Photo Credit: Arxiv.org
Researchers from the University of Waterloo and Canadian startup DarwinAI have open-sourced a new artificial intelligence (AI) tool that claims to detect COVID-19 via a simple X-ray of the chest. Called the COVID-Net, this tool is a convolutional neural network or an AI tool that helps in recognising images. This is revolutionary as coronavirus cases continue to rise, with numbers now increasing in India as well. COVID-Net is specifically trained to identify COVID-19 patients, and the researchers hope to increase computer aided screening in infected countries. It was trained using 5,941 chest x-rays of 2,839 patients. All of these patients had different conditions – some had bacterial infections, some had non-COVID infections, while some had COVID-19 infections.
Researchers Linda Wang and Alexander Wonga from the University of Waterloo and Canadian startup Darwin AI have developed this new COVID-Net tool. They've made this tool public so that researchers and doctors can help fine tune it further and help detect COVID-19 patients faster. While many companies have announced AI tools to diagnose COVID-19 through X-rays, none have made it public as of yet.
In its research paper, DarwinAI notes that COVID-Net is ‘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.'
The investigation process of COVID-Net is explained in detail in an attempt to allow others to gain deeper insights into critical factors associated with COVID-19 cases, which can aid clinicians in improved screening as well as improve trust and transparency when leveraging COVID-Net for accelerated computer aided screening. The hope is to leverage artificial intelligence to build tools to help detect and even prevent further spread coronavirus. To halt the spread of coronavirus, India is in complete lockdown for 21 days.