Artificial intelligence-based patient positioning for faster, more accurate and efficient CT imaging for COVID-19 patients

Abstract Objective: To analyze and compare the imaging workflow, radiation dose and image quality for COVID-19 patients examined using either the conventional manual positioning method or an AI-based positioning method. Materials and Methods: 127 adult COVID-19 patients underwent chest CT scans on a CT scanner using the same scan protocol except with the manual positioning (MP group) for the initial scan and an AI-based positioning method (AP group) for the follow-up scan. Radiation dose, patient off-center distance, examination and positioning time of the two groups were recorded and compared. Image noise and signal-to-noise ratio (SNR) were assessed by three experienced radiologists and were compared between the two groups.Results: The AP group reduced the total positioning time and examination time by 28% and 8%, respectively compared with the MP group. Compared with the MP group, AP group had significantly less patient off-center distance (AP:1.56cm ± 0.83 vs. MP: 4.05cm ± 2.40, p<0.001) and higher proportion of positioning accuracy (AP: 99% vs. MP: 92%), resulted in 16% radiation dose reduction (AP: 6.1mSv ± 1.3 vs. MP: 7.3mSv ± 1.2, p<0.001) and 9% image noise reduction in erector spinae and lower noise and higher SNR for lesions in the pulmonary peripheral areas.Conclusion: The AI-based positioning and centering in CT imaging is a promising new technique for reducing radiation dose, optimizing imaging workflow and image quality in imaging the chest. This technique has important added clinical value in imaging COVID-19 patients to reduce the cross-infection risks.