• Akshay Gaikwad
• Varsha Bodade

Brain tumors is a matter of serious health concern because they have the possibility of being fatal and are inherently complex to be diagnosed and classified. Proper identification of brain tumor types both accurately and early is important in order to create effective treatment strategies. This work provides a comparison of three deep learning models, namely Convolutional Neural Networks (CNN), VGG16, and EfficientNetB2, for classification of brain tumors on the basis of magnetic resonance imaging (MRI). The work uses a publicly available dataset of brain tumors, with images being classified as glioma, meningioma, pituitary tumor, and no tumor. Normalization, resizing, and preprocessing techniques were used to enhance the robustness of the model. The CNN model is built with custom implementation, and VGG16 and EfficientNetB2 are used with transfer learning and pre-trained weights. Experimental outcomes show that EfficientNetB2 performs better than the other models in terms of accuracy, precision and recall factors. This research emphasizes the capability of deep learning models, particularly EfficientNetB2, to automate and improve the diagnostic process for brain tumor detection.

CNN, MRI, Glioma, tumor, Flask

"Analysis Of Deep Learning Models For Brain Tumor Classification", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 10, page no.c460-c468, October-2025, Available :http://www.jetir.org/papers/JETIR2510261.pdf

"Analysis Of Deep Learning Models For Brain Tumor Classification", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 10, page no. ppc460-c468, October-2025, Available at : http://www.jetir.org/papers/JETIR2510261.pdf