Magnetic Resonance Imaging (MRI) For Brain Tumor And Seizures Classification Using Recurrent Neural Network

Abstract

The aim of this paper is to use develop and evaluate a Magnetic Resonance Imaging (MRI) for brain tumor and seizures classification using Recurrent Neural Network (RNN). Medical Science in Image Processing is an emerging field which has proposed a lot of advanced techniques in detection and analysis of a particular disease. Treatment of brain tumors in recent years is getting more and more challenging due to complex structure, shape and texture of the tumor. Therefore, by advancing in image processing, various methodologies have been proposed to identify the tumors in the brain. The advancement in this field created an urge in me to research more on the techniques and methodologies developed for tumor extraction. Hence, we propose a system to extract Tumor from the brain using MRI images. This technique involves different image processing methodologies such as noise removal, filtering, segmentation and morphological operations. Extraction of Brain tumor can be accomplished successfully by performing these operations on MATLAB software. Cross-correlation is computed between the target variable vector and the tumor region to determine how pixels’ values of the tumor region are closely related using image processing and RNN technique achieving an accuracy of 99.71%