A Review of the Automated Techniques for Brain Tumor Detection Using MR Images

In the field of medical diagnostics, identifying brain tumors through imaging is a tough task for radiologists. Sorting out the complexities of finding brain tumors in MRI pictures includes many steps. One important part is segmentation, which helps classify and understand the images. Manually segmenting brain MR images is no easy task and demands a lot of time from experts. The lack of repeatability in this process highlights the need for an automated approach to efficiently segment White Matter (WM), Gray Matter (GM), and Cerebrospinal Fluid (CSF) in the brain more quickly. Accurate segmentation is vital, as misidentifying diseases can have serious consequences. To tackle these challenges this research aims to explore and evaluate the strengths and limitations of existing segmentation techniques discussed in literature. This article enriches the readers with a comprehensive view of the subject, shedding light on innovative aspects of employing various machine learning and image segmentation techniques required for the detection of brain tumors. However, it is important to note that the introduction of a novel technique falls outside the scope of this study as we will not develop any new method but evaluate and review existing techniques.