Methodology to create 3D models of COVID-19 pathologies for virtual clinical trials

Purpose: We describe the creation of computational models lung pathologies indicative COVID-19 disease. The are intended for use in virtual clinical trials (VCT) task-specific optimization chest x-ray (CXR) imaging. Approach: Images patients confirmed by computed tomography were used to segment areas increased attenuation lungs, all compatible with ground glass opacities and consolidations. Using a modeling methodology, segmented converted polygonal meshes adapted fit lungs previously developed mesh thorax phantom. then voxelized resolution 0.5 mm × as input simulation framework generate radiographic images. Primary projections generated via ray tracing while Monte Carlo transport code was scattered radiation. Realistic sharpness noise characteristics also simulated, followed image processing. Example images at 120 kVp validation themodels reader study. Additionally, uploaded an Artificial Intelligence (AI) software detection COVID-19. Results: Nine associated created, covering range disease severity. realism experienced radiologists dedicated AI software. Conclusions: A methodology has been rapid generation realistic 3D large pathologies. can be basis VCTs testing triaging suspected cases.