AI can predict breast cancer relapse from histology images

Every 14 seconds, across the globe, a woman is diagnosed with breast cancer —  and approximately 10% of all patients will relapse after their initial treatment each year. Risk determination is crucial for treatment decisions because breast cancer is a heterogeneous disease encompassing several subtypes associated with a wide range of prognoses.

So Owkin is developing RlapsRisk BC, an AI-based tool that assesses the risk of distant relapse, at 5 years, of ER+/HER2- early invasive breast cancer patients, post surgery, from HE- and HES-stained whole slide histology images and clinical data. This model accurately discriminates between low and high risk breast cancer patients (ER+/HER2) using digital pathology slides on resection pieces and improves  patients identification compared with clinical scores.