An Efficient Approach to Pulmonary Vessels Extraction Based on Curve Evolution

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.

An eikonal equation based path planning method using polygon decomposition and curve evolution

Path planning is a key technique of autonomous navigation for robots,and the velocity field is an important part.Constructing velocity field in a complex workspace is still challenging.In this paper,an inner normal guided segmentation algorithm in a complex polygon is proposed to decompose the complex workspace in this paper.The artificial potential field model based on probability theory is then used to calculate the potential field of the decomposed workspace,and the velocity field is obtained by utilizing the potential field of this workspace.Path optimization is implemented by curve evolution,during which the internal force generated in the smoothing process of the initial path by a mean filter and the external force is obtained from the gradient of the workspace potential field.The parameter selection principle is deduced by analyzing the influence of several parameters on the path length and smoothness.Simulation results show that the designed polygon decomposition algorithm can effectively segment complex workspace and that the path optimization algorithm can shorten and smoothen paths.

Statistical segmentation model on lattices

To reduce the difficulty of implementation and shorten the runtime of the traditional Kim-Fisher model, an entirely discrete Kim-Fisher-like model on lattices is proposed. The discrete model is directly built on the lattices, and the greedy algorithm is used in the implementation to continually decrease the energy function. First, regarding the gray values in images as discrete-valued random variables makes it possible to make a much simpler estimation of conditional entropy. Secondly, a uniform method within the level set framework for two-phase and multiphase segmentations without extension is presented. Finally, a more accurate approximation to the curve length on lattices with multi-labels is proposed. The experimental results show that, compared with the continuous Kim-Fisher model, the proposed model can obtain comparative results, while the implementation is much simpler and the runtime is dramatically reduced.

PULMONARY VESSEL EXTRACTION BASED ON COHERENCE DIFFUSION AND FAST MARCHING

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.

Some Geometric Invariants of Pseudo-Spherical Evolutes in the Hyperbolic 3-Space

In this paper,we study the pseudo-spherical evolutes of curves in three dimensional hyperbolic space.We use techniques from singularity theory to investigate the singularities of pseudo-spherical evolutes and establish some relationships between singularities of these curves and geometric invariants of curves under the action of the Lorentz group.Besides,we defray with illustration some computational examples in support our main results.