The Coronavirus Disease 2019 (COVID-19) pandemic continues to have a devastating effect on the health and well-being of the global population. A critical step in the fight against COVID-19 is effective screening of infected patients, with one of the key screening approaches being radiology examination using chest radiography. It was found in early studies that patients present abnormalities in chest radiography images that are characteristic of those infected with COVID-19. Motivated by this and inspired by the open source efforts of the research community, in this study we introduce COVID-Net, a deep convolutional neural network design tailored for the detection of COVID-19 cases from chest X-ray (CXR) images that is open source and available to the general public. To the best of the authors’ knowledge, COVID-Net is one of the first open source network designs for COVID-19 detection from CXR images at the time of initial release. We also introduce COVIDx, an open access benchmark dataset that we generated comprising of 13,975 CXR images across 13,870 patient patient cases, with the largest number of publicly available COVID-19 positive cases to the best of the authors’ knowledge. Furthermore, we investigate how COVID-Net makes predictions using an explainability method in an attempt to not only gain deeper insights into critical factors associated with COVID cases, which can aid clinicians in improved screening, but also audit COVID-Net in a responsible and transparent manner to validate that it is making decisions based on relevant information from the CXR images. By no means a production-ready solution, the hope is that the open access COVID-Net, along with the description on constructing the open source COVIDx dataset, will be leveraged and build upon by both researchers and citizen data scientists alike to accelerate the development of highly accurate yet practical deep learning solutions for detecting COVID-19 cases and accelerate treatment of those who need it the most.

Mutations in the PTEN-induced kinase 1 (PINK1) gene have recently been implicated in autosomal recessive early onset Parkinson Disease (1, 2). To investigate the role of PINK1 in neurodegeneration, we designed human and murine neuronal cell lines expressing either wild-type PINK1 or PINK1 bearing a mutation associated with Parkinson Disease. We show that under basal and staurosporine-induced conditions, the number of terminal deoxynucleotidyltransferase-mediated dUTP nick end labeling (TUNEL)-positive cells was lower in wild-type PINK1 expressing SH-SY5Y cells than in mock-transfected cells. This phenotype was due to a PINK1-mediated reduction in cytochrome c release from mitochondria, which prevents subsequent caspase-3 activation. We show that overexpression of wild-type PINK1 strongly reduced both basal and staurosporine-induced caspase 3 activity. Overexpression of wild-type PINK1 also reduced the levels of cleaved caspase-9, caspase-3, caspase-7, and activated poly(ADP-ribose) polymerase under both basal and staurosporine-induced conditions. In contrast, Parkinson disease-related mutations and a kinase-inactive mutation in PINK1 abrogated the protective effect of PINK1. Together, these results suggest that PINK1 reduces the basal neuronal pro-apoptotic activity and protects neurons from staurosporine-induced apoptosis. Loss of this protective function may therefore underlie the degeneration of nigral dopaminergic neurons in patients with PINK1 mutations. Parkinson disease (PD)2 is the most common neurodegenerative movement disorder, affecting ϳ1% of the population by age 65 years (3, 4). It is characterized by the predominant degeneration of midbrain dopaminergic neurons. Although most patients with PD are sporadic, familial cases represent ϳ10% of all diagnoses. To date, six genes responsible for inherited forms of PD have been identified. Mutations in the ␣-synuclein (5), LRRK2 (leucine-rich repeat kinase 2) and UCH-L1 (ubiquitin C-terminal esterase L1) genes cause dominant forms of familial PD. In contrast, mutations in parkin (6), DJ-1 (7,8), and the newly identified PTEN (phosphatase and tensin homologue on chromosome 10)-induced kinase 1 (PINK1) (1, 2) are responsible for recessive forms of familial PD.PINK1 encodes a highly conserved, 581-amino acid, putative serinethreonine protein kinase and is a member of a small family of novel kinases including CLIK1 (CLP-36 interacting kinase)/PDLIM1 kinases. Bioinformatic analysis suggests that residues Gly-193 to Leu-507 comprise the catalytic domain, residues Gly-193 to Lys-219 form the ATPbinding cassette (with Tyr-166 as an autophosphorylated regulatory residue), and residues Asp-384 to Glu-417 form an activation loop (Fig. 1). PINK1 is transcriptionally transactivated by the PTEN gene (9) and is expressed at variable levels in different cancer cell types. Valente et al. showed that overexpressed, epitope-tagged PINK1 localized to mitochondria and may have a protective function against cell death (1).To further investigate the role of PINK1 in neuronal ap...

The COVID-19 pandemic continues to have a devastating effect on the health and well-being of the global population. A critical step in the fight against COVID-19 is effective screening of infected patients, with one of the key screening approaches being radiological imaging using chest radiography. It was found in early studies that patients present abnormalities in chest radiography images that are characteristic of those infected with COVID-19. Motivated by this, a number of artificial intelligence (AI) systems based on deep learning have been proposed and results have been shown to be quite promising in terms of accuracy in detecting patients infected with COVID-19 using chest radiography images. However, to the best of the authors' knowledge, these developed AI systems have been closed source and unavailable to the research community for deeper understanding and extension, and unavailable for public access and use. Therefore, in this study we introduce COVID-Net, a deep convolutional neural network design tailored for the detection of COVID-19 cases from chest radiography images that is open source and available to the general public. We also describe the chest radiography dataset leveraged to train COVID-Net, which we will refer to as COVIDx and is comprised of 16,756 chest radiography images across 13,645 patient cases from two open access data repositories. Furthermore, we investigate how COVID-Net makes predictions using an explainability method in an attempt to gain deeper insights into critical factors associated with COVID cases, which can aid clinicians in improved screening. By no means a productionready solution, the hope is that the open access COVID-Net, along with the description on constructing the open source COVIDx dataset, will be leveraged and build upon by both researchers and citizen data scientists alike to accelerate the development of highly accurate yet practical deep learning solutions for detecting COVID-19 cases and accelerate treatment of those who need it the most.

The coronavirus disease 2019 (COVID-19) pandemic continues to have a tremendous impact on patients and healthcare systems around the world. In the fight against this novel disease, there is a pressing need for rapid and effective screening tools to identify patients infected with COVID-19, and to this end CT imaging has been proposed as one of the key screening methods which may be used as a complement to RT-PCR testing, particularly in situations where patients undergo routine CT scans for non-COVID-19 related reasons, patients have worsening respiratory status or developing complications that require expedited care, or patients are suspected to be COVID-19-positive but have negative RT-PCR test results. Early studies on CT-based screening have reported abnormalities in chest CT images which are characteristic of COVID-19 infection, but these abnormalities may be difficult to distinguish from abnormalities caused by other lung conditions. Motivated by this, in this study we introduce COVIDNet-CT, a deep convolutional neural network architecture that is tailored for detection of COVID-19 cases from chest CT images via a machine-driven design exploration approach. Additionally, we introduce COVIDx-CT, a benchmark CT image dataset derived from CT imaging data collected by the China National Center for Bioinformation comprising 104,009 images across 1,489 patient cases. Furthermore, in the interest of reliability and transparency, we leverage an explainability-driven performance validation strategy to investigate the decision-making behavior of COVIDNet-CT, and in doing so ensure that COVIDNet-CT makes predictions based on relevant indicators in CT images. Both COVIDNet-CT and the COVIDx-CT dataset are available to the general public in an open-source and open access manner as part of the COVID-Net initiative. While COVIDNet-CT is not yet a production-ready screening solution, we hope that releasing the model and dataset will encourage researchers, clinicians, and citizen data scientists alike to leverage and build upon them.

Immune dysfunction may contribute to tumor progression in gastric cancer (GC) patients. One mechanism of immune dysfunction is the suppression of T cell activation and impairment of the efficacy of cancer immunotherapy by myeloid-derived suppressor cells (MDSCs). We assessed the phenotype and immunosuppressive function of MDSCs in GC patients. We further investigated the role of S100A8/A9 in GC and the relationship between S100A8/A9 and MDSC function. Lastly, the effect of MDSCs on survival rates and its potential as a prognostic factor in GC patients were investigated. MDSCs from PBMCs of GC patients were identified by comparing the expression of specific surface markers with PBMCs from healthy individuals. The ability of MDSCs to suppress T lymphocyte response and the effect of S100A8/A9 and RAGE blocking were tested in vitro by (autologous) MLR. GC patients had significantly more MDSCs than healthy individuals. These MDSCs suppressed both T lymphocyte proliferation and IFN-γ production and had high arginase-I expression. Levels of S100A8/A9 in plasma were higher in GC patients compared with healthy individuals, and they correlated with MDSC levels in the blood. Blocking of S100A8/A9 itself and the S100A8/A9 receptor RAGE on MDSCs from GC patients abrogated T cell effector function. We found that high levels of MDSCs correlated with more advanced cancer stage and with reduced survival (p = 0.006). S100A8/A9 has been identified as a potential target to modulate antitumor immunity by reversing MDSC-mediated immunosuppression.