Cookies on this website

We use cookies to ensure that we give you the best experience on our website. If you click 'Accept all cookies' we'll assume that you are happy to receive all cookies and you won't see this message again. If you click 'Reject all non-essential cookies' only necessary cookies providing core functionality such as security, network management, and accessibility will be enabled. Click 'Find out more' for information on how to change your cookie settings.

Researchers from Radcliffe Department of Medicine tested the method in COVID-19 patients, to find that the results predicted in-hospital mortality.

Photo composite showing a comparison of Peri-imap pvat images at baseline, and after covid infection. The delineation in the covid image is much less clear.

Cardiovascular complications have emerged as a key feature of COVID-19. Now, a group of researchers in Radcliffe Department of Medicine have found a new way of directly quantifying vascular inflammation in COVID-19 patients. The study, published in Lancet Digital Health, could pave the way to more efficient trials of new treatments and identify patients who might be at risk of long-term complications. 

Professor Charalambos Antoniades, BHF Chair of Cardiovascular Medicine at the Radcliffe Department of Medicine, and lead author of the study, said ”We’ve developed a novel image analysis platform, which uses artificial intelligence to quantify cytokine-driven vascular inflammation from routine CT angiograms.” CT angiograms combine a CT scan with an injection of a special dye to produce pictures of blood vessels and tissue structure in the heart, and are relatively non-invasive and routinely done in many hospitals. 

Professor Antoniades and his team used the data from CT angiograms to carry out ‘virtual biopsies’, by deriving a radiomic ‘signature’ from the angiogram images, and then using machine learning to train this signature against transcriptomic profiles (derived from RNA sequencing data) from tissue biopsies. This is therefore the first study to introduce a new radiotranscriptomics analysis pipeline.

Read the full story on the Radcliffe Department of Medicine website