文献速递神经技术与安全

NeuroAIHub:一个用于神经放射学数据集自动整理与发现的AI驱动框架

NeuroAIHub: An AI-Driven Framework for Automated Curation and Discovery of Neuroradiology Data Sets.
PubMed 文献 · AJNR Am J Neuroradiol · 2026-10-01

本研究构建了NeuroAIHub,一个AI驱动的框架,用于自动发现、提升可访问性并支持神经放射学数据集的结构化探索。该平台通过多审阅者提取和标准化元数据协调构建基础数据库,利用大语言模型每月进行网络搜索并提取结构化元数据,经开发者验证后整合。目前托管180个数据集,覆盖6个诊断领域,并提供网页应用和开源Python包。

要点

  • NeuroAIHub框架自动化发现和整理神经放射学数据集,目前托管180个数据集,覆盖6个诊断领域。
  • 平台采用大语言模型驱动的对话代理,支持自然语言数据集检索、分析查询和可视化。
  • 提供结构化网页界面和开源Python包,旨在提高数据集发现的可重复性、透明度和效率。

核心结论

  • NeuroAIHub是一个持续整理的资源平台,旨在提高神经放射学数据集发现的可重复性、透明度和效率。

研究设计与样本

  • 研究构建了AI驱动的框架,通过多审阅者提取过程与标准化元数据协调建立基础数据库,并采用基于AI的更新工作流每月进行网络搜索、使用大语言模型从异构来源提取结构化元数据,提交候选条目供开发者验证后整合。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

英文原文(摘要)· 点击展开

Neuroradiology data sets have significant potential for advancing neuroimaging research, yet identifying relevant and up-to-date resources remains challenging. NeuroAIHub is an artificial intelligence (AI)-driven framework designed to automate data set discovery, improve accessibility, and support structured exploration of neuroradiology data sets. A foundational database was constructed through a multireviewer extraction process with standardized metadata harmonization. To maintain and expand the registry, an AI-based updating workflow performs monthly Web searches, extracts structured metadata from heterogeneous sources using large language models, and submits candidate entries for developer validation before integration. A large language model-powered conversational agent enables natural language data set retrieval, analytical queries, and visualizations, while a structured Web interface supports reproducible filtering. NeuroAIHub currently hosts 180 data sets across 6 diagnostic domains and is available as a Web application (https://neuroai.streamlit.app/) and an open-source Python package (https://github.com/NeuroAIHub-Registry/NeuroAIHub; https://pypi.org/project/neuroaihub). The platform provides a continuously curated resource designed to improve reproducibility, transparency, and efficiency in neuroradiology data set discovery.

来源:AJNR Am J Neuroradiol,查看原文。版权归原作者所有。

引用

  1. Gheiji B, Moradi S, Vatanparast M, et al. NeuroAIHub: An AI-Driven Framework for Automated Curation and Discovery of Neuroradiology Data Sets. AJNR Am J Neuroradiol. 2026. PMID: 42031665. doi:10.3174/ajnr.A9363

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。