3D U-NET Convolutional Neural Network for Segmentation of Brain Tumour Tissues in Hgg and Lgg Magnetic Resonance Imageing

A brain scan is a picture of the inside anatomy of the brain. Usually the brain scans are MRI (Magnetic Resonance Imaging). MRI provides an unparalleled view inside the human body. For the treatment process, the segmentation of tumors from brain MRI is understood to be complicated and also crucial tasks. Because brain tumors have such a wide range of appearances and because tumor and normal tissues are so comparable, extracting tumor regions from brain images becomes difficult. Brain tumor segmentation using 3D MRI volumes is time consuming and the results drawn can have variability from user to user. As Convolutional Neural Network (CNN) has higher studying capacity. This paper proposes a method for the precise and correct delineation of tumor subregions, an automatic brain tumor segmentation method on which we can rely. For the working of the proposed project, we are working on a BRATS2020 dataset.