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.
Researchers at the University of Southampton have created an AI tool called CenSegNet that can detect subtle changes in breast cancer cells, specifically in structures called centrosomes. These centrosomes, which act as cellular organizing hubs, can become abnormal as tumors grow and spread, potentially leading to cancer. The AI platform can analyze hundreds of thousands of centrosomes in tumor samples, revealing patterns invisible to traditional methods.
This technology could help identify high-risk patients, predict cancer progression, and enable more targeted treatments. The study, published in Nature Communications, analyzed over 330,000 centrosomes from 911 breast cancer patients, discovering two distinct types of centrosome abnormalities that behave independently and have different spatial distributions within tumors.
Enlarged centrosomes were linked to more aggressive tumors, higher disease grade, and poorer survival rates, while fewer in the tumor core correlated with better overall survival. This research opens new avenues for developing personalized treatment strategies and biomarkers, although the technology is not yet ready for clinical use.
The open-source software could be adopted by scientists worldwide, potentially expanding its application to other cancers and tissues.
Written by urgent.news from Medical Xpress's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
