Open dataset · CT

TotalSegmentator (v2)

1228 real clinical CT scans with 117-structure ground-truth segmentations.

Open a case in your browser Create free account

No download, no account needed for the demo case — it opens read-only in the MedSeg editor. Sign up (free) to browse all 1,228 cases, run AI models, and segment.

CT 1,228 cases CC-BY-4.0 Reference masks Pathology
TotalSegmentator (v2) — example case rendered in the MedSeg editor
Example case with its reference segmentation — straight from the catalog, rendered by MedSeg.

Browse cases

Demo cases open instantly in the browser-based editor — scroll the slices, inspect the reference masks, window the image. Everything else is one free account away.

s0698 — TotalSegmentator (v2) case preview

s0698Open preview

 s0490 — TotalSegmentator (v2) case preview

s0490Open preview

 s0006 — TotalSegmentator (v2) case preview

s0006Sign up to open

 s0010 — TotalSegmentator (v2) case preview

s0010Sign up to open

 s0011 — TotalSegmentator (v2) case preview

s0011Sign up to open

 s0012 — TotalSegmentator (v2) case preview

s0012Sign up to open

About this dataset

TotalSegmentator is a dataset of 1228 CT scans from routine clinical practice at University Hospital Basel, annotated with 117 anatomical structures per case. The cohort spans multiple scanners (Siemens, GE, Philips, Toshiba, Canon), ages from pediatric to elderly, mixed contrast/non-contrast, and a wide range of body regions and clinical indications — the variety is the point, and it's why a TotalSegmentator-trained model generalizes.

The dataset doubles as the training set behind the TotalSegmentator model that's bundled into MedSeg, so any case here also lets you compare the bundled model's output against the published ground truth.

FactValue
Cases1,228
Series1,228
Size22.6 GB
ModalityCT
Reference masksYes
LicenseCC-BY-4.0
PublisherUniversity Hospital Basel
Versionv2.0.1
DOI10.5281/zenodo.10047292

What you can do with it in MedSeg

Copied cases behave like normal project series — the public image bytes are linked, not duplicated, so copies are instant and take no extra storage.

  1. Copy cases into a project.
    Filter, multi-select, copy — reference masks come along if you want them.
  2. Run AI segmentation.
    TotalSegmentator, MRSegmentator, nnInteractive 3D clicks/scribbles, or text-prompted VoxTell.
  3. Edit and measure.
    Brush, lasso, fill, oblique planes, volumes in ml — in the browser.
  4. Train your own nnU-Net.
    Correct masks on a handful of cases and train a custom model on hosted GPUs.

Citation

If you use this dataset in your research, cite the source per its license terms.

Wasserthal, J., Breit, H.-C., Meyer, M. T., Pradella, M., Hinck, D., Sauter, A. W., Heye, T., Boll, D., Cyriac, J., Yang, S., Bach, M., & Segeroth, M. (2023). TotalSegmentator: Robust segmentation of 104 anatomical structures in CT images. Radiology: Artificial Intelligence, 5(5), e230024.

License: CC-BY-4.0

Open data still carries obligations — attribution at minimum. Check the license terms and the source publication before publishing work built on this dataset. MedSeg is a research tool, not a medical device.

More public datasets