A survey of methods for brain tumor segmentation-based MRI images

Abstract

Brain imaging techniques play an important role in determining the causes of brain cell injury. Therefore, earlier diagnosis of these diseases can be led to give rise to bring huge benefits in improving treatment possibilities and avoiding any potential complications that may occur to the patient. Recently, brain tumor segmentation has become a common task in medical image analysis due to its efficacy in diagnosing the type, size, and location of the tumor in automatic methods. Several researchers have developed new methods in order to obtain the best results in brain tumor segmentation, including using deep learning techniques such as the convolutional neural network (CNN). The goal of this survey is to present a brief overview of magnetic resonance imaging (MRI) modalities and discuss common methods of brain tumor segmentation from MRI images, including brain tumor segmentation using deep learning techniques, as well as the most important contributions in this field, which have shown significant improvements in recent years. Finally, we focused in summary on the building blocks of the CNN algorithms used for image segmentation. In entire survey methodology, it has been observed that hybrid techniques and CNN-based segmentation are more effective for brain tumor segmentation from MRI images.