# Health system learning achieves generalist neuroimaging models

arXiv: https://arxiv.org/abs/2511.18640 · HTML: https://mlsanity.com/paper/2511.18640/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Nov 2025.

## Built on by (most cited first, 6 of 6)

- [CodeV: Code with Images for Faithful Visual Reasoning via Tool-Aware Policy Optimization](https://mlsanity.com/paper/2511.19661/) (2025)
- [CoRe-BT: A Multimodal Radiology-Pathology-Text Benchmark for Robust Brain Tumor Typing](https://mlsanity.com/paper/2603.03618/) (2026)
- [From Clever Hans to Scientific Discovery: Interpreting EEG Foundational Transformers with LRP](https://mlsanity.com/paper/2605.11885/) (2026)
- [Large Language Models Predict Functional Outcomes after Acute Ischemic Stroke](https://mlsanity.com/paper/2602.10119/) (2026)
- [DS@GT ARC at MEDIQA-CORE-Task-1 2026: Trimodal Model Fusion with Task-Specific Gates for Brain Tumor Subtype Classification](https://mlsanity.com/paper/2608.00086/) (2026)
- [Evaluating the Generalization of Neuroimaging Foundation Models on African Brain MRI](https://mlsanity.com/paper/2609.23983/) (2026)

## Abstract (arXiv)

Frontier artificial intelligence (AI) models, such as OpenAI's GPT-5 and Meta's DINOv3, 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. 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 using a scalable volumetric joint-embedding predictive architecture. NeuroVFM learns comprehensive representations of brain anatomy and pathology, achieving state-of-the-art performance across multiple clinical tasks, including radiologic diagnosis and report generation. The model exhibits emergent neuroanatomic understanding and interpretable visual grounding of diagnostic findings. When paired with open-source language models through lightweight visual instruction tuning, NeuroVFM generates radiology reports that surpass frontier models in accuracy, clinical triage, and expert preference. Through clinically grounded visual understanding, NeuroVFM reduces hallucinated findings and critical errors, offering safer clinical decision support. These results establish health system learning as a paradigm for building generalist medical AI and provide a scalable framework for clinical foundation models.