AI Identifies Aggressive Breast Cancer Tumour Overlooked by Medical Professionals
A woman from Aberdeen has attributed artificial intelligence with preventing her from undergoing more intensive cancer treatment after an aggressive form of breast cancer was identified by the technology. Yvonne Cook's aggressive breast tumour was so minuscule that it escaped detection by human doctors, yet AI successfully highlighted a potential anomaly.
Clinical Trial Reveals Significant Improvements in Detection
This AI-driven detection prompted additional examinations, which later confirmed the presence of cancer. Her diagnosis originated from a clinical trial demonstrating that AI in breast cancer screening could elevate disease detection rates by an impressive 10.4 per cent. The development aligns with remarks from Lord Darzi, a distinguished health expert and author of a pivotal report on the NHS, who asserted that AI possesses the capacity to revolutionise how the health service prevents, identifies, and treats conditions such as cancer.
Ms Cook, residing in Aberdeen, expressed her gratitude, stating she felt "lucky that AI was used and lucky that it caught something so small at exactly the right time". She is convinced that without AI, her cancer would not have been discovered until her next scheduled mammogram appointment approximately three years later, or if the tumour had enlarged sufficiently for her to feel it manually.
Study Published in Nature Cancer Journal
The new trial, featured in the journal Nature Cancer, discovered that alongside enhancing cancer detection rates, AI could also shorten the notification period for affected women from two weeks to merely three days. Furthermore, it was found to decrease the number of women unnecessarily recalled for further tests, including avoidable biopsies. Additionally, it can reduce the workload of healthcare personnel by as much as 31 per cent, according to researchers from the University of Aberdeen, NHS Grampian, and Kheiron Medical Technologies, now part of DeepHealth.
The AI tool, named Mia, was utilised to assist healthcare workers in the routine breast screening of 10,889 women within NHS Grampian. Among these, 106 were diagnosed through standard screening, with an extra 11 cancers identified with AI support, seven of which were classified as "invasive".
Current Screening Practices and AI Integration
Presently, women in the UK aged 50 to 70 are invited for breast cancer screening every three years. Their scans, known as mammograms, are evaluated by two radiologists. However, due to the difficulty in detecting some cancers, a proportion are missed, and a number are "unnecessarily" recalled for further assessment.
The University of Aberdeen indicated that employing AI as a second scan reader—replacing one human reader and acting as an additional safeguard—yielded the optimal balance of workload reductions and heightened early cancer detection without increasing recalls for extra tests.
"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," explained Dr Clarisse de Vries, lecturer in data science at the University of Glasgow, lead author and former research fellow at the University of Aberdeen.
Expert Opinions and Broader Research
She noted that the UK National Screening Committee does not currently endorse the use of AI in breast cancer screening, adding: "Our work adds high-quality evidence to the scientific literature in support of AI." Professor Gerald Lip, lead for artificial intelligence in clinical practice at the University of Aberdeen, supplemented: "The bottom line here is – without AI, doctors would not have caught these cancers as early."
Ms Cook, who is in her 60s, attended a routine mammogram appointment in May 2023. Following her initial test, she received a letter summoning her back for additional imaging. "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," she recounted.
"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," Ms Cook emphasised. She added: "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."
Comprehensive Analysis Across Multiple Institutions
This case emerges as experts from Imperial College London, Google, the universities of Cambridge and Surrey, NHS Trusts at Cambridge University Hospitals, Imperial College Healthcare, the Royal Marsden, the Royal Surrey and St George’s University Hospitals analysed data on over 175,000 women, with the study divided into three segments.
- The first segment examined data on 116,000 women who participated in screening services in 2015/16 and found AI could increase the cancer detection rate, identify more invasive cancers, reduce false positives, and decrease the time required to read a scan.
- The second part scrutinised 9,266 cases at two screening services in London. The average time for AI to complete a read was 17.7 minutes compared to two days for the first medic to assess a scan.
- Researchers also investigated the use of AI in arbitration—when medics disagree on a diagnosis and a third person is called in to make a decision—on scans involving 50,000 women. They found AI performed comparably to humans and reduced the overall screening workload.
Dr Hutan Ashrafian, from the Institute of Global Health Innovation at Imperial College London, stated: "This is the closest AI has ever come to helping reduce breast cancer deaths within the NHS, so the potential for the NHS to take this forward is significant." Author Lord Darzi, director of IGHI who wrote an influential report on the NHS in 2024, added: "AI has the potential to transform how the NHS prevents, detects and treats diseases like cancer. These findings highlight how AI can support clinicians to identify more cancers earlier, reduce errors and deliver higher quality care to patients."
