Randomized Iterative Reconstruction for Sparse View X-ray Computed Tomography

With the availability of more powerful computers, iterative reconstruction algorithms are the subject of an ongoing work in the design of more efficient reconstruction algorithms for X-ray computed tomography. In this work, we show how two analytical reconstruction algorithms can be improved by correcting the corresponding reconstructions using a randomized iterative reconstruction algorithm. The combined analytical reconstruction followed by randomized iterative reconstruction can also be viewed as a reconstruction algorithm which, in the experiments we have conducted, uses up to $35\%$ less projection angles as compared to the analytical reconstruction algorithms and produces the same results in terms of quality of reconstruction, without increasing the execution time significantly.