No abstract

The goal of diagnosing the coronavirus disease 2019 (COVID‐19) from suspected pneumonia cases, that is, recognizing COVID‐19 from chest X‐ray or computed tomography (CT) images, is to improve diagnostic accuracy, leading to faster intervention. The most important and challenging problem here is to design an effective and robust diagnosis model. To this end, there are three challenges to overcome: (1) The lack of training samples limits the success of existing deep‐learning‐based methods. (2) Many public COVID‐19 data sets contain only a few images without fine‐grained labels. (3) Due to the explosive growth of suspected cases, it is urgent and important to diagnose not only COVID‐19 cases but also the cases of other types of pneumonia that are similar to the symptoms of COVID‐19. To address these issues, we propose a novel framework called Unsupervised Meta‐Learning with Self‐Knowledge Distillation to address the problem of differentiating COVID‐19 from pneumonia cases. During training, our model cannot use any true labels and aims to gain the ability of learning to learn by itself. In particular, we first present a deep diagnosis model based on a relation network to capture and memorize the relation among different images. Second, to enhance the performance of our model, we design a self‐knowledge distillation mechanism that distills knowledge within our model itself. Our network is divided into several parts, and the knowledge in the deeper parts is squeezed into the shallow ones. The final results are derived from our model by learning to compare the features of images. Experimental results demonstrate that our approach achieves significantly higher performance than other state‐of‐the‐art methods. Moreover, we construct a new COVID‐19 pneumonia data set based on text mining, consisting of 2696 COVID‐19 images (347 X‐ray + 2349 CT), 10,155 images (9661 X‐ray + 494 CT) about other types of pneumonia, and the fine‐grained labels of all. Our data set considers not only a bacterial infection or viral infection which causes pneumonia but also a viral infection derived from the influenza virus or coronavirus.

BackgroundPer- and polyfluoroalkyl substances (PFAS) are persistent organic pollutants that have become globally ubiquitous in humans and the environment. In utero PFAS exposure is associated with neurodevelopmental effects; however, the mechanism is poorly understood. Brain-derived neurotrophic factor (BDNF) signaling is critical to fetal neurodevelopment during pregnancy and maintains important regulatory roles later in life. This study aims to characterize placental BDNF signaling and investigate whether PFAS exposure disrupts the signaling pathway in placental trophoblast cells.MethodsThe expression and localization of BDNF receptors–p75NTR and TrkB–in first trimester and term human placentas and trophoblast cells were investigated by immunofluorescence staining. To assess the effects of PFAS exposure on the BDNF pathway, BeWo cells were treated with PFAS mixtures that mimicked blood levels in a highly exposed population and major PFAS compounds in the mixture at 0.01, 0.1, 1, and 10 µM concentrations. Changes in pro-BDNF levels and phosphorylation of TrkB receptors were examined by Western blot.ResultsIn first trimester human placentas, TrkB and p75NTR receptors were primarily localized to syncytiotrophoblast and cytotrophoblast cells. At term, TrkB and p75NTR receptors were primarily observed in the placental villous stroma. TrkB receptor staining in trophoblasts was reduced at term, while p75NTR receptor staining was negative. TrkB receptors were confined to the nuclear and perinuclear spaces, and phosphorylation occurred at the Tyr816 residue in BeWo cells. Exposure to PFOS, PFOA, PFBS, and the six-PFAS mixture did not significantly affect BDNF levels or activation (phosphorylation) of TrkB. Treating cells with 1 μM and 10 μM of PFNA resulted in increased TrkB phosphorylation compared to unexposed controls, but BDNF levels were unchanged.ConclusionsBDNF receptors are present in different regions of human placental villi, indicating diverse functions of BDNF signaling in placental development. Our findings suggest that the BDNF pathway in placental trophoblast cells is not disrupted by exposures to PFOS, PFOA, PFBS, and a PFAS mixture, but may be affected by PFNA exposures. Further investigation is needed on how PFAS affects other critical signaling pathways during fetal neurodevelopment.