NeuroNet19, a deep neural network built on the VGG19 backbone with the innovative Inverted Pyramid Pooling Module (iPPM), effectively detects and classifies brain tumors (BTs). It ensures enhanced feature maps, capturing both local and global image contexts. For transparency, Explainable AI, specifically Local Interpretable Model-Agnostic Explanations (LIME), is employed. Trained on glioma, meningioma, no tumor, and pituitary tumors, NeuroNet19 achieves an impressive 99.3% accuracy on a dataset of 7023 images, with precision, recall, and F1 scores at 99.2%, and a Cohen Kappa coefficient (CKC) of 99%.
Source Nature
