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 ...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.展开更多
Pulmonary vessels extraction is a challenging task in clinical medicine. Many pulmonary diseases are accompanied by the changes of vessel diameters. The vessels and their branches, which exhibit much variability, are ...Pulmonary vessels extraction is a challenging task in clinical medicine. Many pulmonary diseases are accompanied by the changes of vessel diameters. The vessels and their branches, which exhibit much variability, are most important in performing diagnosis and planning the follow-up therapies. In this paper, we propose an efficient approach to pulmonary vessels extraction based on the curve evolution. This approach models the vessels as monotonically marching front under the speed field integrating both the region and the edge information where a new region speed function is designed and integrated with the edge based speed function. Due to the region based speed term, the front could even propagate in small narrow vessel branches. To further improve the segmentation results, a multi-initial fast marching algorithm is developed to fast implement the numerical solution, which may avoid the monotonically marching front leaking out of the weak boundary too earlier and also reduce the computational cost. The validity of our approach is demonstrated by CT pulmonary vessels extraction. Experiments show that the segmentation results by our approach, especially on the narrow thin vessel branches extraction, are more precise than that of the existing method.展开更多
文摘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Supported by the national Natural Science Foundation of China under Grant No.6 0 2 710 2 2 and the Creative Research Group Science Foundation of China under Grant No.6 0 0 2 4 30 1
文摘Pulmonary vessels extraction is a challenging task in clinical medicine. Many pulmonary diseases are accompanied by the changes of vessel diameters. The vessels and their branches, which exhibit much variability, are most important in performing diagnosis and planning the follow-up therapies. In this paper, we propose an efficient approach to pulmonary vessels extraction based on the curve evolution. This approach models the vessels as monotonically marching front under the speed field integrating both the region and the edge information where a new region speed function is designed and integrated with the edge based speed function. Due to the region based speed term, the front could even propagate in small narrow vessel branches. To further improve the segmentation results, a multi-initial fast marching algorithm is developed to fast implement the numerical solution, which may avoid the monotonically marching front leaking out of the weak boundary too earlier and also reduce the computational cost. The validity of our approach is demonstrated by CT pulmonary vessels extraction. Experiments show that the segmentation results by our approach, especially on the narrow thin vessel branches extraction, are more precise than that of the existing method.
