Beam Geometry and Input Dimensionality: Impact on Sparse-Sampling Artifact Correction for Clinical CT with U-Nets

TL;DR

This paper investigates how beam geometry and input data dimensionality affect the performance of U-Nets in correcting sparse-sampling artifacts in clinical CT scans, finding 2D axial slices yield the best results.

Contribution

It systematically compares the impact of different beam geometries and input data dimensions on artifact correction performance using U-Nets in clinical CT imaging.

Findings

2D U-Nets on axial slices outperform 2.5D and 3D inputs.

Beam geometry influences artifact correction effectiveness.

Input dimensionality significantly affects model performance.

Abstract

This study aims to investigate the effect of various beam geometries and dimensions of input data on the sparse-sampling streak artifact correction task with U-Nets for clinical CT scans as a means of incorporating the volumetric context into artifact reduction tasks to improve model performance. A total of 22 subjects were retrospectively selected (01.2016-12.2018) from the Technical University of Munich's research hospital, TUM Klinikum rechts der Isar. Sparsely-sampled CT volumes were simulated with the Astra toolbox for parallel, fan, and cone beam geometries. 2048 views were taken as full-view scans. 2D and 3D U-Nets were trained and validated on 14, and tested on 8 subjects, respectively. For the dimensionality study, in addition to the 512x512 2D CT images, the CT scans were further pre-processed to generate a so-called '2.5D', and 3D data: Each CT volume was divided into 64x64x64 voxel blocks. The 3D data refers to individual 64-voxel blocks. An axial, coronal, and sagittal cut through the center of each block resulted in three 64x64 2D patches that were rearranged as a single 64x64x3 image, proposed as 2.5D data. Model performance was assessed with the mean squared error (MSE) and structural similarity index measure (SSIM). For all geometries, the 2D U-Net trained on axial 2D slices results in the best MSE and SSIM values, outperforming the 2.5D and 3D input data dimensions.