Case Study
Mammography – Collaborative AI training with locally retained images
Innowise implemented distributed training for mammography image models.
AI-generated imageCountry
Europe
Industry
Healthcare
Technologies
Federated Learning, Mask R-CNN
Challenge
Clinics wanted to learn from more varied imaging datasets while keeping raw patient images within each institution.
Solution
Mask R-CNN models trained locally, with a central process aggregating updates. Preprocessing and evaluation followed a shared protocol.
Results
Innowise reports segmentation AP gains of up to 68.6% against the weakest single-site baseline. This measures model performance, not an equivalent improvement in clinical diagnoses.