Segmentation of head CT-scan to calculate percentage of brain hemorrhage volume

摘要

Brain hemorrhage is a serious category of head injury that can have a fatal impact on brain function and performance. But sometimes the identification of cerebral hemorrhage can not be known immediately. So far, the identification of cerebral hemorrhage is done through CT Scan image observation that requires special skills. Therefore we need a certain method that can segment the CT Scan image quickly and automated. The goal is to obtain the image segmentation of brain bleeding more quickly and accurately. So patients with cerebral hemorrhage can immediately obtain medical treatment in accordance with the needs. The preprocessing process of CT Scan image starts from the preprocessing phase of the CT Scan image using color filtering, erosion and dilation methods. This stage is done to clarify the cerebral hemorrhage and eliminate the noise contained in the image. Then performed watershed and cropping segmentation to separate the skull bones of the skull with brain tissue. The next step is to improve the image quality using median filtering. Then the image is again segmented using the threshold method to separate the image of cerebral hemorrhage as the observed object. Last performed the calculation of area and volume percentage of bleeding in the brain. From the system test obtained the calculation of brain area has an average error of 1.13%. As for the test calculation of the area of bleeding has an average error of 11.17%.