A Survey of Publicly Available MRI Datasets for Potential Use in Artificial Intelligence Research
Journal of Magnetic Resonance Imaging · 2024
DOI: 10.1002/jmri.29101 ↗Kurz gefasst
Übersichtsarbeit in der Zeitschrift Journal of Magnetic Resonance Imaging, 2024. Verfasst von Katharine A Dishner und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, Memorial Sloan Kettering Cancer Center, New York City, New York, USA. Hauptthemen laut MEDLINE: Artificial Intelligence, Radiology. Die Arbeit wurde bisher 29-mal zitiert (Crossref) und nennt 62 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIA NIH HHS, NCI NIH HHS.
Abstract (Originalsprache)
Artificial intelligence (AI) has the potential to bring transformative improvements to the field of radiology; yet, there are barriers to widespread clinical adoption. One of the most important barriers has been access to large, well‐annotated, widely representative medical image datasets, which can be used to accurately train AI programs. Creating such datasets requires time and expertise and runs into constraints around data security and interoperability, patient privacy, and appropriate data use. Recognizing these challenges, several institutions have started curating and providing publicly available, high‐quality datasets that can be accessed by researchers to advance AI models. The purpose of this work was to review the publicly available MRI datasets that can be used for AI research in radiology. Despite being an emerging field, a simple internet search for open MRI datasets presents an overwhelming number of results. Therefore, we decided to create a survey of the major publicly accessible MRI datasets in different subfields of radiology (brain, body, and musculoskeletal), and list the most important features of value to the AI researcher. To complete this review, we searched for publicly available MRI datasets and assessed them based on several parameters (number of subjects, demographics, area of interest, technical features, and annotations). We reviewed 110 datasets across sub‐fields with 1,686,245 subjects in 12 different areas of interest ranging from spine to cardiac. This review is meant to serve as a reference for researchers to help spur advancements in the field of AI for radiology. Level of Evidence Level 4 Technical Efficacy Stage 6
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Radiology, Memorial Sloan Kettering Cancer Center, New York City, New York, USA.
- SUNY Downstate College of Medicine, Brooklyn, New York, USA.
- Weill Cornell Medicine, New York City, New York, USA.
- Department of Radiology, Weill Cornell Medicine, New York City, New York, USA.
- Department of Neuroscience, Weill Cornell Graduate School of the Medical Sciences, New York City, New York, USA.
ORCID-Profile: Katharine A Dishner, Bala McRae-Posani, Katja Pinker
Förderung
- NIA NIH HHS
- NCI NIH HHS
Zitieren
APA
Dishner, K. A., McRae-Posani, B., Bhowmik, A., Jochelson, M. S., Holodny, A., Pinker, K., Eskreis-Winkler, S., & Stember, J. N. (2024). A Survey of Publicly Available MRI Datasets for Potential Use in Artificial Intelligence Research. Journal of Magnetic Resonance Imaging. https://doi.org/10.1002/jmri.29101
Vancouver
Dishner KA, McRae-Posani B, Bhowmik A, Jochelson MS, Holodny A, Pinker K, et al. A Survey of Publicly Available MRI Datasets for Potential Use in Artificial Intelligence Research. Journal of Magnetic Resonance Imaging. 2024. doi:10.1002/jmri.29101
BibTeX
@article{Dishner2024,
author = {Dishner, Katharine A and McRae-Posani, Bala and Bhowmik, Arka and Jochelson, Maxine S and Holodny, Andrei and Pinker, Katja and Eskreis-Winkler, Sarah and Stember, Joseph N},
title = {A Survey of Publicly Available MRI Datasets for Potential Use in Artificial Intelligence Research},
journal = {Journal of Magnetic Resonance Imaging},
year = {2024},
doi = {10.1002/jmri.29101}
}
EUVIMED