Collin Arocho
27 January 2021

Belgium’s Icovid initiative, which looks for ways to utilize AI to support radiologists in the assessment of CT images of the lungs of Covid-19 patients, is getting a lot of attention as it spreads across Europe. Set up by AI medical imaging expert Icometrix, together with UZ Brussel, KU Leuven and Imec’s ETRO research group at VUB, has now grown into a multicenter European project. Some of the top hospitals, universities and research centers on the continent are looking to help by improving the AI with important clinical information to add to the CT images.

Credit: Imec

In March 2020, when the spread of the coronavirus took off and testing capacity couldn’t keep up, collaborators wanted to use lung scans as a triage tool to help alleviate the burden of insufficient testing. That’s when the initiatives developed the Icolung system, a cloud-based AI software used to quantify the degree of lung involvement in Covid-19 patients. By using the mix of CT and AI analysis, researchers were able to trace patients with suspicious lung lesions and have them tested as a priority. Icolung is currently being used by 75 hospitals worldwide and has analyzed more than 35,000 lung CT scans.

“What started as a local project is now being rolled out in 800 hospitals in Europe and supported by excellent research centers all over Europe. With Icolung, we can detect Covid-19 patients at an early stage and quantify the extent of lung lesions,” comments ETRO professor Jef Vandemeulebroucke. “Meanwhile, we’re further improving the AI software to identify lung damage as Covid-19 even more quickly, and to determine the further care path of the patient faster and better through prognostic models.”