An Approach of SIFT With Fed-VGG16 and Fed-CNN for Identification and Classification of Brain Tumors

Abstract

Brain tumors develop when cells in the brain multiply rapidly and unchecked. It can be fatal if not addressed in its early stages. Getting segmentation and classification right is still a challenge, despite a lot of work and good results in this field. Radiologists may now more easily locate tumor regions with the use of experimental medical imaging techniques like magnetic resonance imaging (MRI). Image processing techniques such as pre-processing, segmentation, contour detection, feature extraction using SIFT (scale invariant feature transformation), classification using VGG16, CNN, Fed-VGG16, Fed-CNN classifiers, and evaluation using confusion matrices are presented in this study. The models reach up to 97%, 98.51%, 99.28%, and 100% classification accuracy for the used classifiers, correspondingly, according to the experimental data. In order to facilitate early detection for subsequent research and activity, it seeks to mitigate some of the problems that have already been addressed.