Reviewed by Danielle Ellis, B.Sc.Sep 26 2024
According to a new study published in The Lancet Digital Health, women around the world could benefit from improved treatment, thanks to new AI technology that allows for better detection of damaged cells and more precise prediction of the risk of developing breast cancer.
Breast cancer is among the most common types of cancer. In 2022, the disease claimed 670,000 lives worldwide. A new study from the University of Copenhagen shows that AI can help women with better treatment by scanning for irregular-looking cells and providing a more accurate risk assessment.
According to the study, AI technology outperformed current clinical benchmarks for assessing breast cancer risk.
Utilizing deep learning artificial intelligence (AI) technology created at the University of Copenhagen, the researchers examined donor mammary tissue biopsies for indications of damaged cells, which could be a sign of cancer risk.
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.
Morten Scheibye-Knudsen, Study Senior Author and Associate Professor, Department of Cellular and Molecular Medicine, University of Copenhagen
Predicts Cases of Five Times the Risk of Breast Cancer
Searching for dying cells—a result of a process known as cellular senescence—is a fundamental part of determining cancer risk. Although they are no longer dividing, senescent cells are still metabolically active. Prior research has linked this senescent state to the suppression of cancer development. Senescent cells may also trigger inflammation, which can result in tumor growth.
The researchers were able to predict the risk of breast cancer more accurately than the Gail model, which is currently the gold standard for estimating breast cancer risk, by using deep learning AI to look for senescent cells in tissue biopsies.
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 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.
Indra Heckenbach, Study First Author, University of Copenhagen
Algorithm Trained on ‘Zombie Cells’ Can Give Better Treatment
The researchers trained the artificial intelligence technology using purposefully damaged, senescent cells cultivated in cell culture. They then used the AI to detect senescent cells in the donor biopsies.
“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. Specifically, our algorithm looks at how the cell nuclei are shaped, because the nuclei become more irregular when the cells are senescent,” added Indra Heckenbach.
The technology will not be ready for clinical use for several years, but once it is, it can be used anywhere in the world because it only needs standard tissue sample images to perform the analysis. Then, using this new understanding, women everywhere might be able to receive better care.
We will be able 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.
Morten Scheibye-Knudsen, Study Senior Author and Associate Professor, Department of Cellular and Molecular Medicine, University of Copenhagen
Journal Reference:
Heckenbach, I., et al. (2024) 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. The Lancet Digital Health. doi.org/10.1016/S2589-7500(24)00150-X