三维加权PFDK重建算法研究

Research on Three-Dimensional Weighted PFDK Reconstruction Algorithm

基于滤波反投影的Feldkamp-Davis-Kress(FDK)算法,具有数学形式简单、容易实现和计算速度快等优点,在医疗和工业等领域得到了广泛的应用.平行重排(PF DK)算法是FDK算法的一种推广,针对PFDK算法重建出的图像受锥角的影响加大的问题,给出一种三维加权PFDK图像重建算法,并研究了重排过程中径向插值间隔对重建图像质量的影响,分别采用三种不同插值总数(插值间隔分别是1单位,0.5单位,0.25单位)重排数据.实验结果表明给出的三维加权PFDK算法可有效减少锥角的影响,且当采用2倍插值总数时重建结果较好.

The original cone beam filtered back-projection algorithm （FDK） has been exten- sively employed in medical and industrial imaging applications, because of its mathematical form is simple, easy to implement and computing speed, and the PFDK （Rearrange the projection data then get reconstruction） is one algorithm of the extending FDK algorithms. Artefacts in images reconstructed by the PFDK algorithm deteriorate with increasing cone angle, to solve this problem, we give a three-dimensional weighted PFDK algorithm for image reconstruction, Simultaneously studying the effect to quality of reconstruction image from different interpolation interval in the radial direction, we compare the reconstructed results of using the total number of three different interpolation （interpolation interval are 1 unit, 0.5 units, 0.25 units respectively）. The experimental results showed that the impact of the cone angle can be effectively reduced by the given algorithm, and we can get satisfactory reconstruction when using two times the total number of interpolation.