Open dataset · CT

MedSeg COVID-19 CT

Name: MedSeg COVID-19 CT
Creator: MedSeg
License: https://creativecommons.org/publicdomain/zero/1.0/

Radiologist COVID-19 lung CT segmentations: ground-glass, consolidation, pleural effusion.

Open a sample case in your browser Open the full dataset in MedSeg →

The sample cases below open read-only in the MedSeg editor - no account needed. Open the full dataset to copy all 10 cases into your workspace, run AI models, and segment.

CT 10 cases CC0-1.0 Reference masks Pathology

MedSeg COVID-19 CT - example case rendered in the MedSeg editor — Example case with its reference segmentation - straight from the catalog, rendered by MedSeg.

Browse sample cases

These cases open instantly in the browser-based editor - scroll the slices, inspect the reference masks, window the image. No account needed.

dataset-1-100-axial-slices - MedSeg COVID-19 CT case preview

dataset-1-100-axial-slicesOpen

dataset-2-case-01 - MedSeg COVID-19 CT case preview

dataset-2-case-01Open

dataset-2-case-02 - MedSeg COVID-19 CT case preview

dataset-2-case-02Open

dataset-2-case-03 - MedSeg COVID-19 CT case preview

dataset-2-case-03Open

dataset-2-case-04 - MedSeg COVID-19 CT case preview

dataset-2-case-04Open

dataset-2-case-05 - MedSeg COVID-19 CT case preview

dataset-2-case-05Open

Open the full dataset in MedSeg → All 10 cases - copy into your workspace to run AI and segment.

About this dataset

MedSeg's COVID-19 CT segmentation data - the dataset MedSeg is best known for. Two figshare sets are combined here:

- Case 1 is *Dataset 1*: 100 axial CT slices (one slice per patient, from >40 COVID-19 patients) stacked into a single volume. - Cases 2-10 are *Dataset 2*: 9 whole-volume axial CT scans (positive and negative slices).

Every slice was segmented by a radiologist into ground-glass opacity, consolidation, and pleural effusion.

Source images: Dataset 1 from SIRM (sirm.org), Dataset 2 from Radiopaedia - both openly shared for research and education.

Fact	Value
Cases	10
Series	10
Size	0.5 GB
Modality	CT
Reference masks	Yes
License	CC0-1.0
Publisher	MedSeg
Version	-
DOI	10.6084/m9.figshare.13521488

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.

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

License: CC0-1.0

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.