Search

Abstract Background This study aims to assess the performance of an established an AI algorithm trained on conventional polychromatic computed tomography (CT) images (CPIs) to detect pulmonary ground-glass nodules (GGNs) on virtual monochromatic images (VMIs), and to screen the optimal virtual monochromatic energy for the clinical evaluation of GGNs. Methods Non-enhanced chest SDCT images of patients with pulmonary GGNs in our clinic from January 2022 to December 2022 were continuously collected: adenocarcinoma in situ (AIS, n = 40); minimally invasive adenocarcinoma (MIA, n = 44) and invasive adenocarcinoma (IAC, n = 46). A commercial CAD system based on deep convolutional neural networks (DL-CAD) was used to process the CPIs, 40, 50, 60, 70, and 80 keV monochromatic images of 130 spectral CT images. AI-based histogram parameters by logistic regression analysis. The diagnostic performance was evaluated by the receiver operating characteristic (ROC) curves, and Delong’s test was used to compare the CPIs group with the VMIs group. Results When distinguishing IAC from MIA, the diagnostic efficiency of total mass was obtained at 80 keV, which was superior to those of other energy levels (P 0.05). Conclusion The AI algorithm trained on CPIs showed consistent diagnostic performance on VMIs. When pulmonary GGNs are encountered in clinical practice, 80 keV could be the optimal virtual monochromatic energy for the identification of preoperative IAC on a non-enhanced chest CT.

Abstract Background To determine whether maintaining ventilation during cardiopulmonary bypass (CPB) with a different fraction of inspired oxygen (FiO2) had an impact on the occurrence of postoperative pulmonary complications (PPCs). Methods A total of 413 adult patients undergoing elective cardiac surgery with CPB were randomly assigned into three groups: 138 in the NoV group (received no mechanical ventilation during CPB), 138 in the LOV group (received a tidal volume (VT) of 3–4 ml/kg of ideal body weight with the respiratory rate of 10–12 bpm, and the positive end-expiratory pressure of 5–8 cmH2O during CPB; the FiO2 was 30%), and 137 in the HOV group (received the same ventilation parameters settings as the LOV group while the FiO2 was 80%). Results The primary outcomes were the incidence and severity of PPCs during hospitalization. The composite incidence of PPCs did not significantly differ between the NoV (63%), LOV (49%) and HOV (57%) groups (P = 0.069). And there was also no difference regarding the incidence of PPCs between the non-ventilation (NoV) and ventilation (the combination of LOV and HOV) groups. The LOV group was observed a lower proportion of moderate and severe pulmonary complications (grade ≥ 3) than the NoV group (23.1% vs. 44.2%, P = 0.001). Conclusion Maintaining ventilation during CPB did not reduce the incidence of PPCs in patients undergoing cardiac surgery. Trial registration: Chinese Clinical Trial Registry ChiCTR1800015261. Prospectively registered 19 March 2018. http://www.chictr.org.cn/showproj.aspx?proj=25982