利用Gibbs距离图Snake模型分割医学图像

Medical image segmentation based on Gibbs morphological gradient and distance map Snake model

目的提出利用Gibbs距离图Snake模型分割医学图像的算法。该方法能克服医学图像固有的噪声和伪边缘干扰,收敛到正确的目标轮廓。方法首先推导Gibbs形态学梯度,然后提出基于Gibbs形态学梯度的距离图Snake模型的医学图像分割方法。结果本文所提出的算法克服了传统距离图Snake模型的上述缺点。结论本文所提出的方法分割结果鲁棒性好,分割过程无须人工干预,适合应用于临床医学图像分割。

Objective To propose a new algorism for medical image segmentation based on Gibbs morphological gradient and distance map （DM） Snake model, which allows identification of the correct contours of the objects when processing medical images with noises and pseudo-edges. Methods Gibbs morphological gradient was deduced and the method for image segmentation based on Gibbs morphological gradient and distance map Snake model was presented. Results This new medical image segmentation algorithm proved to effectively suppress the noises and pseudo-edges when calculating distance map. Conclusion The proposed algorism is robust for image noise suppression and allows easy implementation in clinical image segmentation without the need of user interventions.