Brain Tumor Detection based on Multiple Deep Learning Models for MRI Images

Abstract

INTRODUCTION: Medical imaging techniques are used to analyze the inner workings of the human body. In today's scientific world, medical image analysis is the most demanding and rising discipline, with brain tumor being the most deadly and destructive kind of malignancy. A brain tumor is an abnormal growth of cells within the skull that disrupts normal brain function by damaging neighboring cells. Brain tumors are regarded as one of the most dangerous, visible, and potentially fatal illnesses in the world. Because of the fast proliferation of tumor cells, brain tumors kill thousands of people each year all over the world. To save the lives of thousands of individuals worldwide, prompt analysis and automated identification of brain tumors are essential.
 OBJECTIVES: To design a enhanced deep learning model for brain tumor detection and classification from MRI analysis.
 METHODS: The proposed models Densenet-121, Resnet-101 Mobilenet-V2 is used to perform the task of Brain tumor detection for multi- class classification.
 RESULTS: The proposed models achieved an accuracy of up to 99% in our evaluations, and when compared to competing models, they yield superior results.
 CONCLUSION: The MRI image collection has been used to train deep learning models. The experimental findings show that the Densnet-121 model delivers the highest accuracy (99%) compared to other models. The system will have significant applications in the medical field. The presence or absence of a tumour can be ascertained using the proposed method.