All datasets
AvailableCT

CTPelvic1K

CTPelvic1K is a multi-source pelvic CT dataset created for multi-class segmentation of the lumbar spine, sacrum, left hip and right hip across varied scanners and clinical imaging conditions.

Licence and access

The dataset is publicly downloadable. The authors state that the existing source datasets retain their original Creative Commons terms and that the CLINIC and CLINIC-metal subsets are released under CC BY-NC-SA 4.0. Users must review the applicable license for each component dataset.

open accesscommercial use mixedredistribution allowed
Visit official sourcelast verified 2026-09-03
Coverage
pelvishipspinesegmentationin vivo
subjects
not verified
images
1,184
formats
NIfTI
origin
Sweden · 2019
Citation
Liu P, Han H, Du Y, et al. Deep learning to segment pelvic bones: large-scale CT datasets and baseline models. International Journal of Computer Assisted Radiology and Surgery. 2021;16:749-756. DOI: 10.1007/s11548-021-02363-8.
Notes

The collection contains 1,184 three-dimensional CT volumes and more than 320,000 slices from seven sources. The number of unique subjects is not explicitly reported, so num_subjects is null. Seventy-five volumes contain metal artifacts; only 14 of those CLINIC-metal cases have annotations, while 61 unannotated cases were assigned to the training partition.

This record is a pointer. Licence and access terms are recorded as they stood on the verification date above; what binds you is the dataset's own licence text. Confirm at the source before use.

Orthopedic AI Research Updates

Monthly research digest, product updates, and clinical AI insights.

Unsubscribe anytime.

CTPelvic1K, dataset record