各向异性PDE改进分水岭脑MRI图像分割算法

Algorithm of Segmentation of the Watershed for Brain MRI Images is Improved by Anisotropic Diffusion PDE

详细论述了各向异性扩散的PDE(偏微分方程)降噪算法原理,提出一种各向异性扩散的PDE降噪和分水岭算法相结合的脑MRI医学图像分割算法。采用各向异性扩散的PDE降低原始图像噪声,然后利用形态学算法对降噪后的图像进行形态学处理,通过形态学知识提取图像边界。利用图像的几何特征,去除非目标区域,再采用分水岭变换进行图像分割,并通过脑MRI图像验证了此方法的优势。实验结果进一步验证了其可行性。

In this paper discusses principles of the algorithm of the anisotropic diffusion PDE（partial differential equation） noise reduction.An image segmentation algorithm proposed of the anisotropic diffusion PDE noise reduction and watershed algorithm combining.First,that original image reduces noise by the anisotropic diffusion PDE;secondly,that use algorithms of morphological processing image of noise reduction after;finally,that extracted image boundary by morphological knowledge.We use geometric features of the image,and remove non—target area,and using watershed transformation segmentation of the image,and verify the advantages of the method by MRI image of brain.The results further validate the feasibility