Skip to content
DraconiticResearch
Search Sources API
203,948 studies31 sourcesUpdated 41 min ago
Peer-reviewedCC BYAJNR: American Journal of Neuroradiology

NeuroAIHub: An AI-Driven Framework for Automated Curation and Discovery of Neuroradiology Data Sets

  • Benyamin Gheiji1
  • Sina Moradi2
  • Mahsa Vatanparast1
  • Sana Shokrani3
  • Mohammad Aref Bagherzadeh4,5
  • Danial Elyassirad1
  • Oluwatobi Iyanuoluwa Akinmuleya6
  • Sina Goodarzi7
  • Mahsa Heidari-Foroozan8
  • Mana Moassefi9
  • Jeffrey D. Rudie10,11
  • Evan Calabrese12
2 more authors
  • R. Jain13
  • Shahriar Faghani9,14
14 affiliations
  1. 1From the Mashhad University of Medical Sciences (B.G., M.V., D.E.), Mashhad, Iran
  2. 2Zumud (S.M.), Twickenham, London, UK
  3. 3Tehran University of Medical Sciences (S.S.), Tehran, Iran
  4. 4Research Center for Noncommunicable Diseases (M.A.B.), Jahrom University of Medical Sciences, Jahrom, Iran
  5. 5Department of Immunology (M.A.B.), Jahrom University of Medical Sciences, Jahrom, Iran
  6. 6Department of Medicine (O.I.A.), Shenyang Medical College, Liaoning, Shenyang, China
  7. 7Lorestan University of Medical Sciences (S.G.), Khorramabad, Iran
  8. 8Shahid Beheshti University of Medical Sciences (M.H.-F.), Tehran, Iran
  9. 9Radiology Informatics Lab (M.M., S.F.), Department of Radiology, Mayo Clinic, Rochester, Minnesota
  10. 10Department of Radiology (J.D.R.), University of California San Diego, San Diego, California
  11. 11Department of Radiology (J.D.R.), Scripps Clinic Medical Group, San Diego, California
  12. 12Department of Radiology (E.C.), Duke University Medical Center, Durham, North Carolina
  13. 13Department of Radiology and Neurosurgery (R.J.), NYU Grossman School of Medicine, New York, New York
  14. 14Department of Radiolog y (S.F.), University of Pennsylvania, Philadelphia, Pennsylvania
Read full textDOICite

Abstract

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.

Related

  1. Artificial Intelligence in Neuroradiology: Transforming Diagnosis, Prognostication, and Workflow.
    Tamaghna Ghosh
    The Indian journal of radiology & imagingPeer-reviewedCC BY-NC-NDFull textEpidemiology & public healthEurope PMC
  2. [A History of Neuro-Head and Neck Radiology in Korea Focused on the Korean Society of Neuroradiology].
    Inpyeong Hwang, Yun Jung Bae, Hye Jin Baek +2
    Journal of the Korean Society of RadiologyPeer-reviewedCC BY-NCFull textMedical imaging & radiologyEurope PMC
  3. Automated model discovery based on COVID-19 epidemiological data from Thuringia, Germany
    Morteza Babazadeh Shareh, Florian Kleiner, Michael Böhme +3
    PLOS OnePeer-reviewedCC BY 4.0Full textImmunologyEpidemiology & public healthPLOS
  4. CERVEX: A Foundation-Model Framework With Built-In Explainable AI for Automated Cervical Cytology Classification From Pap Smear Images
    N. Sriratana, P. Pongsiripreeda, P. Uasawaengboon +2
    medRxivPreprintAll rights reservedFull textGeneral medicinemedRxiv
  5. A Semi-Automated Interactive Annotation Framework for Intraoperative Neurosurgical Ultrasound: A Proof-of-Concept Study
    R. Bertani, S. Bahadir, M. Y. Ferreira +3
    medRxivPreprintAll rights reservedFull textMedical imaging & radiologymedRxiv

Cite

BibTeXRIS
BibTeX
@article{gheiji2026neuroaihub,
  title = {{NeuroAIHub: An AI-Driven Framework for Automated Curation and Discovery of Neuroradiology Data Sets}},
  author = {Benyamin Gheiji and Sina Moradi and Mahsa Vatanparast and Sana Shokrani and Mohammad Aref Bagherzadeh and Danial Elyassirad and Oluwatobi Iyanuoluwa Akinmuleya and Sina Goodarzi and Mahsa Heidari-Foroozan and Mana Moassefi and Jeffrey D. Rudie and Evan Calabrese and R. Jain and Shahriar Faghani},
  journal = {AJNR: American Journal of Neuroradiology},
  year = {2026},
  month = nov,
  doi = {10.3174/ajnr.a9363},
  url = {https://doi.org/10.3174/ajnr.a9363},
  note = {CC BY},
}
RIS
TY  - JOUR
TI  - NeuroAIHub: An AI-Driven Framework for Automated Curation and Discovery of Neuroradiology Data Sets
AU  - Benyamin Gheiji
AU  - Sina Moradi
AU  - Mahsa Vatanparast
AU  - Sana Shokrani
AU  - Mohammad Aref Bagherzadeh
AU  - Danial Elyassirad
AU  - Oluwatobi Iyanuoluwa Akinmuleya
AU  - Sina Goodarzi
AU  - Mahsa Heidari-Foroozan
AU  - Mana Moassefi
AU  - Jeffrey D. Rudie
AU  - Evan Calabrese
AU  - R. Jain
AU  - Shahriar Faghani
PY  - 2026
DA  - 2026/11/06
JO  - AJNR: American Journal of Neuroradiology
DO  - 10.3174/ajnr.a9363
UR  - https://doi.org/10.3174/ajnr.a9363
AB  - 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.
SN  - 0195-6108
SN  - 1936-959X
ER  -