为稳定地自动从MR颅脑图像中提取脑组织，在经典的BET算法(brain extraction tool)的基础上提出了一种改进算法。该算法简化了BET中用来保持曲线光滑的平滑力，改进了BET中将曲线演化到脑组织边界的扩张力，引入了图像梯度的作用使曲线在脑组织内部演化快，在脑组织边界演化慢从而得到更好的结果。改进算法对100个临床病例的真实MR图像进行处理都得到理想的结果，相比之下BET算法有8例不成功。可见改进算法在处理真实MR图像时比经典BET算法更为稳定。

To extract the brain from cerebral MR image automatically and stably, an improved BET (brain extraction tool) algorithm is proposed in this paper. The improved algorithm simplifies the smoothing force used in BET which makes the contour of edge smooth and modifies the expansionary force used in BET to evolve the edge of brain according to the intensity distribution and the gradient of images. The modified expansionary force puts the contour fast when the contour is in the brain and puts the contour slowly when the contour is close to the edge of brain. The experiment results of the MR images from 100 patients processed by the improved algorithm are satisfying, but BET leads to 8 unsatisfying results whatever the parameters are set as, which shows the improved algorithm is more robust than BET algorithm when processing real MR images.