Deep Learning Algorithm Could Improve Breast Cancer Risk Prediction

University of Copenhagen researchers report that artificial intelligence can improve breast cancer detection and risk assessment. Their research, published in The Lancet Digital Health, demonstrates that AI technology outperforms current clinical benchmarks in predicting breast cancer risk.

The study utilized deep learning AI to analyze mammary tissue biopsies, focusing on identifying senescent cells—damaged cells that have stopped dividing but remain metabolically active. These "zombie cells" are associated with both cancer suppression and potential tumor development due to inflammation.

Morten Scheibye-Knudsen, the study's senior author, emphasized the technology's potential impact: "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."

The AI model, when combined with existing risk assessment tools like the Gail model, showed remarkable predictive power. Indra Heckenbach, the study's first author, noted, "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."

The AI was trained on intentionally damaged cells in culture before being applied to donor biopsies. It specifically analyzes the shape of cell nuclei, which become more irregular in senescent cells.

While the technology is still years away from clinical use, its potential is significant. It could enable more personalized treatment approaches, allowing for closer monitoring of high-risk individuals and reduced burden on those at lower risk. Scheibye-Knudsen concludes, "We will be able use this information to stratify patients by risk and improve treatment and screening protocols."