NHS Grampian, a healthcare provider in Aberdeenshire and Moray in Scotland, is using Kherion Medical Technologies’ artificial intelligence solution Mia to expedite the breast cancer detection process.
Normally, two radiologists will read each mammogram scan to ensure they make an accurate diagnosis, which increases the time it takes to deliver results to patients. Mia, which is supported by Microsoft Azure, can replace one radiologist and use AI technology to analyse scans quickly, which will help to cut down the backlog of patients waiting for scan results due to Covid-19 and staffing issues.
A previous study with the University of Aberdeen and the Industrial Center for Artificial Intelligence in Digital Diagnostics assessed Mia with a dataset of mammograms over a three-year period. Results showed that a single specialist reading alone would have picked up 261 cancers, whereas Mia alone would have picked up 271.
“We have seen significant results using Mia,” said Dr Gerald Lip, lead radiologist at NHS Grampian. “Not just in the detection of difficult cancers but also in the time it takes to get results to patients. Radiologists can’t work 24 hours a day, but the AI can. By considering replacing one human review of a screening with AI we project a 30-40 per cent reduction in reporting workload on our team.
“But it’s important to remember that the AI isn’t being used in isolation. It is great at detecting breast cancer, but it is unable to review the findings in the context of past scans and medical history. This is why we are using a combination of a highly trained radiologist with the AI in all screenings.”
NHS Grampian has also developed mobile mammogram unit which travels to remote areas in the northeast of Scotland. Images taken in the unit are transferred through the cloud where they can be read by Mia before they reach the radiologists in the healthcare centre.
The solution is currently deployed at four sites in Europe, with 14 additional deployments underway at NHS sites in the UK.