Designing of Deep Learning based program for automatic detection of brain tumour using MRI data

Abstract

The essential organ of the human body is the brain, consisting of millions and millions of cells. But when these cells form abnormal groups due to their uncontrolled division, it is called a tumor. Brain tumors are further classified into two categories, benign (low-grade tumor) and malignant (high-grade tumor). Brain tumors are the most common life-threatening disease, which leads to immediate death in its highest grade or a very short lifespan. Thus, proper accurate detection and planning are crucial in improving the quality of life of people. In this work, MRI scanned images are used to determine whether the brain has a tumor or not. However, manually differentiating these images may lead to some errors and inaccurate results. Hence these trusted digital automatic classification schemes are nowadays an essential part of diagnosis and detection. Here, CNN architecture is implemented to build a simple model that is efficient in detecting of tumor and non-tumor images. The images are initially preprocessed and normalized, and then a Convolution model with dense layers is built to train and test the dataset. The training dataset accuracy and validation accuracy achieved are 89% and 77%, respectively, and the overall accuracy achieved by the model is 88% in a simple architecture. This advancement in deep learning algorithms has made tumor detection much more efficient, accurate and is a boon to the healthcare industry.