Survey on Segmentation of Brain Abnormalities in MRI Scan Images

-Medical image segmentation plays an important role in disease monitoring, such as tumor growth, dosage control of medication, and radiation exposure in the human body. Image segmentation is a technique that involves partitioning an image into multiple segments or regions with a strong correlation with the region of interest in the given image to extract some useful information. Despite its importance, medical image segmentation is a challenging task due to the presence of several artifacts in the images. Traditional approaches to image segmentation, such as thresholding and region-growing, have limitations when faced with complex images and varied image characteristics. On the other hand, deep learning-based segmentation methods have shown promising results in recent years, but their effectiveness is still limited by challenges such as data scarcity and overfitting. Therefore, there is a need to explore and compare both approaches when used for medical image segmentation. This paper aims to apply a survey on traditional image processing techniques and deep learning approaches to improve brain abnormalities segmentation from medical images. This paper aims to explore and compare the performance of traditional and deep learning-based segmentation methods on medical images with various characteristics and complexities and tries to explore a pipeline that combines traditional and deep learning approaches to enhance the segmentation results. In this survey, we are going through the foremost common brain segmentation methods utilized to segment brain abnormalities from MRI brain pictures.