health 🔬 AI nails bladder cancer metastasis detection
A deep learning model successfully identified all lymph node metastases in a bladder cancer test set, showing 100% sensitivity. This was done by researchers using 100 histopathological slides collected from Sahlgrenska University Hospital between 2015 and 2024. The model achieved 60% specificity, and it significantly reduced pathologists' review times to 4.2 and 4 seconds. This suggests AI can be a practical tool to support pathology assessment in bladder cancer. Further evaluation is needed to see how these systems perform in wider clinical settings.