Objectives The measurement of visceral fat (VF) is clinically important for the identification of individuals at high risk of visceral obesity-related health conditions. Bioelectrical impedance analysis (BIA) is a widely available and frequently used body composition assessment method, but there have been few validation studies for the measurement of VF. This validation study investigated agreement between BIA and CT for the assessment of VF in adults. Design Cross-sectional study. Setting Between 2015 and 2016 in China. Participants A total of 414 adults (119 men and 295 women) aged 40–82 years. Primary and secondary outcome measures CT-visceral fat area (VFA) was derived at the L2-3 and umbilicus level and VFA cut-offs for visceral obesity applied. BIA measurements of visceral fat level were compared with CT VFA findings using scatter plots and receiver operator characteristic (ROC) curves. Results Scatter plots showed poor agreement between BIA and CT-derived visceral fat measurements in both sexes (R=0.387–0.636). ROC curves gave optimum figures for sensitivity and specificity of 65% and 69% in women and 76% and 70% in men, respectively, for BIA to discriminate between adults with normal levels of VF and those with visceral obesity determined by CT. Conclusion BIA has limited accuracy for the assessment of VF in adults in practice when compared with the criterion method.

Purpose: In the present study, we aimed to evaluate the expression of programmed death-ligand 1 (PD-L1) in patients with non-small cell lung cancer (NSCLC) by radiomic features of ¹⁸F-FDG PET/CT and clinicopathological characteristics.Methods: A total 255 NSCLC patients (training cohort: n = 170; validation cohort: n = 85) were retrospectively enrolled in the present study. A total of 80 radiomic features were extracted from pretreatment ¹⁸F-FDG PET/CT images. Clinicopathologic features were compared between the two cohorts. The least absolute shrinkage and selection operator (LASSO) regression was used to select the most useful prognostic features in the training cohort. Radiomics signature and clinicopathologic risk factors were incorporated to develop a prediction model by using multivariable logistic regression analysis. The receiver operating characteristic (ROC) curve was used to assess the prognostic factors.Results: A total of 80 radiomic features were extracted in the training dataset. In the univariate analysis, the expression of PD-L1 in lung tumors was significantly correlated with the radiomic signature, histologic type, Ki-67, SUV_max, MTV, and TLG (p< 0.05, respectively). However, the expression of PD-L1 was not correlated with age, TNM stage, and history of smoking (p> 0.05). Moreover, the prediction model for PD-L1 expression level over 1% and 50% that combined the radiomic signature and clinicopathologic features resulted in an area under the curve (AUC) of 0.762 and 0.814, respectively.Conclusions: A prediction model based on PET/CT images and clinicopathological characteristics provided a novel strategy for clinicians to screen the NSCLC patients who could benefit from the anti-PD-L1 immunotherapy.

Objective: To investigate the diagnostic performance of deep learning (DL)-based vascular extraction and stenosis detection technology in assessing coronary artery disease (CAD). Methods: The diagnostic performance of DL technology was evaluated by retrospective analysis of coronary computed tomography angiography in 124 suspected CAD patients, using invasive coronary angiography as reference standard. Lumen diameter stenosis ≥50% was considered obstructive, and the diagnostic performances were evaluated at per-patient, per-vessel and per-segment levels. The diagnostic performances between DL model and reader model were compared by the areas under the receiver operating characteristics curves (AUCs). Results: In patient-based analysis, AUC of 0.78 was obtained by DL model to detect obstructive CAD [sensitivity of 94%, specificity of 63%, positive predictive value of 94%, and negative predictive value of 59%], While AUC by reader model was 0.74 (sensitivity of 97%, specificity of 50%, positive predictive value of 93%, negative predictive value of 73%). In vessel-based analysis, the AUCs of DL model and reader model were 0.87 and 0.89 respectively. In segment-based analysis, the AUCs of 0.84 and 0.89 were obtained by DL model and reader model respectively. It took 0.47 min to analyze all segments per patient by DL model, which is significantly less than reader model (29.65 min) (p < 0.001). Conclusion: The DL technology can accurately and effectively identify obstructive CAD, with less time-consuming, and it could be a reliable diagnostic tool to detect CAD. Advances in knowledge: The DL technology has valuable prospect with the diagnostic ability to detect CAD.