Severe, but not mild to moderate, non-alcoholic fatty liver disease associated with increased risk of subclinical coronary atherosclerosis.

BACKGROUND: Non-alcoholic fatty liver disease (NAFLD) is associated with high risk of cardiovascular disease. The prevalence is increasing to 45-65% in the general population with routine health check-up, and most subjects have the mild degree NAFLD in recent years. Moreover, there are no studies on the association between NAFLD severity and coronary atherosclerosis in the real-world setting by ultrasonography. METHODS: The aim of this study was to determine the relationship between the severity of NAFLD and subclinical coronary atherosclerosis. Overall, 817 subjects meet criteria for NAFLD were enrolled in the retrospective cohort study (155 subjects were excluded). The severity of NAFLD was divided into the normal, mild, moderate and severe degree based on the finding of abdominal ultrasonography. The assessment of coronary atherosclerosis was based on CAC scan/coronary CT angiography finding in terms of CAC score ≧ 100, CAC score ≧ 400, CAD-RADS ≧ 3 and presence of vulnerable plaque(s). RESULTS: A significant linear trend was observed between the severity of NAFLD and subclinical coronary atherosclerosis. Compared with the reference group (including normal, mild, and moderate NAFLD), severe degree NAFLD was the independently associated risk of subclinical coronary atherosclerosis in term of CAC score ≧ 100, CAC score ≧ 400, CAD-RADS ≧ 3 and presence of vulnerable plaque(s) based on binary logistic regression after adjustment for FRS score and body fat percentage. CONCLUSIONS: Severe degree, but not mild to moderate, was associated with high risk of subclinical coronary atherosclerosis, independently of FRS score and body-fat percentage.

Performance and educational training of radiographers in lung nodule or mass detection: Retrospective comparison with different deep learning algorithms.

ABSTRACT: The aim of this investigation was to compare the diagnostic performance of radiographers and deep learning algorithms in pulmonary nodule/mass detection on chest radiograph.A test set of 100 chest radiographs containing 53 cases with no pathology (normal) and 47 abnormal cases (pulmonary nodules/masses) independently interpreted by 6 trained radiographers and deep learning algorithems in a random order. The diagnostic performances of both deep learning algorithms and trained radiographers for pulmonary nodules/masses detection were compared.QUIBIM Chest X-ray Classifier, a deep learning through mass algorithm that performs superiorly to practicing radiographers in the detection of pulmonary nodules/masses (AUCMass: 0.916 vs AUCTrained radiographer: 0.778, P < .001). In addition, heat-map algorithm could automatically detect and localize pulmonary nodules/masses in chest radiographs with high specificity.In conclusion, the deep-learning based computer-aided diagnosis system through 4 algorithms could potentially assist trained radiographers by increasing the confidence and access to chest radiograph interpretation in the age of digital age with the growing demand of medical imaging usage and radiologist burnout.