Background: The extraction of brain tissue from magnetic resonance head images,\r\nis an important image processing step for the analyses of neuroimage data. The\r\nauthors have developed an automated and simple brain extraction method using an\r\nimproved geometric active contour model.\r\nMethods: The method uses an improved geometric active contour model which\r\ncan not only solve the boundary leakage problem but also is less sensitive to\r\nintensity inhomogeneity. The method defines the initial function as a binary level set\r\nfunction to improve computational efficiency. The method is applied to both our\r\ndata and Internet brain MR data provided by the Internet Brain Segmentation\r\nRepository.\r\nResults: The results obtained from our method are compared with manual\r\nsegmentation results using multiple indices. In addition, the method is compared to\r\ntwo popular methods, Brain extraction tool and Model-based Level Set.\r\nConclusions: The proposed method can provide automated and accurate brain\r\nextraction result with high efficiency
Loading....