Back to all papers

The Duke University Cervical Spine MRI Segmentation Dataset (CSpineSeg).

October 27, 2025pubmed logopapers

Authors

Zhou L,Wiggins W,Zhang J,Colglazier R,Willhite J,Dixon A,Malinzak M,Gu H,Mazurowski MA,Calabrese E

Affiliations (5)

  • Gannon University, Erie, USA.
  • Duke University Medical Center, Durham, USA.
  • Duke University, Durham, USA. [email protected].
  • Duke University School of Medicine, Durham, USA.
  • Duke University, Durham, USA.

Abstract

This work describes a publicly available dataset, the Duke University Cervical Spine MRI Segmentation Dataset (CSpineSeg), consisting of 1,255 cervical spine magnetic resonance imaging (MRI) examinations from 1,232 patients collected from the Duke University Health System. CSpineSeg also includes expert manual semantic segmentations of vertebral bodies and intervertebral discs for 481 patients. This dataset aims to provide a resource for training and evaluation of deep learning segmentation models and facilitate cervical spine research. Along with the dataset, we present a deep learning segmentation model which could be used as a benchmark in cervical spine segmentation tasks. Our segmentation model achieves a Dice Coefficient of 0.916, demonstrating the feasibility of utilizing CSpineSeg to train segmentation models.

Topics

Magnetic Resonance ImagingCervical VertebraeJournal ArticleDataset

Ready to Sharpen Your Edge?

Join hundreds of your peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.

We respect your privacy. Unsubscribe at any time.