Abstract
Rising computed tomography (CT) workloads require more efficient image interpretation methods. Digitally reconstructed radiographs (DRRs), generated from CT data, may enhance workflow efficiency by enabling faster radiological assessments. Various techniques exist for generating DRRs. We conducted a pilot study to explore which DRR technique best approaches the image quality of chest X-Rays (CXR). We quantitatively and qualitatively compared four DRR techniques. A retrospective convenience sample of 217 patients who underwent both ultra-low-dose (ULD) chest CT and CXR was used. Four DRRs were generated per ULDCT, and CheXNet, a neural network trained to detect 14 diseases, was applied to CXRs and DRRs to compute area under the curve (AUC) scores. For qualitative assessment, six radiologists rated the image quality of the four DRRs generated from six ULDCTs on a Likert scale from 1 to 6 ('not diagnostic quality' to 'diagnostic quality') and provided feedback, which was analysed using inductive category development. CheXNet's AUC for CXRs was 0.80, while DRR techniques ranged from 0.75 to 0.82 (p > 0.26). Radiologists rated the diagnostic quality of the DRRs between 3.0 and 3.5 on average. The SoftMip technique scored highest in both the quantitative (AUC = 0.82) and the qualitative (score = 3.5) evaluation. DRRs showed comparable disease detection performance to CXRs, suggesting non-inferiority. However, radiologists expressed concerns about DRR image quality, particularly in terms of resolution, noise, and overall look-and-feel. Addressing these limitations with advanced techniques may further align DRRs with the diagnostic standards of CXRs.