Helical CT Reconstruction from Wide Cone-Beam Angle Data Using ART

We report on new results on the use of Algebraic Reconstruction Techniques (ART) for reconstructing from helical cone-beam Computerized Tomography (CT) data. We investigate two variants of ART for this task: a standard one that considers a single ray in an iterative step and a block version which groups several cone-beam projections when calculating an iterative step. Both algorithms were implemented using modified Kaiser-Bessel window functions, also known as blobs, placed on the body-centered cubic (bcc) grid. The algorithms were used to reconstruct a modified 3D Shepp-Logan phantom from data collected for the PI-geometry for two different maximum cone-beam angles (±9.46◦ and ±18.43◦). Both scattering and quantum noise (for three different noise levels) were introduced to create noisy projections. The results presented here (for both noiseless and noisy data sets) point to the fact that, as opposed to filtered backprojection algorithms, the quality of the reconstructions produced by the ART methods does not suffer from the increase in the cone-beam angle.