Researchers from the East Midlands Radiology Consortium, a partnership of seven U.K. National Health Service (NHS) trusts, are investigating the viability of integrating artificial intelligence (AI) into breast cancer screening, according to an article from U.K. newspaper Sleaford Standard.
In 2018, the consortium formed a collaboration with two U.K. startups to develop and test AI tools that would support breast screening services. One of the startups, Faculty, has developed software that uses AI to optimize scheduling and staff resourcing. The other company, Kheiron Medical Technologies, recently launched an AI software for breast cancer screening called Mia.
For the retrospective trial, the group has been testing the accuracy of Mia for detecting breast cancer on medical scans acquired at United Lincolnshire Hospitals and Nottingham University Hospitals. Early results indicate the AI software is already performing better than most radiologists.
Successful integration of AI into the breast screening workflow could improve both the quality and efficiency of the service, project leader and consultant mammographer Bernadette Trzcinski said in a statement. For example, hospitals could rely on the AI software and a single radiologist to read breast cancer screening exams, as opposed to the standard practice of having two radiologists review the same screening exam.
"Across the country we desperately need something to help us with the current staff shortages [in radiology], which are predicted to become increasingly challenging as the demand for imaging grows. ... [AI] has the potential to half the amount of time we spend reviewing scans, this is time we could be spending with our patients, improving their overall experience," she said.
![A normal mammogram confirmed by three-year radiologic follow-up illustrates reader-marked regions of interest (ROIs) during (A) unaided (round 1) and (B) artificial intelligence (AI)–assisted (round 2) reading. Each colored dot represents an ROI for recall by a human reader. Readers could mark more than one ROI per case, represented by multiple dots of the same color. During AI-assisted reading, the AI system displayed three visible prompts: two with suspicion of malignancy scores of 35% (left mediolateral oblique [L MLO] and craniocaudal [L CC]) and one with a suspicion of malignancy score of 10% (right craniocaudal [R CC]), shown as polygonal overlays. Without AI, six of 10 readers (60%) marked a false-positive ROI. With AI assistance, this fell to two of 10 (20%). R MLO = right mediolateral oblique.](https://img.auntminnieeurope.com/mindful/smg/workspaces/default/uploads/2026/07/2026-07-14-radiology-mammogram-ai-auto-bias.H0bYO8QlWs.jpg?auto=format%2Ccompress&dpr=2&fit=crop&h=167&q=70&w=250)
