Brain Tumor Classification using Deep Learning Models under Neutrosophic Environment

Abstract

A brain tumor is a highly malignant disease that affects both children and adults. Magnetic resonance imaging (MRI) is the most effective way to detect brain cancer. Scanning generates a huge amount of image data. This paper presents a study on the importance of neutrosophic sets (NS) in deep learning (DL) models for accurately classifying images. The work employs the NS and theory to convert medical images from the grayscale spatial domain to the neutrosophic domain. The purpose of this study is to investigate the effect of NS on DL models. The proposed work was evaluated on 3263 images of the brain tumor MRI dataset. The dataset is divided into four categories: glioma, meningioma, no tumor, and pituitary tumor. The study suggests that including the NS in DL models improves testing accuracy, especially when working with limited brain tumor datasets.