Health system learning achieves generalist neuroimaging models.

ABSTRACT: Frontier artificial intelligence (AI) models, such as OpenAI's GPT-5 (1) and Meta's DINOv3 (2), have advanced rapidly through training on internet-scale public data, yet such systems lack access to private clinical data. Neuroimaging, in particular, is underrepresented in the public domain due to identifiable facial features within MRI and CT scans, fundamentally restricting model performance in clinical medicine (3). Here, we show that frontier models underperform on neuroimaging tasks and that learning directly from uncurated data generated during routine clinical care at health systems, a paradigm we call health system learning, yields high-performance, generalist neuroimaging models. We introduce NeuroVFM, a visual foundation model trained on 5.24 million clinical MRI and CT volumes us

SUBMITTER: Kondepudi A 

PROVIDER: S-EPMC12687827 | biostudies-literature | 2025 Dec

REPOSITORIES: biostudies-literature