Reducing Loss for Brain Tumour Detection and Classification in MRI using Deep Learning Techniques

Abstract

The signs of a brain tumour might be general or specific. The typical symptom is brought on by a tumour pressing against the brain or spinal cord. When the tumour has impacted a certain section of the brain and that area is not working correctly. Identification of brain tumours was extremely difficult and complicated due to the location, kind, shape, and size of the tumour in the brain. Brain tumour diagnosis is difficult since the tumor's size and resolution cannot be clearly evaluated in the early stages of growth. However, if a tumour is found and diagnosed early in the stage of tumour growth, there is a good chance that the patient will be treated. As a result, early tumour diagnosis is essential for successful treatment. To solve this problem, we suggested an automated method that can more help detect and classify three different types of brain tumours on MRI using deep learning techniques, faster RCNN+ResNet50.