The American College of Radiology (ACR) Data Science Institute (DSI) has introduced an artificial intelligence (AI) federated learning program on its AI-LAB platform.
Available for free, the vendor-neutral toolset enables users to test out, develop, and train AI algorithms using their institution's local patient data, according to the ACR DSI. With the federated learning approach, registered sites can collaborate with multiple other institutions to develop algorithms while keeping their data on their own servers.
In addition to being able to access the community-created models, participants can also view anonymized performance benchmarks to help them understand the performance of the algorithm produced by the community compared with a model that's fine-tuned to the site's own data, the ACR DSI said.
![A normal mammogram confirmed by three-year radiologic follow-up illustrates reader-marked regions of interest (ROIs) during (A) unaided (round 1) and (B) artificial intelligence (AI)–assisted (round 2) reading. Each colored dot represents an ROI for recall by a human reader. Readers could mark more than one ROI per case, represented by multiple dots of the same color. During AI-assisted reading, the AI system displayed three visible prompts: two with suspicion of malignancy scores of 35% (left mediolateral oblique [L MLO] and craniocaudal [L CC]) and one with a suspicion of malignancy score of 10% (right craniocaudal [R CC]), shown as polygonal overlays. Without AI, six of 10 readers (60%) marked a false-positive ROI. With AI assistance, this fell to two of 10 (20%). R MLO = right mediolateral oblique.](https://img.auntminnie.com/mindful/smg/workspaces/default/uploads/2026/07/2026-07-14-radiology-mammogram-ai-auto-bias.H0bYO8QlWs.jpg?auto=format%2Ccompress&dpr=2&fit=crop&h=167&q=70&w=250)
