Implementing a Detection System for COVID-19 based on Lung Ultrasound Imaging and Deep Learning (preprint)

The COVID-19 pandemic started in China in December 2019 and quickly spread to several countries. The consequences of this pandemic are incalculable, causing the death of millions of people and damaging the global economy. To achieve large-scale control of this pandemic, fast tools for detection and treatment of patients are needed. Thus, the demand for alternative tools for the diagnosis of COVID-19 has increased dramatically since accurated and automated tools are not available. In this paper we present the ongoing work on a system for COVID-19 detection using ultrasound imaging and using Deep Learning techniques. Furthermore, such a system is implemented on a Raspberry Pi to make it portable and easy to use in remote regions without an Internet connection.

Preclinical Evaluation of a Newcastle Disease Virus-Vectored Intranasal SARS-CoV-2 Vaccine (preprint)

The COVID-19 pandemic has claimed the lives of millions of people. Vaccination is a critical tool for the control of transmission; however, the recent emergence of potentially vaccine-resistant variants renders it important to have a range of vaccines types. It is desirable that vaccines are safe, effective, easy to administer and store, and inexpensive to produce. Newcastle disease virus (NDV), responsible for respiratory disease in chickens, has no pathogenic homologue in humans. We developed two types of NDV-vectored candidate vaccines, and evaluated them in a SARS-CoV-2 challenge in hamsters.  Vaccinations resulted in generation of neutralizing antibodies, prevented lung damage, and reduced viral load and viability. In conclusion, our NDV-based vaccine candidate performed well in a SARS-CoV-2 challenge and warrants evaluation in a Phase I human clinical trial. This candidate represents a promising tool in the fight against COVID-19.

Detection of COVID-19 Disease using Deep Neural Networks with Ultrasound Imaging (preprint)

The new coronavirus 2019 (COVID-2019) has rapidly become a pandemic and has had a devastating effect on both everyday life, public health and the global economy. It is critical to detect positive cases as early as possible to prevent the further spread of this epidemic and to treat affected patients quickly. The need for auxiliary diagnostic tools has increased as accurate automated tool kits are not available. This paper presents a work in progress that proposes the analysis of images of lung ultrasound scans using a convolutional neural network. The trained model will be used on a Raspberry Pi to predict on new images.

Development and pre-clinical evaluation of Newcastle disease virus-vectored SARS-CoV-2 intranasal vaccine candidate (preprint)

The COVID-19 pandemic has claimed the lives of millions of people worldwide and threatens to become an endemic problem, therefore the need for as many types of vaccines as possible is of high importance. Because of the millions of doses required, it is desirable that vaccines are not only safe and effective, but also easy to administer, store, and inexpensive to produce. Newcastle Disease Virus (NDV) is responsible for a respiratory disease in chickens. It has no pathogenic homologue in humans. NDV is recognized as an oncolytic virus, and its use in humans for oncological treatment is being evaluated. In the present work, we have developed two types of NDV-vectored candidate vaccines, which carry the surface-exposed RBD and S1 antigens of SARS-CoV-2, respectively. These vaccine candidates were produced in specific-pathogen-free embryonating chicken eggs, and purified from allantoic fluid before lyophilization. These vaccines were administered intranasally to three different animal models: mice, rats and hamsters, and evaluated for safety, toxicity, immunogenicity, stability and efficacy. Efficacy was evaluated in a challenge assay against active SARS-CoV-2 virus in the Golden Syrian hamster model. The NDV-vectored vaccine based on the S1 antigen was shown to be safe and highly immunogenic, with the ability to neutralize SARS-CoV-2 in-vitro, even with an extreme dilution of 1/640. Our results reveal that this vaccine candidate protects the lungs of the animals, preventing cellular damage in this tissue. In addition, this vaccine reduces the viral load in the lungs, suggesting that it may significantly reduce the likelihood of transmission. Being lyophilized, this vaccine candidate is very stable and can be stored for several months at 4-8{degrees}C. In conclusion, our NDV-based vaccine candidate has shown a very favorable performance in the pre-clinical study, serving as evidence for a future evaluation in a Phase-I human clinical trial. This candidate represents a promising tool in the fight against COVID-19.