A comparison between manual and artificial intelligence-based automatic positioning in 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 (MP) method or an AI-based automatic positioning (AP) 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 automatic positioning method (AP group) for the follow-up scan. Radiation dose, patient positioning time and off-center distance, 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 operation was successful for all patients in the AP group and reduced the total positioning time by 28% compared with the MP group. Compared with the MP group, the 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 automatic 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.

The role of artificial intelligence in clinical imaging and workflows

“…In radiology, the precision of clinical decision-making depends on the the patient using automated positioning through AI machine learning algorithms. 9 Machine learning can be used to detect inadequate positioning of radiographs as well as assist in automated positioning for radiographs and computed tomography (CT). Deep learning (DL) classifiers demonstrated a 0.9 characteristic curve when detecting suboptimal positioning of neck radiographs versus 0.36 among technologists.…”

“…Deep learning (DL) classifiers demonstrated a 0.9 characteristic curve when detecting suboptimal positioning of neck radiographs versus 0.36 among technologists 10 . Automated positioning of the patient in CT has been pitted against manual positioning in human medicine 9 . AI automation reduced positioning time by 28% and increased positioning accuracy to 99% (vs. 92% for manual positioning).…”

“…AI automation reduced positioning time by 28% and increased positioning accuracy to 99% (vs. 92% for manual positioning). The better positioning also resulted in a 9% reduction of image noise 9 . Automated positioning could be applied to magnetic resonance imaging as well as radiography equipment for studies where the veterinary patient is anesthetized.…”

“…al. showed a 16% reduction in radiation exposure to the patient using automated positioning through AI machine learning algorithms 9 . Machine learning can be used to detect inadequate positioning of radiographs as well as assist in automated positioning for radiographs and computed tomography (CT).…”

The impact of vertical off-centering on image noise and breast dose in chest CT with organ-based tube current modulation: A phantom study

“…Despite the technical solutions for CT optimization, the role of radiographers remains important for achieving optimal results. Several studies have shown harmful effects of patient vertical off-centering on patient dose and image quality due to misalignment of beam-shaping filters and impacts of geometric magnification or minification of patient structures in planning radiographs [20][21][22][23][24][25][26][27][28][29][30][31][32][33]. CT manufacturers have developed technical tools to prevent patient off-centering and to reduce its effects on patient dose and image quality [30,32,34,35].…”