# Neuro-VL preprint reports gains in interpreting complete brain imaging examinations

_Published Saturday, November 14, 2026 at 6:06 AM EST · Science, AI · Latest · Tier 2 — Notable_

Researchers report in a preprint that Neuro-VL, a model trained on nearly one million neuroimaging studies from routine clinical care, outperformed general-purpose and specialized medical models at diagnosing, locating and describing abnormalities across internal and international datasets.

The model combines image interpretation with natural language conversation and generates comprehensive radiology reports. It also compared examinations taken over time to assess disease progression and resisted misleading clinical assumptions more reliably than leading models from OpenAI and Google. The reported comparisons establish performance on datasets, rather than outcomes from clinical deployment.

## Sources

- [cs.AI updates on arXiv.org](https://arxiv.org/abs/2611.15094)

---
Canonical: https://techandbusiness.org/newswire/xB2fHWun7tydXgMKHkAcBW
Published: 2026-11-14T11:06:14.307Z
Story chronology: 2026-11-14T05:00:00.000Z
Retrieved: 2026-11-15T00:01:46.308Z
Publisher: Tech & Business (techandbusiness.org)