Kheiron Medical Technologies mammography intelligent assessment (Mia) v.3 system can increase breast cancer detection by 10 per cent and reduce clinical workload by more than 30 per cent compared to the current process, according to a new study published in Nature Cancer this week.
The Grampian’s Evaluation of Mia in an Innovative National breast screening Initiative (GEMINI) study was carried out by the University of Aberdeen and NHS Grampian, in partnership with Kheiron Medical Technologies (now part of DeepHealth Inc.). GEMINI combined both live AI integration and workflow simulations to enable the assessment of multiple AI implementation strategies in the routine breast screening of 10,889 women in NHS Grampian.
Mia v.3 was prospectively used within a routine breast screening service, using two complementary approaches – as an additional read to flag suspicious cases not recalled by routine double human review; and for triage to reduce workload. For this approach, AI ran prospectively, in the background, to enable simulations of AI as a second reader. To comprehensively evaluate the different ways in which AI could support breast screening, 17 different scenarios were tested by incorporating AI into the existing breast screening workflow at various points and with different operating point configurations.
Reduce time to notify
The study found that not only did AI help detect more cancers, most of which were invasive and high grade, it could also reduce the time to notify affected women from 14 days to just three days. The researchers also found that using AI as part of a large-scale screening programme could reduce the number of women recalled unnecessarily for further assessment.
The results also showed that combining AI as a second reader (substituting one human reader) or as an extra reader, resulted in the best combination of workload savings and increased early cancer detection without recalling more women for additional tests.
“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. So, when there is the suspicion of cancer on a mammogram, the woman is recalled for additional investigations,” said Dr Clarisse de Vries, Lecturer in Data Science at the University of Glasgow, lead author and former Research Fellow at the University of Aberdeen. “Despite this, approximately 20 per cent of cancers are missed using this process.”
“Furthermore, many more women are recalled for further assessments than are diagnosed with cancer. 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.”
Re-imagining care
Niccolo Stefani, Business and Product Leader for Population Health & Clinical AI at DeepHealth, said: “This study demonstrates how AI can do more than enhance clinical accuracy, it can re-imagine how we deliver care.
“By detecting more cancers at an earlier stage, and reducing unnecessary interventions, we’re not only helping to improve outcomes for women today, but also setting a new standard for scalable, proactive care. It’s a real-world example of how AI-powered solutions can potentially stage shift disease.”
