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.

One hundred twenty-seven 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.

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 1.56 cm ± 0.83 vs. MP 4.05 cm ± 2.40, p < 0.001) and higher proportion of positioning accuracy (AP 99% vs. MP 92%), resulting in 16% radiation dose reduction (AP 6.1 mSv ± 1.3 vs. MP 7.3 mSv ± 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.

The AI-based automatic positioning and centering in CT imaging is a promising new technique for reducing radiation dose and optimizing imaging workflow and image quality in imaging the chest.

• The AI-based automatic positioning (AP) operation was successful for all patients in our study.

• AP method reduced the total positioning time by 28% compared with the manual positioning (MP).

• AP method had less patient off-center distance and higher proportion of positioning accuracy than MP method, resulting in 16% radiation dose reduction and 9% image noise reduction in erector spinae.

• Artificial intelligence
• Coronavirus
• Radiation dosage
• Tomography

AIM: To define the benefits of three-dimensional video-assisted thoracoscopic esophagectomy (3D-VATE) over 2D-VATE for esophageal cancer.

METHODS: A total of 93 patients with esophageal cancer including 45 patients receiving 3D-VATE and 48 receiving 2D-VATE were evaluated. Data related to patient and cancer characteristics, operating time, intraoperative bleeding, morbidity and mortality, postoperative inflammatory markers, Numerical Rating Scale for postoperative pain, Constant-Murley rating system for shoulder recovery and oxygenation index (OI) were collected. All medical records were retrieved from a prospectively maintained oncological database at our institution. A retrospective study was performed to compare the short-term surgical outcomes between the two groups.

RESULTS: No significant differences were found between the two groups in either morbidity or mortality (P = 0.328). An enhanced surgical recovery was noted in the 3D group as indicated by shortened thoracoscopic operation time (3D vs 2D: 68 ± 13.79 min vs 83 ± 13 min, P < 0.01), minor intraoperative blood loss (3D vs 2D: 68.2 ± 10.7 mL vs 89.8 ± 10.4 mL, P < 0.01), earlier chest tube removal (3D vs 2D: 2.67 ± 1.01 vs 3.75 ± 1.15 d, P < 0.01), shorter length of hospital stay (3D vs 2D: 9.07 ± 2.00 vs 10.85 ± 3.40 d, P < 0.01), lower in-hospital expenses (3D vs 2D: 74968.4 ± 9637.8 vs 86211.1 ± 8519.7 RMB, P < 0.01), lower pain intensity (P < 0.01) and faster recovery of the left shoulder function (P < 0.01). Better preservation of the pulmonary function was also found in the 3D group as the decline of the OI post operation was significantly lower than that of the 2D group (P < 0.01). Changes of postoperative inflammatory markers, including procalcitonin [postoperative days (PODs) 4 and 7: P < 0.01], peripheral granulocytes (PODs 1, 4 and 7: P < 0.01) and hypersensitive C-reactive protein (POD 4: P < 0.01) in 3D-VATE patients were less than those in the 2D group. Moreover, utilization of the 3D technique extended the dissection of the thoracic lymph nodes (P < 0.01), with better exposure of nodes in the left recurrent laryngeal nerve (P = 0.031).

CONCLUSION: 3D-VATE could be a more viable technique over 2D-VATE in terms of short-term outcomes for patients with esophageal cancer.

• Esophageal cancer
• Three-dimensional video-assisted thoracoscopic esophagectomy
• Two-dimensional video-assisted thoracoscopic esophagectomy
• Surgical outcomes

• Aged
• C-Reactive Protein/metabolism
• China
• Databases, Factual
• Esophageal Neoplasms/diagnosis
• Esophageal Neoplasms/pathology
• Esophagectomy/methods
• Female
• Granulocytes/metabolism
• Hemorrhage
• Humans
• Image Processing, Computer-Assisted
• Imaging, Three-Dimensional/methods
• Inflammation
• Intraoperative Period
• Lymph Nodes/pathology
• Male
• Middle Aged
• Pain, Postoperative
• Prospective Studies
• Retrospective Studies
• Thoracoscopy/methods
• Treatment Outcome
• Video Recording