Citation

Nabi, Md Serajun and Rashidul Islam, Md and Alam, Shahaba and Touhami, Meriem and Hossain, Md Shakil and Ahmad Fauzi, Mohammad Faizal (2025) AI-Driven Diagnosis of Neurological Disorders Using Brain MRI. In: 2025 Multimedia University Engineering Conference, MECON 2025, 21 July 2025 - 23 July 2025, Cyberjaya, Malaysia.

Text IEEE Xplore Full-Text PDF_20.pdf - Published Version Restricted to Repository staff only Download (1MB)

Abstract

Brain tumor classification is crucial for timely diagnosis and treatment. This paper presents a deep learningbased method utilizing EfficientNetB0 and EfficientNetB3 models for brain tumor classification from MRI images. The study employs the publicly available "Brain Tumor Classification (MRI)" dataset includes 3,264 MRI images of glioma, meningioma, pituitary tumor, and no tumor. The proposed framework incorporates advanced data preprocessing, augmentation methods, and Multiscale Feature Fusion (MSFF) to support classification performance improvement. Experimental results demonstrate that the EfficientNetB0 and EfficientNetB3 models, combined with an enhanced convolutional neural network and MSFF, achieve a high accuracy of 98.0%. The evaluation metrics, including AUC-ROC, precision, recall, and F1-score confirm the robustness and reliability of the proposed approach in accurate brain tumor identification. The findings highlight the potential of the proposed system for accurate and efficient brain tumor detection, providing valuable insights into clinical applications.

Item Type:	Conference or Workshop Item (Paper)
Uncontrolled Keywords:	Brain tumor, MRI imaging
Subjects:	R Medicine > R Medicine (General) > R858-859.7 Computer applications to medicine. Medical informatics
Divisions:	Faculty of Artificial Intelligence & Engineering (FAIE)
Depositing User:	Ms Rosnani Abd Wahab
Date Deposited:	17 Mar 2026 06:19
Last Modified:	17 Mar 2026 06:19
URII:	http://shdl.mmu.edu.my/id/eprint/15485

Downloads

Edit (login required)