Multiple Sclerosis Segmentation using Deep Learning Models : Comparative Study

Central Nervous System (CNS) has directly been affected by many demyelination diseases. Multiple Sclerosis (MS) is one among these diseases. Such a series pathologies could be explored of the CNS which can be imagined through Magnetic Resonance Imaging (MRI) scans is more prone to be affected. The progression of the disease could be determined by the detection of all (MS) lesions and especially their multiplication. This will also help to supervise the efficacy of a candidate treatment. Medical image segmentation is said to be another great contributor in the field of medicine. The recent methods like Deep Learning (DL), specifically, Convolutional Neural Networks (CNNs) associated with various applications has been excellent too. This study reviews the technique of MS Segmentation based on (DL) in MRI slices. This research study reviews several techniques of MS segmentation based on (DL) in MRI slices and the focus is on using U-Net architecture. It also focuses on simple adjustments to the well-known U-net and evaluates the impact of modifications. An overview of current (DL) based medical image segmentation techniques is provided to aid researchers address existing problems. Significant improvements in segmentation quality compared to competing methods are demonstrated by using the Dice metric.