摘要
Objective To accurately extract pulmonary vessels on medical images. Methods An efficient vessel segmentation framework is presented, which includes a smoothing method and a extraction algorithm. The smoothing method is based on an improved coherence diffusion approach that integrates the second-order directional differential information. It can analyze weak edges such as narrow peak or ridge-like structures. Meanwhile, an improved extraction algorithm is proposed. It is based on a fast marching algorithm where a sorted sequence array and multi-initialization technique are applied. Results The improved coherence diffusion approach can precisely preserve important oriented patterns and remove noises on the images. Experimental results on several images show that the proposed method can effectively find the location of pulmonary vessels. Conclusion The segmentation method is accurate and fast that can be a useful tool for medical imaging applications.
Objective To accurately extract pulmonary vessels on medical images. Methods An efficient vessel segmentation framework is presented, which includes a smoothing method and a extraction algorithm. The smoothing method is based on an improved coherence diffusion approach that integrates the second-order directional differential information. It can analyze weak edges such as narrow peak or ridge-like structures. Meanwhile, an improved extraction algorithm is proposed. It is based on a fast marching algorithm where a sorted sequence array and multi-initialization technique are applied. Results The improved coherence diffusion approach can precisely preserve important oriented patterns and remove noises on the images. Experimental results on several images show that the proposed method can effectively find the location of pulmonary vessels. Conclusion The segmentation method is accurate and fast that can be a useful tool for medical imaging applications.
基金
TheworkwassupportedbytheNationalNaturalScienceFoundationofChina(No.60271022,60271025).
