Yvonne Cook went in for a routine mammogram and walked out part of a study that has just rewritten the case for AI in the NHS. The Aberdeen-led GEMINI trial, published in Nature Cancer, found that AI screening picked up cancers that human radiologists would have missed — including hers — and is now feeding directly into the UK’s biggest evaluation of medical AI to date.
In May 2023, Yvonne Cook attended what she expected to be a routine mammogram in Aberdeen. In the waiting room, she noticed a sign explaining that a research project was using artificial intelligence to help review breast scans. Participation was optional.
“It didn’t occur to me for a minute to opt out,” she said. “I think it said that AI would be utilised as part of the research project to review the mammogram and I just thought, why not?”
A short time later — in her 60s, with no symptoms — Yvonne received a recall letter requesting additional imaging. The wording was deliberately gentle.
“I guess they don’t want to alarm people unnecessarily, the letter said they wanted to do a follow-up mammogram which might be as a result of the initial result not being particularly clear.”
At the clinic, she learned the real reason for the recall.
“When I arrived for that appointment, they said that it was the AI part of the analysis that had picked up something. I had a scan and the consultant confirmed that the AI diagnosis was correct, that there was a small, Grade 2 tumour there, too small to be detected by the human eye.”
Yvonne had lobular breast cancer — the second most common type. Her response surprised her.
“You would expect a negative and emotional reaction to, ‘Oh my goodness, I have cancer,’ but overwhelmingly I just felt incredibly lucky that I was part of the research programme and that it had been picked up at this early stage. The fact that it started with me feeling incredibly lucky I think really helped to shape my positive approach to the treatment and everything that followed.”
Surgery followed in December 2023, with a second operation in January 2024 to achieve clearer margins. Yvonne completed treatment with a week of low-dose radiotherapy in May 2024 and was able to keep working throughout. The former Head of Tourism Development at VisitAberdeenshire continues to work as a freelance tourism consultant in the city.
By the end of treatment, the picture was clear to her.
“Had the AI not picked up the small tumour when it did, then either it would have been discovered at my next routine mammogram three years later, or I would have picked it up when it had grown to a stage that I was able to feel it. If that had been the scenario, then it’s likely that the surgery would have been more invasive. The cancer could have spread… it could have involved chemotherapy and a much longer recovery time with more impact on my life.”
A study built around 10,889 women in NHS Grampian
Yvonne is one of 10,889 women whose routine NHS Grampian screening data sat at the heart of GEMINI — Grampian’s Evaluation of Mia in an Innovative National breast screening Initiative — published in Nature Cancer on 10 March 2026 and the UK’s first comprehensive evaluation of AI in breast cancer screening.
Carried out by the University of Aberdeen, NHS Grampian and Kheiron Medical Technologies(now part of DeepHealth Inc.), and facilitated by the North of Scotland NHS Innovation Hub, the study tested an AI software tool called Mia across 17 different deployment scenarios. The optimal configuration — Mia as a second reader replacing one of the two human radiologists, with an extra AI safeguard pass — increased early cancer detection by 10.4%, cut radiologist workload by more than 30%, and shortened time-to-notification for women requiring follow-up from 14 days to three. Crucially, no additional women were recalled.
The lead author is Dr Clarisse de Vries, now Lecturer in Data Science at the University of Glasgow and a former Research Fellow at Aberdeen. She set out the scale of the problem the study was designed to address.
“As part of the UK breast screening programme all women aged between 50 and 70 years old in the UK are invited for mammograms every three years. This results in over 2 million mammogram examinations being performed annually. Currently, in the UK, to reduce the number of cancers missed, two radiologists read every mammogram. However, some breast cancers are extremely hard to detect, and it is not always clear from mammograms whether breast cancer is present… Despite this, approximately 20% of cancers are missed using this process.”
The recall problem cuts the other way too.
“Furthermore, many more women are recalled for further assessments than are diagnosed with cancer,” Dr de Vries said. “For each five women recalled, approximately one will be diagnosed with breast cancer. So, they have had unnecessary, often invasive tests — not to mention the additional worry for the patient. This is why our findings are so important — not only did we find optimal ways to detect breast cancer, quicker and more accurately, we also found ways to reduce the number of women having to return for unnecessary tests.”
A north-east AI story years in the making
GEMINI is not the first time Aberdeen has put AI mammography on the map. ABN reported in late 2023 on the pioneering integration of AI into Aberdeen healthcare led from Foresterhill, with NHS Grampian’s Professor Gerald Lip at the centre of the work — the same clinician now reporting GEMINI’s headline results.
Professor Lip, Clinical Director for breast screening in the North East of Scotland at NHS Grampian and Lead for Artificial Intelligence in Clinical Practice at the University of Aberdeen, framed the operational case.
“Our results show that AI could effectively support breast screening services by increasing cancer detection and reducing doctors’ workload. Ultimately, for radiologists, AI augments practice. Along with picking up more cancers, in UK and European screening programs where mammograms are read by two humans, partial substitution of one of the human readers for normal examinations can deliver real workload savings and reduce burnout. The bottom line here is — without AI, doctors would not have caught these cancers as early.”
There is a longer Aberdeen lineage here too. The University of Aberdeen pioneered the development of MRI scanners under the late Professor John Mallard — a story celebrated by the university and ABN in 2023. Half a century on, Aberdeen has put its name to another reinvention of medical imaging.
A study with national consequences
The study’s findings will feed directly into the UK-wide EDITH trial (Evaluating the use of AI in Detecting cancers wITH mammography), with the Scottish element led jointly by the University of Aberdeen, NHS Grampian and the University of Glasgow. They also directly address evidence gaps previously cited by the UK National Screening Committee — which until now has not recommended AI use in the NHS breast screening programme on the grounds that the evidence base was insufficient.
The Aberdeen-led work also lands in a tense moment for NHS Grampian. The board has just announced a strategy to save £177 million over the next five years, and costs for the long-delayed Aberdeen cancer centre and maternity hospital are now expected to top £420 million. A workforce-saving, cancer-finding AI deployment, evaluated in-house and now informing UK policy, is the kind of story Aberdeen needs.
It also fits a wider north-east life sciences picture. ABN reported earlier this year that, while big pharma has cooled on UK investment, North East Scotland’s biotech scene is booming, and the University of Aberdeen continues to attract major cancer research grants — including the £2.4 million awarded to Professor Anne Donaldson last year to unravel a cancer mystery.
For Silicon Scotland readers, our sister title has covered the AI-policy and national-framework angle of the GEMINI findings in detail — replace this URL with the live Silicon Scotland GEMINI piece once published.
The patient’s verdict
For Yvonne, the experience has reshaped how she thinks about screening itself.
“I do have faith in the current screening system but at the back of my mind when I go in for my checkups, I am thinking if there’s no AI as a second check, what if there’s something small there that isn’t picked up early? There could be many other women who would be in the same situation as me. Being caught very early through AI and dealt with quickly and in a less invasive way is a huge bonus.”
In Case You Missed it:
“I just feel incredibly lucky,” she added. “Lucky that AI was used, and lucky that it caught something so small at exactly the right time.”
Sources: University of Aberdeen — Pioneering study finds AI increases cancer detection by more than 10 percent · Nature Cancer — Prospective evaluation of artificial intelligence integration in breast screening · BBC News — Breast cancer detection ‘up by 10% with use of AI’
