Preliminary brain region segmentation using FCM and graph cut for CT scan images

Brain segmentation is important in the field of neuropsychiatric disorders. With Computed Tomography (CT) scan being the gold standard in brain scan, brain segmentation in CT images is also very important in the detection of many pathology related to the brain. Fuzzy c-Means (FCM) is a popular method in data clustering and also in image segmentation due to it being robust. Graph cut is a segmentation algorithm that is able to separate the image into several partitions based on the similarity between each nodes in the image. In this paper, the CT scan images were first processed with FCM optimization and are separated into clusters based on pixel intensity. After that the post-FCM images were then loaded into the graph cut algorithm to separate the images into partitions, allowing users to manually select the appropriate partitions that best represent the brain region. The results showed that the images are less erroneous when they are clustered first with FCM before going through the graph cut algorithm.