AI model detects signs of faulty DNA repair in ovarian cancer using tissue images
An AI model created by researchers at King's can detect signs of faulty repair mechanisms in ovarian cancer cells, potentially leading to a low-cost, widely accessible diagnostic tool in the future. By analyzing tissue images, the model could accurately recognize tumors that contained broken DNA repair mechanisms. This could enable clinicians to choose treatments that exploit this flaw. The…
Researchers at King's College London have developed an AI model called HRDPath that can identify faulty DNA repair mechanisms in ovarian cancer tissue images. This breakthrough could lead to a new, accessible diagnostic tool to help clinicians choose targeted treatments for patients with high-grade serous ovarian carcinoma (HGSOC), a particularly aggressive form of ovarian cancer.
The AI model was trained on high-resolution digital images of tissue samples, enabling it to accurately detect HRD-positive cancers in about 91% of cases when multiple images per patient were analyzed. This method could make precision cancer medicine more affordable and widely available, as it would rely on existing hospital imaging procedures rather than expensive genetic testing.
Written by urgent.news from Medical Xpress's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.