New NCIMI collaboration to drive forward the use of imaging AI for COVID-
NCIMI has joined a European wide research collaboration to respond to the rapidly evolving needs of the COVID-19 pandemic, and accelerate impact of lung imaging AI in diagnosis and stratification of patients with Covid-19.
The pandemic continues to infect new patients, as well as the increasing number of people experiencing ongoing long-term symptoms –known as "long Covid", affecting about 2% of all patients (over 70,000 people in the UK).
The Consoritium aims to help address both issues. It will help clinicians to detect COVID-19 cases early and distinguish them from other types of pneumonia, thus preventing isolated cases leading to local outbreak. The icovid project will also use AI technology to better predict the long-term effects of COVID-19, which are today still largely unknown.
icovid first started as a pro-bono initiative in Belgium to support radiologists with the assessment of lung CT images. It uses AI scanning software icolung developed by the medical imaging tech company icometrix. The AI is being used by 75 hospitals worldwide and has analysed over 35,000 lung CT scans. The programme is now co-funded by the EU Horizon programme, which will bring the UK into the collaboration.
NCIMI will undertake a clinical validation study of the algorithm, against data held in NCIMI's databank, and provide algorithm evaluation compared to a variety of different levels of clinical experience and expertise to ensure the AI provides useful support.
NCIMI's chief medical officer Fergus Gleeson said: "A wide adoption of AI-based software for the analysis of chest CT images, like icolung, will help the fight against a pandemic that, unfortunately, we will have to endure for quite some time. These large-scale research collaborations with a variety of expertise are critical to responding to the evolving needs during this pandemic."
Dr. Dirk Smeets, icovid project coordinator, and CTO at icometrix said: "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, Liège, and Maastricht."