Design and Development of 3D Brain MRI System Using Deep Neural Networks

Abstract

A Brain tumor is otherwise known as intracranial tumor. It is a formation of abnormal cells within the brain. A tumor cells grows continuously in the brain and destroys the cells in that specific region causing brain damage. The main problem in the tumor detection is that some normal brain cells tend to behave as tumor cell which leads to misclassification or unwanted brain surgery. A great challenge for the researchers is to identify the region and appropriate tumor mass. Due to this main reason, automated classifications are acquired for the early detection of brain tumor. In this research work, two standard datasets were used to test the developed classification algorithms. In this study, four different deep learning models were utilized to identify the accurate fit model to classify the brain tumor. From the results, it was observed that googlenet has achieved maximum mean classification accuracy of 98.2%, sensitivity 98.67% and specificity 96.17%. Our proposed model can be used to classify the brain tumor more accurately and effectively.