Brain damage detection using machine learning approach

Abstract

The diagnosis of brain tumours has sparked attention in several research fields recently. Since the human body has anatomical structure by nature, finding brain tumours is an extremely laborious and time-consuming task. Cells develop quickly and uncontrollably, which causes brain tumours. It may cause death if not addressed in the beginning stages. Although there have been many substantial efforts and encouraging results in this field, precise segmentation and classification remain difficult tasks. Because of the variability in tumour location, shape, and size, detecting brain tumours is a significant difficulty. One of the most crucial problems with artificial intelligence systems is medical diagnostics using image processing and machine learning. Magnetic resonance imaging (MRI) is one of the technologies frequently used to find tumours in the brain (MRI). It provides crucial details that are employed in the process of carefully scanning the internal organisation of the human body. The variety and intricacy of brain tumours make it difficult to classify MR images. Sigma sifting, versatile limit, and detection locale are a portion of the cycles in the recommended technique for finding a brain cancer in MR pictures.