Potential of digital chest radiography-based deep learning in screening and diagnosing pneumoconiosis: An observational study.

The diagnosis of pneumoconiosis is complex and subjective, leading to inevitable variability in readings. This is especially true for inexperienced doctors. To improve accuracy, a computer-assisted diagnosis system is used for more effective pneumoconiosis diagnoses. Three models (Resnet50, Resnet101, and DenseNet) were used for pneumoconiosis classification based on 1250 chest X-ray images. Three experienced and highly qualified physicians read the collected digital radiography images and classified them from category 0 to category III in a double-blinded manner. The results of the 3 physicians in agreement were considered the relative gold standards. Subsequently, 3 models were used to train and test these images and their performance was evaluated using multi-class classification metrics. We used kappa values and accuracy to evaluate the consistency and reliability of the optimal model with clinical typing. The results showed that ResNet101 was the optimal model among the 3 convolutional neural networks. The AUC of ResNet101 was 1.0, 0.9, 0.89, and 0.94 for detecting pneumoconiosis categories 0, I, II, and III, respectively. The micro-average and macro-average mean AUC values were 0.93 and 0.94, respectively. The accuracy and Kappa values of ResNet101 were 0.72 and 0.7111 for quadruple classification and 0.98 and 0.955 for dichotomous classification, respectively, compared with the relative standard classification of the clinic. This study develops a deep learning based model for screening and staging of pneumoconiosis is using chest radiographs. The ResNet101 model performed relatively better in classifying pneumoconiosis than radiologists. The dichotomous classification displayed outstanding performance, thereby indicating the feasibility of deep learning techniques in pneumoconiosis screening.

Long-noncoding RNA LINC00461 promotes proliferation and invasion of nonsmall cell lung cancer cells via targeting miR-518a-3p/WDR1 pathway.

Long noncoding RNAs (lncRNAs) are a class of RNAs participating in many biological processes such as imprinting, alternative splicing and RNA decay. Recently, lncRNAs have drawn a great deal of attention for their critical role in cancer progression. LINC00461, a newly identified lncRNA, has been reported to be significantly overexpressed in breast cancer and markedly expedited breast cancer progression. However, the specific role of LINC00461 in nonsmall cell lung cancer (NSCLC) remains unknown. In this study, we for the first time showed the biological functions of LINC00461 in NSCLC. Our results demonstrated that LINC00461 was significantly up-regulated in NSCLC tissues and cell lines. Furthermore, knockdown of LINC00461 inhibited NSCLC cell proliferation and invasion in vitro as well as suppressed tumor growth and metastasis in vivo. We also performed luciferase reporter assays and found that LINC00461 functioned as a sponge for miR-518a-3p and WDR1 was a target of miR-518a-3p. Taken together, we suggested an essential role of LINC00461/miR-518a-3p/WDR1 axis in NSCLC, which could be used as a potential therapeutic target for NSCLC treatment.

Catalpol inhibits TGF-ß1-induced epithelial-mesenchymal transition in human non-small-cell lung cancer cells through the inactivation of Smad2/3 and NF-κB signaling pathways.

Catalpol, one of the main active ingredients isolated from Rehmannia glutinosa, was reported to possess anticancer activity. However, the role of catalpol in transforming growth factor ß1 (TGF-ß1)-induced epithelial-mesenchymal transition (EMT) in human non-small-cell lung cancer (NSCLC) cells has not been elucidated. The objective of this study was to investigate the effect of catalpol on EMT in human NSCLC cells. Our results showed that catalpol significantly inhibited the TGF-ß1-induced cell migration and invasion of A549 cells, as well as repressed matrix metalloproteinase (MMP)2 and MMP9 expression induced by TGF-ß1 in A549 cells. In addition, catalpol markedly repressed the EMT process in A549 cells in response to TGF-ß1. Furthermore, catalpol prevented the activation of Smad2/3 and nuclear factor κB (NF-κB) signaling pathways induced by TGF-ß1 in A549 cells. In conclusion, these findings indicated that catalpol inhibits TGF-ß1-induced EMT in human NSCLC cells through the inactivation of Smad2/3 and NF-κB signaling pathways. Thus, catalpol may be a promising agent for the treatment of NSCLC.

LGR5 promotes hepatocellular carcinoma metastasis through inducting epithelial-mesenchymal transition.

The purpose of the present study was to investigate the prognostic value of Leucine-rich repeat-containing G-protein coupled receptor 5 (LGR5) in hepatocellular carcinoma (HCC) and its role in promoting HCC metastasis. The expression level of LGR5 in liver tumor tissues and adjacent non-tumor tissues were detected adopting immunohistochemistry (IHC), real-time PCR (RT-PCR) and western blot assays. Chi-square test was used to evaluate the correlation between LGR5 expression and clinicopathological characteristics. In addition, we assessed the relationship between LGR5 and two epithelial-mesenchymal transition (EMT) markers (E-cadherin and N-cadherin) in HCC tissues and cell lines. Our results showed that the expression of LGR5 was significantly higher in liver tumor tissues than in adjacent non-tumor tissues. Moreover, up-regulated LGR5 was associated with larger tumor diameter (>5cm, P=0.001), higher TNM stage (P=0.021), increased recurrence (P=0.023) and growing metastasis (P=0.030). Besides, we found that the expression level of LGR5 was correlated with E-cadherin and N-cadherin. In conclusion, up-regulated LGR5 in HCC patients is associated with malignant clinicopathological characteristics. LGR5 may promote HCC metastasis through inducting EMT process, and thus can be regarded as a candidate biomarker for prognosis and as a target in therapy.

Genetic association between the cyclin-dependent kinase inhibitor gene p27/Kip1 polymorphism (rs34330) and cancer susceptibility: a meta-analysis.

The p27 rs34330 (-79C/T) polymorphism has been widely studied for human cancer susceptibility. The current findings, however, still remained controversial. Therefore, we performed the meta-analysis to provide a more accurate result. Eligible studies were identified from PubMed database up to June 2015. The association of p27 rs34330 polymorphism and cancer susceptibility was estimated with odds ratios and corresponding 95% confidence intervals. The meta-analysis was performed with Stata 12. A total of ten studies with 11,214 cases and more than 8,776 controls were included in the meta-analysis (including breast, lung, thyroid, endometrial, and hepatocellular cancer). In pooled analysis, p27 gene rs34330 polymorphism significantly increased the cancer susceptibility. Subgroup analysis indicated that the elevated risk was observed under all the genetic models for Asians and under three genetic models for Caucasians. Results of sensitivity analysis were similar to the overall results. The results suggested that the p27 rs34330 polymorphism increased the cancer susceptibility, especially in Asians. Further well-designed and large sample size studies are warranted to verify the conclusion.

Molecular mechanism of hepatitis B virus (HBV) on suppression of raf kinase inhibitor protein (RKIP) expression.

Raf kinase inhibitor protein (RKIP) has been shown to be a suppressor of the mitogen-activated protein kinase pathway and is reported to be involved in human malignancy. However, the molecular mechanism of hepatitis B virus (HBV) in regulating RKIP expression is not yet clarified. In this study, we compared RKIP expression in 107 pairs of matched liver cancer and adjacent non-cancerous liver tissues. Among seven HBV-encoded proteins, we found HBV X (HBX) protein could significantly inhibit the expression level of RKIP, indicating that HBV could suppress RKIP expression through regulating HBX. To further elucidate the mechanism, analyses on transcriptional regulation and promoter methylation inhibition were conducted in Huh7 cells. Our results showed that HBX can interact with AP1 protein to inhibit the RKIP transcription. Moreover, we observed that the promoter methylation level of RKIP could be enhanced by HBV. In conclusion, our study revealed that RKIP could act as a molecular marker for HBV-infected liver cancer, but had no tumor-suppressing effect.