The RSNA Cervical Spine Fracture CT Dataset
Hui Ming Lin1, Errol Colak1, Tyler Richards1
1From the Department of Medical Imaging, St Michael's Hospital, Unity Health Toronto, 30 Bond St, Toronto, ON, Canada M5B 1W8 (H.M.L., E.C.); Department of Medical Imaging, University of Toronto, Toronto, Ontario, Canada (E.C.); Department of Radiology and Imaging Sciences, University of Utah, Salt Lake City, Utah (T.R.); Dasa, Universidade Federal de São Paulo (Unifesp), São Paulo, Brazil (F.C.K.); Department of Radiology, The Ohio State University, Columbus, Ohio (L.M.P.); Department of Radiology and Biomedical Imaging, University of California, San Francisco, San Francisco, Calif (J.T.); The Jackson Laboratory, Bar Harbor, Maine (R.L.B.); Department of Radiology, Hacettepe University, Ankara, Turkey (E.G.); Standard School of Medicine, Stanford University, Stanford, Calif (K.W.Y.); School of Computing (M.H., A.L.S., J.J.P.), Department of Biomedical and Molecular Sciences (A.L.S.), and Department of Diagnostic Radiology (J.O.J.), Queen's University, Kingston, Ontario, Canada; Department of Biomedical Engineering, Qazvin Branch, Islamic Azad University, Qazin, Iran (M.H.); Department of Radiology, Cantonal Hospital Zenica, Zenica, Bosnia and Herzegovina (J.S.); Clinic of Radiology, Clinical Center University of Sarajevo, Sarajevo, Bosnia and Herzegovina (D.B.); Department of Radiology, Chiang Mai University, Chiang Mai, Thailand (S.A.); Department of Radiology, Hospital Regional Universitario de Málaga, Málaga, Spain (A.P.L.); Department of Radiology, Hospital Quirónsalud Málaga, Málaga, Spain (M.I.G.A.); Department of Radiology and Nuclear Medicine, Alfred Health, Monash University, Melbourne, Australia (M.L.); Department of Radiology, Koç University School of Medicine, Istanbul, Turkey (H.D., E.A.); Department of Diagnostic, Molecular and Interventional Radiology, Icahn School of Medicine at Mount Sinai, New York, NY (E.A.); Department of Radiology, National Cancer Institute, Cairo University, Cairo, Egypt (A.Y.); Department of Radiology, Sultan Qaboos University Hospital, Muscat, Oman (Y.M.); Department of Ophthalmology, University of Colorado Anschutz Medical Campus, Aurora, Colo (J.K.C.); Department of Radiology and Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital, Charlestown, Mass (J.K.C.); and Department of Radiology, Division of Neuroradiology, Thomas Jefferson University, Philadelphia, Pa (A.E.F.).
This dataset provides cervical spine CT images with fracture annotations. These resources aid in developing and validating AI models for detecting cervical spine fractures.
Area of Science:
- Radiology
- Medical Imaging
- Artificial Intelligence
Background:
- Cervical spine fractures are critical injuries requiring accurate and timely diagnosis.
- Medical imaging, particularly CT scans, are essential for identifying these fractures.
- Developing advanced diagnostic tools can improve patient outcomes.
Purpose of the Study:
- To present a comprehensive dataset of cervical spine CT images.
- To provide annotations for fractures within these images.
- To facilitate research in automated cervical spine fracture detection.
Main Methods:
- The dataset comprises cervical spine CT scans.
- Annotations detail the presence and location of fractures.
- Data is made available for public access and research.
Main Results:
- A collection of annotated cervical spine CT images is established.
- The dataset enables the training and evaluation of machine learning models.
- This resource supports advancements in diagnostic accuracy.
Conclusions:
- The availability of this dataset is crucial for AI-driven fracture detection research.
- It serves as a valuable tool for the medical imaging community.
- Further development of AI algorithms can be accelerated using this data.


