Published August 28, 2025
| Version 2.0.1
Model
Open
TS2D-V2-R001
Authors/Creators
Contributors
Researcher (2):
Description
This dataset comprises models for TotalSegmentator (TS2D) Tool (see Github).
The model checkpoints have been trained on the v2.0.1 TotalSegmentator dataset and constitute the initial release (R001). The checkpoints were generated using nnU-Net, which is also used within TS2D for inference.
Each model was trained on a specific subset of labels from the TotalSegmentator dataset.
This release includes:
- Cardiac: 18 cardiovascular structures, trained using mean and max intensity images
- Muscles: 23 musculoskeletal structures, including the brain and spinal-cord, using mean and max intensity images
- Organs: 24 organ structures, using mean and max intensity images
- Ribs: 26 ribs, including sternum and costal-cartilages, using mean and max intensity images
- Vertebrae: 26 vertebrae, including the sacrum, using mean and max intensity images
Files
ts2d-v2-ep4000b2_cardiac.zip
Files
(1.3 GB)
| Name | Size | Download all |
|---|---|---|
|
md5:4977642c0172d263c37f14a01ef7373f
|
252.0 MB | Preview Download |
|
md5:7a8d951d710654dd29bd4f8014c975dd
|
255.0 MB | Preview Download |
|
md5:2c8c9a8a924cfcd7a82f587bd6b95550
|
253.0 MB | Preview Download |
|
md5:cee0d87e77fba50bb2ad96b48dc94dec
|
253.3 MB | Preview Download |
|
md5:2c8d2975070b63a7c0c60190f565a81f
|
254.0 MB | Preview Download |
Additional details
Related works
- Is derived from
- Dataset: 10.5281/zenodo.6802614 (DOI)
- Is part of
- Conference paper: 10.1007/978-3-031-98694-9_3 (DOI)
Funding
- Austrian Research Promotion Agency
- MEDUSA 872604
- Upper Austrian Research
Software
- Repository URL
- https://github.com/risc-mi/totalsegmentator2D
- Programming language
- Python
- Development Status
- Active