A deep-learning-based framework for identifying and localizing multiple abnormalities and assessing cardiomegaly in chest X-ray.

Accurate identification and localization of multiple abnormalities are crucial steps in the interpretation of chest X-rays (CXRs); however, the lack of a large CXR dataset with bounding boxes severely constrains accurate localization research based on deep learning. We created a large CXR dataset named CXR-AL14, containing 165,988 CXRs and 253,844 bounding boxes. On the basis of this dataset, a deep-learning-based framework was developed to identify and localize 14 common abnormalities and calculate the cardiothoracic ratio (CTR) simultaneously. The mean average precision values obtained by the model for 14 abnormalities reached 0.572-0.631 with an intersection-over-union threshold of 0.5, and the intraclass correlation coefficient of the CTR algorithm exceeded 0.95 on the held-out, multicentre and prospective test datasets. This framework shows an excellent performance, good generalization ability and strong clinical applicability, which is superior to senior radiologists and suitable for routine clinical settings.

Poor recovery of cardiac function in myocardial infarction patients with metabolic syndrome and microalbuminuria.

BACKGROUND: This study aimed to investigate the impact of metabolic syndrome (MetS) with microalbuminuria on the improvement of cardiac function after acute myocardial infarction (AMI). METHODS: Nondiabetic patients with acute ST segment elevation MI (STEMI) who underwent coronary revascularization from 2013 to 2017 were included. They were grouped according to history of MetS and microalbuminuria test results as follows: microalbuminuria/MetS group, normoalbuminuria/MetS group, microalbuminuria/no MetS group, and normoalbuminuria/no MetS group. Left ventricular ejection fraction (LVEF) and serum N-terminal pro-brain natriuretic peptide (NT-proBNP) levels at the 6­month follow-up were measured and the predictive value of MetS with microalbuminuria on recovery of cardiac function was assessed by multivariable logistic regression modeling. RESULTS: A total of 530 STEMI patients were included (average age = 66.6 years). Analysis of covariance showed that LVEF recovery in the normoalbuminuria/no MetS group was better than that of the normoalbuminuria/MetS, microalbuminuria/no MetS, and microalbuminuria/MetS groups (49.22% vs. 48.92% vs. 47.48% vs. 46.99%, respectively, p < 0.001) when acute phase LVEF was the covariable. The NT-proBNP level of the normoalbuminuria/no MetS group at the 6­month follow-up was lower than that of the microalbuminuria/MetS group (p < 0.001). Further regression analysis revealed that there was a lower probability of complete cardiac function recovery after 6 months in patients with microalbuminuria (odds ratio: 0.455) than in patients without microalbuminuria (95% CI: 0.316-0.655, p < 0.001). CONCLUSION: Although post-AMI cardiac function in MetS patients with microalbuminuria can be improved after revascularization, the improvement is not as good as that of patients without microalbuminuria, suggesting that clinical attention should be paid to this subgroup.

Improved Desulfurization Performance of Polyethyleneglycol Membrane by Incorporating Metal Organic Framework CuBTC.

In this paper, copper benzene-1,3,5-tricarboxylate (CuBTC) was incorporated into polyethylenglyol (PEG) to prepare a mixed matrix membrane (MMM) for pervaporation desulfurization. The characterization results showed that the prepared CuBTC particles had an ideal octahedral shape and micropores. The Cu2+ in CuBTC interacts with thiophene via π-complexation, thus enhancing the separation performance of the hybrid membranes. The effect of CuBTC content and the operating condition on the pervaporation performance of the MMMs was investigated. An optimal pervaporation separation performance was acquired with a permeation flux of 2.21 kg/(m2·h) and an enrichment factor of 8.79, which were increased by 100% and 39% compared with the pristine PEG membrane. Moreover, the CuBTC-filled PEG membrane showed a good stability in the long-term desulfurization under a high operating temperature of 75 °C for five days.