University of Copenhagen Pioneers AI Technology to Revolutionise Breast Cancer Risk Assessment
In a groundbreaking development with potential global impact, researchers at the University of Copenhagen have unveiled a new artificial intelligence (AI) technology poised to transform the detection and treatment of breast cancer. This innovative approach provides enhanced precision in identifying damaged cells and assessing cancer risk far more accurately than current methods.
Breast cancer remains one of the most pervasive forms of cancer, claiming an estimated 670,000 lives worldwide in 2022 alone. The study, published in The Lancet Digital Health, demonstrates that AI can significantly improve treatment methods by accurately scanning for irregular cells and thus providing superior risk assessments.
The newly developed deep learning AI technology was trained to analyse mammary tissue biopsies from donors. Its capability to identify signs of damaged cells, which are strong indicators of cancer risk, represents a substantial leap forward in medical diagnostics. "The algorithm is a great leap forward in our ability to identify these cells. Millions of biopsies are taken every year, and this technology can help us better identify risks and give women better treatment," noted Associate Professor Morten Scheibye-Knudsen from the Department of Cellular and Molecular Medicine, who is the senior author of the study.
One critical aspect of breast cancer risk assessment involves the detection of senescent cells, or 'zombie cells'. These cells, while no longer dividing, remain metabolically active and can contribute to tumor formation through inflammation. The AI’s ability to better identify these senescent cells in tissue samples enabled the researchers to predict breast cancer risk with greater accuracy compared to the Gail model, the current clinical gold standard.
Beyond its predictive accuracy, the researchers found that combining their models with the Gail score produced even more significant results. "We also found that if we combine two of our own models or one of our models with the Gail score, we get results that are far better at predicting the risk of getting cancer. One model combination gave us an odds ratio of 4.70, and that is huge. It is significant if we can look at cells from an otherwise healthy biopsy sample and predict that the donor has almost five times the risk of developing cancer several years later," said Indra Heckenbach, the study's lead author.
The AI was trained through exposure to cells in culture that were intentionally damaged to induce senescence. These cells were then used to analyse donor biopsies, focusing on changes in cell nuclei, which become more irregular as senescence sets in. Heckenbach explained, "We sometimes refer to them as zombie cells because they have lost some of their function, but they are not quite dead. They are associated with cancer development, so we developed and trained the algorithm to predict cell senescence."
Although it may take several years before this technology is widely available in clinical settings, the researchers are optimistic about its global applicability. Once deployed, the AI technology could utilise standard tissue sample images, making it accessible worldwide.
Scheibye-Knudsen emphasised the potential benefits of the technology, noting, "We will be able to use this information to stratify patients by risk and improve treatment and screening protocols. Doctors can keep a closer eye on high-risk individuals, they can undergo more frequent mammograms and biopsies, and we can potentially catch cancer earlier. At the same time, we can reduce the burden for low-risk individuals, e.g. by taking biopsies less frequently."
The study titled "Deep learning assessment of senescence-associated nuclear morphologies in mammary tissue from healthy female donors to predict future risk of breast cancer: a retrospective cohort study," authored by Indra Heckenbach and colleagues, is available in the latest issue of The Lancet Digital Health.
Source: Noah Wire Services