponding Authors: Sarfaraz Abdul Sattar Natha. Email: ; Mohammad Siraj. Email:

(This article belongs to the Special Issue: Advanced Computational Intelligence Techniques, Uncertain Knowledge Processing and Multi-Attribute Group Decision-Making Methods Applied in Modeling of Medical Diagnosis and Prognosis)

Computer Modeling in Engineering & Sciences 2025, 145(3), 4179-4201. https://doi.org/10.32604/cmes.2025.072529

Received 28 August 2025; Accepted 27 November 2025; Issue published 23 December 2025

Abstract

A brain tumor is a disease in which abnormal cells form a tumor in the brain. They are rare and can take many forms, making them difficult to treat, and the survival rate of affected patients is low. Magnetic resonance imaging (MRI) is a crucial tool for diagnosing and localizing brain tumors. However, the manual interpretation of MRI images is tedious and prone to error. As artificial intelligence advances rapidly, DL techniques are increasingly used in medical imaging to accurately detect and diagnose brain tumors. In this study, we introduce a deep convolutional neural network (DCNN) framework for brain tumor classification that uses EfficientNet-B6 as the backbone architecture and adds additional layers. The model achieved an accuracy of 99.10% on the public Brain Tumor MRI datasets, and we performed an ablation study to determine the optimal batch size, optimizer, loss function, and learning rate to maximize the accuracy and robustness of the model, followed by K-Fold cross-validation and testing the model on an independent dataset, and tuning Hyperparameters with Bayesian Optimization to further enhance the performance. When comparing our model to other deep learning (DL) models such as VGG19, MobileNetv2, ResNet50, InceptionV3, and DenseNet201, as well as variants of the EfficientNet model (B1–B7), the results show that our proposed model outperforms all other models. Our investigational results demonstrate superiority in terms of precision, recall/sensitivity, accuracy, specificity, and F1-score. Such innovations can potentially enhance clinical decision-making and patient treatment in neurooncological settings.

---

Keywords

---