Architectural Model of Deep Convolution Neural Network Approach for Brain Tumor Prediction

Magnetic Resonance Imaging (MRI) is most commonly used technique to detect a tumor by physicians in medical science. The MRI images are three-dimensional images with the number of slices that are analyzed to identify the defective cells in the naked eye that leads to a time-consuming process. Machine Learning (ML) techniques are investigated as a solution to improve tumor identification in a better way. Early and accurate detection is crucial for effective treatment planning and improving patient outcomes. Traditionally, brain tumor diagnosis relies on manual analysis of MRI (Magnetic Resonance Imaging) scans by radiologists, which can be time-consuming and prone to human error. The advent of deep learning, particularly Convolutional Neural Networks (CNNs), has opened new avenues for automating and improving the accuracy of brain tumor prediction. In this paper, we study the Convolutional Neural Network(CNN) model which is popular in image analysis. Similar way, we develop a CNN model to process and classify the MRI images to detect the type of brain tumor. We examine the model’s performance by using 5712 MRI images from a standard dataset available in the public domain. The aim of the work is to classify the tumor in four classes like: Glioma, Meningioma, Pituitary and No Tumour using the proposed CNN model. Our model follows data preprocessing, image encoding, filtering and classification. The proposed model scores 78% accuracy as its performance in the dataset which needs more investigations and comparison with other techniques in further study.