Skip to main content
KBS_Icon_questionmark link-ico

Go to…

School researchers contribute to initiative for AI lung scan analysis in fight against COVID-19

icovid is being rolled out across Europe and is on the OECD shortlist for AI initiatives against current and future pandemics

icolung_monitor

Researchers from the School of Biomedical Engineering & Imaging Sciences have joined icovid, a multicenter European project, co-funded the by the EU Horizon 2020 programme, to support radiologists with the assessment of lung CT images of COVID-19 patients, equipping researchers with greater scope to respond to the rapidly evolving needs of the COVID-19 pandemic.

The local Belgian pro bono initiative continues the development of the CE-marked artificial intelligence software, icolung, which is currently being used by over 75 hospitals worldwide and has analysed over 35,000 lung CT scans. It is now being rolled out to 800 hospitals free of charge across Europe.

PhD student Lucas Fidon had developed an algorithm for the icolung software that allowed lung lesions caused by COVID to be automatically segmented. The AI software became available for clinical use in Europe and the US.

icovid is a fantastic opportunity for King's to contribute its expertise in Artificial Intelligence for medical imaging to tackle the ongoing pandemic. Close collaboration between leading academic centres, clinical sites and the medtech industry is critical to deliver rapid impact.– Tom Vercauteren, Professor of Interventional Imaging Computing

While vaccination will eventually normalise daily life, the virus will still circulate as a full vaccination coverage and effectiveness are not expected. In local outbreaks it will be important to identify COVID patients early.

One key purpose of icolung will be recognizing COVID pneumonia from other pneumonias and will help to decide on the further care pathway of the patient.

With the improved software, the consortium will also better predict long term effects of COVID-19, which is still a largely unknown factor.

The possibility to identify patients who will develop long COVID opens opportunities for a modified treatment to reduce the burden.

This project allows us to further demonstrate that AI, and medical technology in general, can add value to clinical decisions and save costs. I strongly believe that icolung will benefit from the advice, clinical expertise and critical evaluation from renowned academic centres, like Oxford, Heidelberg, Brussels, Liege and Maastricht.– Dr Dirk Smeets, icovid project coordinator and CTO at icometrix

Prof Johan de Mey, VUB-UZ Brussel: “At the time, there was insufficient testing capacity to quickly test all patients. With icolung, we wanted to use lung scans as a triage tool. By using CT and with the help of the AI analyses, we were able to trace patients with suspicious lung lesions and have them tested as a priority. During the busiest periods, everyone who entered the UZ Brussel as a patient was scanned, also as a means of preventing COVID-19 outbreaks in the hospital.”

Professor Jef Vandemeulebroucke, Vrije Universiteit Brussel, Electronics and Informatics (ETRO): “What started as a local project is now being rolled out in 800 hospitals in Europe and supported by excellent research centres all over Europe. With icolung, we can detect COVID-19 patients at an early stage and quantify the extent of lung lesions. Meanwhile, we are 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.”

The icovid project now builds on the development of icolung and is committed to scaling up, thanks to the commitment of renowned research institutes such as King’s College London, Universitätsklinikum Heidelberg, University of Oxford, Maastricht University and the University and Centre Hospitalier Universitaire of Liège. The partners will also collaborate with The Medical Cloud Company to incorporate other clinical information into the models in addition to CT images. icovid receives funding for this from the European Union’s Horizon 2020 research and innovation programme.