We conducted a systematic review and meta-analysis of the diagnostic performance of current deep learning algorithms for the diagnosis of lung cancer. We searched major databases up to June 2022 to include studies that used artificial intelligence to diagnose lung cancer, using the histopathological analysis of true positive cases as a reference. The quality of the included studies was assessed independently by two authors based on the revised Quality Assessment of Diagnostic Accuracy Studies. Six studies were included in the analysis. The pooled sensitivity and specificity were 0.93 (95% CI 0.85–0.98) and 0.68 (95% CI 0.49–0.84), respectively. Despite the significantly high heterogeneity for sensitivity (I² = 94%, p < 0.01) and specificity (I² = 99%, p < 0.01), most of it was attributed to the threshold effect. The pooled SROC curve with a bivariate approach yielded an area under the curve (AUC) of 0.90 (95% CI 0.86 to 0.92). The DOR for the studies was 26.7 (95% CI 19.7–36.2) and heterogeneity was 3% (p = 0.40). In this systematic review and meta-analysis, we found that when using the summary point from the SROC, the pooled sensitivity and specificity of DL algorithms for the diagnosis of lung cancer were 93% and 68%, respectively.

To perform a systematic review of the effect of blood glucose levels on 2-Deoxy-2-[18F]fluoro-D-glucose (18F-FDG) uptake in normal organs. We searched the MEDLINE, EMBASE and Cochrane databases through 22 April 2017 to identify all relevant studies using the keywords “PET/CT” (positron emission tomography/computed tomography), “standardized uptake value” (SUV), “glycemia,” and “normal.” Analysis followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses recommendations. Maximum and mean SUVs and glycemia were the main parameters analyzed. To objectively measure the magnitude of the association between glycemia and 18F-FDG uptake in different organs, we calculated the effect size (ES) and the coefficient of determination (R²) whenever possible. The literature search yielded 225 results, and 14 articles met the inclusion criteria; studies included a total of 2714 (range, 51–557) participants. The brain SUV was related significantly and inversely to glycemia (ES = 1.26; R² 0.16–0.58). Although the liver and mediastinal blood pool were significantly affected by glycemia, the magnitudes of these associations were small (ES = 0.24–0.59, R² = 0.01–0.08) and negligible (R² = 0.02), respectively. Lung, bone marrow, tumor, spleen, fat, bowel, and stomach 18F-FDG uptakes were not influenced by glycemia. Individual factors other than glycemia can also affect 18F-FDG uptake in different organs, and body mass index appears to be the most important of these factors. The impact of glycemia on SUVs in most organs is either negligible or too small to be clinically significant. The brain SUV was the only value largely affected by glycemia.

Chest imaging is often used as a complementary tool in the evaluation of coronavirus disease 2019 (COVID-19) patients, helping physicians to augment their clinical suspicion. Despite not being diagnostic for COVID-19, chest CT may help clinicians to isolate high suspicion patients with suggestive imaging findings. However, COVID-19 findings on CT are also common to other pulmonary infections and non-infectious diseases, and radiologists and point-of-care physicians should be aware of possible mimickers. This state-of-the-art review goal is to summarize and illustrate possible etiologies that may have a similar pattern on chest CT as COVID-19. The review encompasses both infectious etiologies, such as non-COVID viral pneumonia, Mycoplasma pneumoniae, Pneumocystis jiroveci, and pulmonary granulomatous infectious, and non-infectious disorders, such as pulmonary embolism, fat embolism, cryptogenic organizing pneumonia, non-specific interstitial pneumonia, desquamative interstitial pneumonia, and acute and chronic eosinophilic pneumonia.

Arrhythmogenic right ventricular cardiomyopathy was first described as a right ventricular disease that is an important cause of death in young adults. However, with the advent of advanced imaging, arrhythmogenic right ventricular cardiomyopathy has been found to commonly have biventricular involvement, and a small portion of patients have left ventricular–dominant forms. On the other hand, a number of primarily left ventricular disease such as sarcoid and myocarditis can be arrhythmogenic and have right ventricular involvement. A few recent publications on arrhythmogenic right ventricular cardiomyopathy cohorts have average left ventricular functions that are comparable to sarcoid or myocarditis cohorts. We review the current literature and compare these cohorts of patients, and call for left ventricular functional criteria for arrhythmogenic right ventricular cardiomyopathy as inherited arrhythmogenic cardiomyopathy.