• ULHT and NUH to use AI to review scans as part of trial
  • Trust says there is a “clear need” to mitigate national shortage of radiologists
  • But AI will not totally replace radiologists, says consultant mammographer

Two East Midlands trusts are trialling the use of artificial intelligence tools to diagnose breast cancer in a bid to mitigate the national shortage of radiologists.

United Lincolnshire Hospitals Trust and Nottingham University Hospitals Trust are the only two trusts in the country to take part in the trial, which is a collaboration between the East Midlands Radiology Consortium (EMRAD) and two UK-based AI companies Faculty and Kheiron Medical.

Kheiron Medical’s mammography intelligent assessment tool has already been trialled in Hungary but is new to the UK. The first stage of the trial will involve assessing old scans from ULHT and NUH to establish how accurate AI is at diagnosing scans needing further investigation. These will be compared to the results already produced by the breast scanning team. 

In the next stage of the trial, AI will perform the first read of all scans, before these are reviewed by a member of the radiology team.

Breast screening images are currently reviewed by two members of the screening team, but ULHT said there is a “clear need” to mitigate the national shortage in radiologists.

ULHT consultant mammographer and trust project lead, Bernadette Trzcinski, said: “Across the country we desperately need something to help us with the current staff shortages, which are predicted to become increasingly challenging as the demand for imaging grows.” 

She stressed the point of the trial was not to replace radiologists and said all scans at the trust would continue to be read by at least one member of the breast screening team.

“If the mammography intelligence assessment is successful, it has the potential to half the amount of time we spend reviewing scans,” Dr Trzcinski added. “This is time we could be spending with our patients, improving their overall experience.”

Jonathan James, consultant radiologist at NUH said the AI tool had the potential to help with the staffing crisis that the NHS breast screening programme is currently experiencing.

”There is a shortfall in the number of trained radiologists nationally with breast radiology particularly badly affected as in next five years for every two radiologists who currently join the screening programme, three are predicted to retire,” Dr James said.

“Currently, all mammograms are read by two radiologists as we know that this enables us to find more small cancers and reduce the number of women called back unnecessarily for extra tests,” he added. “The new MIA tool could replace one of those readers so that more of our radiologists are freed up to see women more quickly, reduce waiting times and help improve the overall patient experience.”

HSJ asked how long the trial would last, but did not receive a response ahead of publication. 

According to the Royal College of Radiologists’ 2018 UK workforce census, there were 379 unfilled consultant radiologist posts across UK hopsitals in 2018. Of these, almost two-thirds (61 per cent) had been vacant for at least a year. 


Ammended at 9:50 on 22 August to reflect NUH’s comment and add detail about the use of the MIA tool in Hungary.



The HSJ Digital Transformation Summit, taking place at the Crowne Plaza, Stratford-upon-Avon from 12-13 February 2020, unites 120+ senior leaders from across the provider, commissioning and STP landscape with those who have leveraged technology to drive tangible improvements across other industries, to discuss how to realise your digital visions in a cash-limited environment and scale up innovations to improve quality and outcomes for your local population.

Held under the Chatham House Rule, attendees will quiz NHSX and other national figures on general policy direction and co-develop solutions to their local challenges with innovators from across the country. The Summit is free to attend for senior NHS digital leaders – register your interest here https://digitaltransformation.hsj.co.uk