Directional anisotropic diffusion applied to segmentation of vessels in 3D images

Abstract

Anisotropic diffusion is a method which allows to reduce the noise in the image without blurring the frontiers between different regions. This process can be applied in medical image analysis to segment the different anatomical structures. In this article, we introduce a new implementation of the anisotropic diffusion which better preserves small structures like vessels in 3D images. This method is based on the explicit weighting of the diffusion in the directions of the gradient, and minimum and maximum curvatures. This algorithm gave good results on real medical images.