Brain Tumor Classification using EfficientNet
Md Masum Billah, Rashad Bakhshizadaa, Denesh Dasb, Tasmita Tanjim Tanhac d, Rashedur Rahmand
- aMissouri S&T Rolla , MO , USA
- bLamar University Beaumont , TX , USA
- cDepartment of Computer Science
- dSchool of Engineering , San Francisco Bay University , Fremont , CA , 94539 , USA
Papers open inside SciRah from the original publisher or repository; SciRah never hosts them.
Abstract
Accurate classification of brain tumors from magnetic resonance imaging (MRI) is essential for assisting clinical diagnosis and treatment planning.This study presents a deep learning-based approach for brain tumor classification using the EfficientNetB3 architecture.Transfer learning with initialization from weights learned on ImageNet is used, and the network is fine-tuned on a brain MRI dataset containing four classes: glioma, meningioma, pituitary tumor, and no tumor.The proposed system learns end to end to produce discriminative features from an image.Experimental results show that EfficientNetB3 achieves a test accuracy of 99%, with macro-averaged precision, recall (sensitivity), and F1-score of 99%.These results demonstrate the effectiveness of EfficientNetB3 for reliable and high-performance brain tumor classification.