In vitro rapid inactivation of SARS-CoV-2 by visible light photocatalysis using boron-doped bismuth oxybromide (preprint)

Inactivation of SARS-CoV-2 in wastewater and on surfaces is critical to prevent the fecal-oral and fomite transmission, respectively. We hypothesized that visible light active photocatalysts could dramatically enhance the rate or extent of virus inactivation and enable the use of visible light rather than shorter wavelength ultraviolet light. A novel visible light active photocatalyst, boron-doped bismuth oxybromide (B-BiOBr), was synthesized and tested for its SARS-CoV-2 inactivation towards Vero E6 cell lines in dark and under irradiation at 426 nm by a light emitting diode (LED) in water. SARS-CoV-2 inactivation in the presence of B-BiOBr (0.8 g/L) under LED irradiation reached 5.32-log in 5 min, which was 400 to 10,000 times higher than those achieved with conventional photocatalysts of tungsten or titanium oxide nanomaterials, respectively. Even without LED irradiation, B-BiOBr inactivated 3.32-log of SARS-CoV-2 in the dark due to the ability of bismuth ions interfering with the SARS-CoV-2 helicase function. LED irradiation at 426 nm alone, without the photocatalyst, contributed to 10% of the observed inactivation and was attributed to production of reactive oxygen species due to blue-light photoexcitation of molecules in the culture media, which opens further modes of action to engineer disinfection strategies. The visible light active B-BiOBr photocatalyst, with its rapid SARS-CoV-2 inactivation in the presence and absence of light, holds tremendous opportunities to build a healthy environment by preventing the fecal-oral and fomite transmission of emerging pathogens.

Towards Unbiased COVID-19 Lesion Localisation and Segmentation via Weakly Supervised Learning (preprint)

Despite tremendous efforts, it is very challenging to generate a robust model to assist in the accurate quantification assessment of COVID-19 on chest CT images. Due to the nature of blurred boundaries, the supervised segmentation methods usually suffer from annotation biases. To support unbiased lesion localisation and to minimise the labeling costs, we propose a data-driven framework supervised by only image-level labels. The framework can explicitly separate potential lesions from original images, with the help of a generative adversarial network and a lesion-specific decoder. Experiments on two COVID-19 datasets demonstrate the effectiveness of the proposed framework and its superior performance to several existing methods.

Deep learning Enables Accurate Diagnosis of Novel Coronavirus (COVID-19) with CT images (preprint)

BackgroundA novel coronavirus (COVID-19) has emerged recently as an acute respiratory syndrome. The outbreak was originally reported in Wuhan, China, but has subsequently been spread world-widely. As the COVID-19 continues to spread rapidly across the world, computed tomography (CT) has become essentially important for fast diagnoses. Thus, it is urgent to develop an accurate computer-aided method to assist clinicians to identify COVID-19-infected patients by CT images. Materials and MethodsWe collected chest CT scans of 88 patients diagnosed with the COVID-19 from hospitals of two provinces in China, 101 patients infected with bacteria pneumonia, and 86 healthy persons for comparison and modeling. Based on the collected dataset, a deep learning-based CT diagnosis system (DeepPneumonia) was developed to identify patients with COVID-19. ResultsThe experimental results showed that our model can accurately identify the COVID-19 patients from others with an excellent AUC of 0.99 and recall (sensitivity) of 0.93. In addition, our model was capable of discriminating the COVID-19 infected patients and bacteria pneumonia-infected patients with an AUC of 0.95, recall (sensitivity) of 0.96. Moreover, our model could localize the main lesion features, especially the ground-glass opacity (GGO) that is of great help to assist doctors in diagnosis. The diagnosis for a patient could be finished in 30 seconds, and the implementation on Tianhe-2 supercompueter enables a parallel executions of thousands of tasks simultaneously. An online server is available for online diagnoses with CT images by http://biomed.nscc-gz.cn/server/Ncov2019. ConclusionsThe established models can achieve a rapid and accurate identification of COVID-19 in human samples, thereby allowing identification of patients.