fidoptCT-FM whole-body segmentation
CT-FM's whole-body model, a SegResNet pretrained by self-supervision on 148,000 CTs and fine-tuned on TotalSegmentator's training split: TotalSegmentator v2's 117 structures of a CT at its own resolution, run as its model card's notebook runs it.
SegmentationGPUversion whole_body_segmentation 96b49a7 (model.safetensors sha256 16815842), lighter_zoo 0.1.3, MONAI 1.4.0CTApache-2.0
Run it
With its KonfAI app, at the benchmark's settings (the fidopt app repositories are private for now: a Hugging Face token with access opens them):
pip install konfai-apps konfai-apps infer fideus-labs/fidopt-segmentation:CTFM_WholeBody -i image.nii.gz -o out --gpu 0
The app on Hugging Face: its model, its settings and how it is scored.
Where it works
Its place on each kind of problem it has results on, among the methods ranked there. A method that leads one problem can trail another: read the one closest to yours.
| Problem | Place | Ranked | Datasets |
|---|---|---|---|
| Clinical pelvic bones, CTPelvic1K | 3 | of 5 | 1 of 1 |
| Liver segmentation on CT without physical geometry | 4 | of 5 | 1 of 1 |
| Abdomen CT, segmentation | not ranked yet | 7 of 12 | |
| Body CT, many structures, segmentation | not ranked yet | 1 of 5 | |
| Spine, bones and joints, segmentation | not ranked yet | 3 of 9 | |
| Prostate and pelvis, segmentation | not ranked yet | 1 of 6 |
Results
| Dataset | # | Read by | Score | Failed | Time s |
|---|---|---|---|---|---|
| AMOS CT, abdominal organs | 3 | Dice | 0.351 | 0 | 56 |
| COVID-19 CT Lung and Infection | 6 | Dice | 0.571 | 1 | 79 |
| Colorectal-Liver-Metastases, liver and veins | 5 | Dice | 0.861 | 0 | 24 |
| CT-ORG | 5 | Dice | 0.764 | 0 | 214 |
| CTPelvic1K, CLINIC pelvic bones | 3 | Dice | 0.930 | 0 | 159 |
| FLARE22 | 4 | Dice | 0.395 | 5 | 14 |
| HaN-Seg | 5 | Dice | 0.404 | 0 | |
| Abdomen CT (Learn2Reg 2020, Task 3) | 4 | Dice | 0.209 | 0 | 5 |
| CT follow-up of liver metastases, liver | 3 | Dice | 0.000 | 0 | 8 |
| PLC-CECT, delayed-phase liver segmentation | 4 | Dice | 0.320 | 2 | 57 |
| MSD Liver | 3 | Dice | 0.831 | 1 | 220 |
| MSD Pancreas | 4 | Dice | 0.353 | 8 | 22 |
| MSD Spleen | 4 | Dice | 0.245 | 5 | 19 |
| Spinal-Multiple-Myeloma-SEG, vertebrae and lytic lesions | 3 | Dice | 0.355 | 0 | 398 |
| PENGWIN CT | 3 | Dice | 0.907 | 0 | 101 |
| Pancreas-CT, 8 organs | 3 | Dice | 0.766 | 0 | 86 |
| Prostate-Anatomical-Edge-Cases | 4 | Dice | 0.719 | 0 | 103 |
| RibSeg v2, individual ribs | 3 | Dice | 0.573 | 0 | 164 |
| VerSe, vertebrae | 2 | Dice | 0.272 | 5 | 232 |
- Source
- huggingface.co/project-lighter/whole_body_segmentation/tree/96b49a7c62ff7185b9ad2320686d33318ecd2f1e
- Reference
- Pai et al., arXiv:2501.09001, 2025 (CT-FM)