AI reveals distinct cell defects inside breast cancer

Researchers at the University of Southampton have developed a powerful AI tool that reveals previously invisible patterns inside breast cancers. It uncovers how tiny cellular structures called centrosomes change as tumors grow, spread and evolve. The technology could help clinicians identify high-risk patients, predict how breast cancer might progress and deliver more targeted treatments.
    CenSegNet, an open-source AI platform created by researchers, can analyze hundreds of thousands of cells in tumor samples with unprecedented speed and precision. The technology allows scientists to map centrosome abnormalities across entire tumors and identify how these defects vary between different parts of the same cancer. The results have been published in Nature Communications.

    Dr. Salah Elias, who led the research at the University of Southampton’s School of Biological Sciences and Institute for Life Sciences, said, “For more than a century, centrosome abnormalities have been recognized as a hallmark of cancer, but studying them in patient tissues has been extremely challenging. Centrosomes act as the cell’s organizing hubs, helping cells divide correctly and maintain their structure. When centrosomes become abnormal, cells can accumulate genetic errors—a trait of cancer.

    Sign up for Blog Updates