ABSTRACT
The prevalence of pulmonary fibrosis is increasing with an aging population and its burden is likely to increase following COVID-19, with large financial and medical implications. As approved therapies in pulmonary fibrosis only slow disease progression, there is a significant unmet medical need. Hyperbaric oxygen (HBO) is the inhaling of pure oxygen, under the pressure of greater than one atmosphere absolute, and it has been reported to improve pulmonary function in patients with pulmonary fibrosis. Our recent study suggested that repetitive HBO exposure may affect biological processes in mice lungs such as response to wounding and extracellular matrix. To extend these findings, a bleomycin-induced pulmonary fibrosis mouse model was used to evaluate the effect of repetitive HBO exposure on pulmonary fibrosis. Building on our previous findings, we provide evidence that HBO exposure attenuates bleomycin-induced pulmonary fibrosis in mice. In vitro, HBO exposure could reverse, at least partially, transforming growth factor (TGF)-ß-induced fibroblast activation, and this effect may be mediated by downregulating TGF-ß-induced expression of hypoxia inducible factor (HIF)-1α. These findings support HBO as a potentially life-changing therapy for patients with pulmonary fibrosis, although further research is needed to fully evaluate this.
ABSTRACT
The novel coronavirus severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has caused a major pandemic outbreak recently. Various diagnostic technologies have been under active development. The novel coronavirus disease (COVID-19) may induce pulmonary failures, and chest X-ray imaging becomes one of the major confirmed diagnostic technologies. The very limited number of publicly available samples has rendered the training of the deep neural networks unstable and inaccurate. This study proposed a two-step transfer learning pipeline and a deep residual network framework COVID19XrayNet for the COVID-19 detection problem based on chest X-ray images. COVID19XrayNet firstly tunes the transferred model on a large dataset of chest X-ray images, which is further tuned using a small dataset of annotated chest X-ray images. The final model achieved 0.9108 accuracy. The experimental data also suggested that the model may be improved with more training samples being released. COVID19XrayNet, a two-step transfer learning framework designed for biomedical images.