MULTI-CLASS BRAIN CANCER CLASSIFICATION USING DEEP LEARNING CONVOLUTIONAL NEURAL NETWORK

Abstract

Deep Learning is a modern area in machine learning that has been gaining more attention in the last few years. It has been commonly used in a variety of applications and has proved to be a strong machine learning method for numerousdifficulttroubles. In the context of screening services for prevention, Brain cancer tends to be one of women's leading causes of mortality and an amount of cash has been spent. Computer-assisted detection strategies adapted to date to improve diagnosis have not led to a significant improvement in performance metrics without multiple systematic readings. The use of advanced image processing techniques resulting from deep learning in this context represents a promising way to help diagnose brain cancer. The classifier was combined with the fuzzy system hybrid deformable model and superpixel-based adaptive clustering and the efficient feature extraction tool and Harish Hawks Optimization (HHO) Tetrolet Transform (TT) and the performance evaluation was very good overall performance steps. Experimental findings on MRI images indicate that the ResNet CNN model achieved a high degree of perfect processing.