Brain Tumor Classification Using EfficientNet-B1: A Deep Learning Approach


  • Walid Abdalla Ramdhan Abdalla General Department, College of Electrical and Electronics Technology (CEET), Benghazi,Libya


Brain tumour, EfficientNet-B1, MRI Images, CNN, Transfer learning


Tumors in the brain are the most common cause of death, and detection at an early stage is very important for treatment and better patient outcomes. Lacking a clear primary cause still makes the correct diagnosis of brain tumors very important to lower the high death rate of these tumors. This study focuses on the classification of three common types of brain tumors: meningioma, pituitary, and glioma. Applying deep learning capabilities of pre-trained convolutional neural networks (CNNs) will help in feature extraction and classification of brain tumors. This work employs EfficientNet-B1 as an advanced pre-trained CNN to achieve brain tumor classification accuracy of 100%. Our findings show that deep learning algorithms could be the tool that ensures the accuracy of brain tumor diagnosis to allow early intervention and decrease mortality.




How to Cite

Walid Abdalla Ramdhan Abdalla. (2024). Brain Tumor Classification Using EfficientNet-B1: A Deep Learning Approach. African Journal of Advanced Pure and Applied Sciences (AJAPAS), 603–613. Retrieved from