AI imaging database to improve COVID-19 diagnosis

An AI imaging database is set to improve the diagnosis of patients presenting with COVID-19 symptoms.

NHSX, a unit tasked with driving the digital transformation of care in the NHS, has brought together over 40,000 CT scans, MRIs and X-rays from more than 10,000 patients across the UK during the course of the pandemic.

Access to this National COVID-19 Chest Imaging Database (NCCID) has now been extended to hospitals and universities across the country which are using the images to track patterns and markers of illness.

Clinicians at Addenbrooke’s Hospital in Cambridge are developing an algorithm based on the NCCID images to help inform a more accurate diagnosis of patients when they present to hospital with potential COVID-19 symptoms and have not yet had a confirmed test.

Using visual signatures of the virus as they appear in chest scans, they are able to compare the patterns in the patient’s imaging with those seen previously in the NCCID to get a more accurate diagnosis and prognosis.

Carola-Bibiane Schönlieb, professor of applied mathematics and head of the Cambridge Image Analysis group at the University of Cambridge, said: “The NCCID has been invaluable in accelerating our research and provided us with a diverse, well-curated, dataset of UK patients to use in our algorithm development.

“The ability to access the data for 18 different trusts centrally has increased our efficiency and ensures we can focus most of our time on designing and implementing the algorithms for use in the clinic for the benefit of patients.

“By understanding in the early stages of disease whether a patient is likely to deteriorate, we can intervene earlier to change the course of their disease and potentially save lives as a result.”

The NCCID is also helping researchers from universities in London (University College London), and Bradford, to develop AI tools that could help doctors improve the treatment for patients with COVID-19.

The database is helping to inform the development of a potential national AI imaging platform to safely collect and share data, developing AI technologies to address a number of other conditions such as heart disease and cancers.

The NCCID is one workstream taken forward by the NHS AI Lab at NHSX. The NHS AI Lab has also set up and launched a £140m AI award this year in collaboration with the Accelerated Access Collaborative (AAC) and National Institute for Health Research (NIHR), which aims to bring the benefits of AI technologies to patients and staff across health and care.

Initial bids were awarded to 42 organisations in September 2020 with a further round of bids closing last month.

Dominic Cushnan, head of AI imaging at NHSX, said: “We are applying the power of artificial intelligence to quickly detect disease patterns and develop new treatments for patients. There is huge potential for patient care, whether through quicker analysis of chest images or better identification of abnormalities.

“The industrial scale collaboration of the NHS, research and innovators on this project alone has demonstrated the huge potential and benefits of technology in transforming care.”