受限视角投影图像重建的压缩恢复算法及改进

The Improvement of Squashing Algorithm for Limited Angle Projection Reconstruction

讨论了用于受限视角投影的压缩恢复算法的局限性,并指出其固有缺点是采样极不均匀,形成混迭,且不能靠增加投影数克服。提出改进的压缩恢复算法,先利用压缩恢复法求出初始图像,再估算缺失的投影数据,后者与原有的受限投影数据一起形成完全投影数据,并用熟知的卷积反投影法重建最后的图像。计算机仿真结果表明,用改进后的算法重建,其成像质量明显提高。

An improved squashing algorithm for image reconstruction from limited angle projection is presented here. The paper first introduces the squ- ashing algorithm for limited angle reconstruction by Reeds and Shepp, then gives an intuitive proof and analyzes the artifacts caused by their algorithm. Our analysis indicates that these artifacts including aliasing and tailing are inherent to the squashing algorithm, mainly by the uneven sampling in angle direction, and can not be alleviated by merely increasing the number of proj- ections. The essential of our new algorithm lies in that the image reconstructed via squashing algorithm is only used to evaluate the missing projection data, which are then combined with the original limited angle projections to form the 'complete data'. The final image is reconstructed with this 'complete' data via traditional convolved backprojection algorithm. Simulations show that the image quality is better than that of the squashing algorithm.