Brain Tumor Segmentation Using Machine Learning
Abstract
Among the brain tumors, glioblastoma is one of the most dangerous brain tumor that can lead to a very short life expectancy. MRI (Magnetic Resonance Imaging) is a widely used imaging technique to locate such tumors but the amount of data produced by MRI is huge which makes manual segmentation a very tedious task. Because of this, automatic methods are required but the variation in the structure and location of such tumors makes automatic segmentation a very challenging task. In this paper, we have proposed different algorithms of machine learning like KNN (k-nearest neighbor), watershed algorithm, and canny edge detection for extracting patches which can easily overcome this challenge. This would not only be used to detect the exact location of brain tumor but will also predictthe patient’s life-span.
Keywords:Brain Tumor, Glioblastoma, KNN, MRI (Magnetic Resonance Imaging), Pituitary, Watershed