Brain MRI segmentation is an important task in many clinical applications. Various approaches for brain analysis rely on accurate segmentation of anatomical regions. Quantitative analysis of brain MRI has been used extensively for the characterization of brain disorders such as Alzheimer’s disease, epilepsy, schizophrenia, multiple sclerosis (MS), cancer, and infectious and degenerative diseases. Manual Segmentation requires outlining structures slice-by-slice, and is not only expensive and tedious but also inaccurate due to human error. Not only that, segmentation is extremely time-consuming and initial hours of brain tumor and strokes are crucial to diagnosing. Therefore, there is a need for automated segmentation methods to provide accuracy close to that of expert ratters’ with high consistency. We propose to create a Deep Learning based Brain Segmentation web application that would fully automate the process of Brain Segmentation to help in solving out those cases which are generally missed by the human eye and save time.
Volume: Volume 24
Issues: Issue 4
Keywords: Mask R-CNN, Brain Tumor, medical, deep learning, python, magnetic resonance imaging, image segmentation.