Identification of Brain Tumor on Mri images with and without Segmentation using DL Techniques

Abstract

Brain cancer is a critical disease that results in the deaths of many individuals. Early detection and classification of brain tumors is essential for effective treatment and improved patient outcomes. However, current manual examination of MRI images for tumor detection can be time-consuming and imprecise. In this project, we propose a computer-based system that utilizes image processing techniques and convolutional neural networks (CNNs) for accurate and efficient brain tumor detection and classification. Our system involves several stages, including image pre-processing, segmentation, feature extraction, and classification. By training a CNN on a large dataset of MRI images with known tumor types, our system can accurately detect and classify brain tumors based on extracted features. The results of our experiments demonstrate the effectiveness of our systemin accurately detecting and classifying brain tumors, with potential to greatly improve the accuracy and speed of diagnosis, and ultimately lead to improved patient outcomes. To explicitly depict the tumor region, we have also added the segmentation procedure.