These are difficult times, it is clear that this COVID19 pandemic that is assailing the world is going to change our way of life. It is time to be united and to collaborate, where doctors, researchers, mathematicians, physicists and the entire scientific community unites to fight the COVID-19 virus by sharing our knowledge and research.
After opening up free access to our Quibim Precision® – COVID19 platform and AI algorithms to the scientific community to find new diagnostic tools and ways to understand the mechanisms and aggressiveness of the disease, we co-founded the Imaging COVID-19 AI initiative, a multicenter European project to enhance computed tomography (CT) in the diagnosis of COVID-19 by using artificial intelligence.
This collaborative initiative coordinated by the Netherlands Cancer Institute, together with Rovobision, the European Society of Medical Imaging Informatics (EuSoMII) and Quibim, has had a great response with the participation of several hospitals, radiology centres and research groups from across the world including Italy, Spain, Netherlands, India, and Korea among others.
Furthermore, last March 30th the Radiological Society of North America (RSNA) announced (press release) its willingness to join this initiative. We are proud to welcome our partnering with this renowned society by joining the Imaging COVID-19 AI initiative to spread it throughout the medical imaging community around the world.
“The organizations expressed the common goal of creating a secure way to share COVID-19 imaging, in order to assess lung involvement more accurately with AI. They will collaborate to enable hospitals to provide imaging data securely and efficiently with researchers, respecting privacy and ethical principles. They will define and publish protocols for selecting and labeling imaging data associated with COVID-19 as a tool for researchers and practitioners. Other interested organizations are invited to join this coalition to share information and facilitate a rapid response to COVID-19.” the Radiological Society of North America declares in the press release issued on March 30th, 2020.
Fighting COVID19 through AI
This initiative for automated diagnosis and quantitative analysis of COVID-19 will create a deep learning model for automated detection and classification of COVID-19 on CT scans. This model will also be used for assessing disease severity in patients by quantification of lung involvement to rapidly develop an artificial intelligence solution.
The number of people affected by COVID-19 is increasing every day with healthcare systems across the world on the verge of collapsing, which is why Quibim took part in this initiative to develop a tool to support doctors against this virus. As the initiative states “automated image analysis with artificial intelligence techniques has the potential to optimize the role of CT in the assessment of COVID-19 by allowing accurate and fast diagnosis of infection in a large number of patients. AI has the potential to support clinical decision making and improve workflow efficiency.”
Our role in the initiative
As a company specialized in machine learning and image processing technologies for medical images, Quibim provides to the initiative the research platform Quibim Precision for development and deployment of the deep learning model. The data will be transferred directly and securely from each participating hospital to the servers of the company. The Quibim platform, as well as other software utilities to upload images and clinical information provided, enforces a role-based authentication mechanism which guarantees that Study Data remain protected and only available to authorized users.
In that sense, Quibim places at the service of the project its experience on interconnectivity with hospitals and sending images through its tool MIUC (Medical Imaging Universal Connector) following all regulations of GDPR, anonymization and personal data processing.
Visit Imaging COVID-19 AI initiative site.
