Modern medical imaging technologies have revolutionized the visualization of the body for clinical examinations and medical interventions, as well as the visualization of the capabilities of a particular organ or tissue. Medical imaging attempts to reveal much more effectively the internal structures hidden by skin and bones and thus plays an important role in improving the diagnosis of disease, creating an overall sense of well-being for all. MRI brain segmentation is an important step from both clinical and neurobiological points of view, as it affects the final completion of the entire process. This model can be used to assess its effectiveness in the segmentation of MRI images of the brain. This chapter presents a cluster-based segmentation approach that uses soft computing techniques to segment regions of interest from MRI images. This study proposes an MRI image segmentation method from a human brain dataset using Fuzzy C-Means (FCM). Another approach to clustering based on genetic algorithm (GA) is used to segment brain tissue to avoid limiting the definition of initial clustering. The proposed model was tested, and the accuracy was calculated as a performance measure by comparing the underlying truths of the dataset presented in different figures. The proposed GA-based clustering provides greater accuracy than FCM clustering by randomly changing the clustering.