Screening and staging of chronic obstructive pulmonary disease with deep learning based on chest X-ray images and clinical parameters.

BACKGROUND: Chronic obstructive pulmonary disease (COPD) is underdiagnosed with the current gold standard measure pulmonary function test (PFT). A more sensitive and simple option for early detection and severity evaluation of COPD could benefit practitioners and patients. METHODS: In this multicenter retrospective study, frontal chest X-ray (CXR) images and related clinical information of 1055 participants were collected and processed. Different deep learning algorithms and transfer learning models were trained to classify COPD based on clinical data and CXR images from 666 subjects, and validated in internal test set based on 284 participants. External test including 105 participants was also performed to verify the generalization ability of the learning algorithms in diagnosing COPD. Meanwhile, the model was further used to evaluate disease severity of COPD by predicting different grads. RESULTS: The Ensemble model showed an AUC of 0.969 in distinguishing COPD by simultaneously extracting fusion features of clinical parameters and CXR images in internal test, better than models that used clinical parameters (AUC = 0.963) or images (AUC = 0.946) only. For the external test set, the AUC slightly declined to 0.934 in predicting COPD based on clinical parameters and CXR images. When applying the Ensemble model to determine disease severity of COPD, the AUC reached 0.894 for three-classification and 0.852 for five-classification respectively. CONCLUSION: The present study used DL algorithms to screen COPD and predict disease severity based on CXR imaging and clinical parameters. The models showed good performance and the approach might be an effective case-finding tool with low radiation dose for COPD diagnosis and staging.

circRNA-miRNA-mRNA regulatory network in human lung cancer: an update.

Circular RNAs, as hopeful diagnosis markers and therapeutic molecules, have been studied, probed and applied into several diseases, such as cardiovascular diseases, systemic lupus erythematosus, leukemia, pulmonary tuberculosis, and cancer especially. Recently, mounting evidence has supported that circRNAs play a key role in the tumorigenesis, progress, invasion and metastasis in lung cancer. Its special structure-3'-5' covalent loop-allow it to execute several special functions in both normal eukaryotic cells and cancer cells. Our review summaries the latest studies on characteristics and biogenesis of circRNAs, and highlight the regulatory functions about miRNA sponge of lung-cancer-related circRNAs. In addition, the interaction of the circRNA-miRNA-mRNA regulatory network will also be elaborated in detail in this review. Therefore, this review can provide a new idea or strategy for further development and application in clinical setting in terms of early-diagnosis and better treatment.

Oxymatrine­mediated maturation of dendritic cells leads to activation of FOXP3+/CD4+ Treg cells and reversal of cisplatin­resistance in lung cancer cells.

The dendritic cell (DC)­regulatory T (Treg) system serves a leading role in the immunosuppression of the tumor microenvironment, which is not conducive to radiotherapy and chemotherapy treatment for lung cancer. The present study aimed to investigate the effect of oxymatrine (OMT) on the DC­Treg system in the tumor microenvironment in vitro and to examine its mechanism. The expressions of CD83 antigen, T­lymphocyte activation antigen CD86, CD11 antigen­like family member C and major histocompatibility complex II in DCs were increased upon treatment with 1 mg/ml OMT, as detected by flow cytometry. Following pretreatment with OMT, the DCs mediated the forkhead box protein P3 overexpression in primitive cluster of differentiation 4+ T cells at the protein and mRNA expression levels. The expression levels of anti­inflammatory factors, including interleukin (IL)­10, tumor growth factor­ß, IL­35, and pro­inflammatory cytokines, including interferon­Î³, IL­12 and IL­2, in the co­culture supernatant were increased as measured by ELISA. When DCs and DC­Tregs were co­cultured with cisplatin­resistant A549 cells, the proportion of apoptosis in the co­culture groups was increased under treatment with cisplatin, which was detected by Annexin V/propidium Iodide staining and western blotting. The present results suggested that OMT may promote the maturation of DCs, mediate the differentiation of T cells into Treg cells, and reverse the resistance of tumor cells to cisplatin in vitro. It was suggested that OMT is an important adjunct to chemotherapy through the regulation of antitumor responses.

MicroRNA Regulation of Energy Metabolism to Induce Chemoresistance in Cancers.

Since "Warburg effect" has been firstly uncovered in cancer cells in 1956, mounting evidence has supported the molecular mechanism underlying the energy metabolism in induced chemoresistance in cancers. MicroRNAs can mediate fine-tuning of genes in physiological process. MicroRNAs' energy metabolic role in chemoresistance has been probed recently. In this review, we summarize 5 microRNAs in regulating glucose and lipid metabolism and other energy metabolism. They partially modulate chemoresistance to cancer treatments. Furthermore, we discuss the great therapeutic potential of metabolism-related microRNAs in novel combinatorial means to treat human cancers.

Oxymatrine and Cisplatin Synergistically Enhance Anti-tumor Immunity of CD8+ T Cells in Non-small Cell Lung Cancer.

Oxymatrine (OMT) has shown broad antitumor activities for the treatment of several types of cancers. However, little is known about its effect on anti-tumor immunity. Combination therapy is a potentially promising strategy of cancer to enhance anticancer activity, overcome drug resistance, and lower treatment failure rate. In the present study, we demonstrated that the combination of OMT with cisplatin (DDP) synergistically inhibited non-small cell lung cancer (NSCLC) cells growth when co-cultured with peripheral blood mononuclear cells in vitro. Furthermore, the combination of OMT with DDP significantly inhibited the growth of Lewis lung cancer (LLC) mouse xenograft tumors. Flow cytometry analysis revealed that OMT and DDP synergistically increase the CD8+/ regulatory T cells ratio and enhanced more CD8+ T cells secreted cytokines of IFN-γ, TNF-α, and IL-2 in vivo. Mechanistically, upregulation of miR-155 and downregulation of suppressor of cytokine signaling-1 (SOCS1) were confirmed as a target signaling pathway to positively regulate the anti-tumor response of CD8+ T cells. Overall, OMT in combination with DDP showed outstanding synergistic anti-tumor immunity, suggesting that this beneficial combination may offer a potential immunotherapy for NSCLC patients.