fidoptVerSe, vertebrae
22 cases · ordered on Dice| # | Method | Dice |
|---|---|---|
| 1 | KonfAI segmentation app · TotalSegmentator (total), KonfAI app | 0.574 |
| 2 | CT-FM whole-body segmentation | 0.272 |
| 3 | MONAI wholeBody CT | 0.113 |
Spine, bones and joints, segmentation
9 datasets, 125 test cases. A method is ranked here when it has a result on every case of every one of them.
Read before comparing
- 6 datasets of this kind are shown below and not ranked on the official board: their licence does not allow a public leaderboard. The research board (Research, above the ranking) ranks them too.
Ranking OfficialResearch
Provisional: no method has run on every dataset here yet. The methods that cover the most datasets come first, then the lower mean place on those.
| # | Method | Mean rank | Datasets | VerSe, vertebrae | SPIDER, lumbar vertebrae, discs and canal | Spine-generic, spinal cord | PENGWIN CT | PIANO hand MRI, bones | Spine-Mets-CT-SEG | Spinal-Multiple-Myeloma-SEG, vertebrae and lytic lesions | TotalSegmentator hip_implant, CT | CSI 2014 vertebrae |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | KonfAI segmentation app · TotalSegmentator (total), KonfAI appGPUapp | 1.50 | 4 of 9 | 1 | n/a | n/a | 2 | n/a | 2 | 1 | n/a | n/a |
| 2 | KonfAI segmentation app · TotalSegmentator (total), the authors' packageGPUapp | 1.33 | 3 of 9 | n/a | n/a | n/a | 1 | n/a | 1 | 2 | n/a | n/a |
| 3 | CT-FM whole-body segmentationGPUapp | 3.00 | 3 of 9 | 2 | n/a | n/a | 3 | n/a | 3 | n/a | ||
| 4 | MONAI wholeBody CTGPUapp | 3.33 | 3 of 9 | 3 | n/a | n/a | 5 | n/a | 3 | 10/10 | n/a | |
| 5 | KonfAI segmentation app · TotalSegmentator (total_mr), the authors' packageGPUapp | 1.33 | 1 of 9 | n/a | n/a | 1 | n/a | n/a | n/a | n/a | n/a | n/a |
| 6 | KonfAI segmentation app · TotalSegmentator (total_mr), KonfAI appGPUapp | 1.67 | 1 of 9 | n/a | n/a | 2 | n/a | n/a | n/a | n/a | n/a | n/a |
| 7 | KonfAI segmentation app · IMPACTSeg body, KonfAI appGPUapp | 3.00 | 1 of 9 | n/a | n/a | 3 | n/a | n/a | n/a | n/a | n/a | n/a |
| 8 | KonfAI segmentation app · MRSegmentator, KonfAI appGPUapp | 4.00 | 1 of 9 | n/a | n/a | n/a | 4 | n/a | n/a | n/a | n/a | n/a |
1 place in that table, 1 is best2/10 cases done, not ranked yetn/a does not apply not run some cases failed
Under each dataset, the method's place in that dataset's table: 1 is best, the darker the better. The mean rank averages its places over the datasets.
The scores, dataset by dataset
Spine-generic, spinal cord
24 cases · ordered on DicePENGWIN CT
10 cases · ordered on DiceSpine-Mets-CT-SEG
10 cases · ordered on Dice| # | Method | Dice |
|---|---|---|
| 1 | KonfAI segmentation app · TotalSegmentator (total), the authors' package | 0.858 |
| 2 | KonfAI segmentation app · TotalSegmentator (total), KonfAI app | 0.844 |
| 3 | MONAI wholeBody CT | 0.715 |
Spinal-Multiple-Myeloma-SEG, vertebrae and lytic lesions
10 cases · ordered on Dice| # | Method | Dice |
|---|---|---|
| 1 | KonfAI segmentation app · TotalSegmentator (total), KonfAI app | 0.890 |
| 2 | KonfAI segmentation app · TotalSegmentator (total), the authors' package | 0.822 |
| 3 | CT-FM whole-body segmentation | 0.355 |
OAIZIB-CM, knee bones and cartilage
25 cases · ordered on Dice research only9 datasets without a ranked method yet
SPIDER, lumbar vertebrae, discs and canal, PIANO hand MRI, bones, TotalSegmentator hip_implant, CT, CSI 2014 vertebrae, CTSpine1K, PENGWIN 2026, femur, whole-spine T2 MR, MyoSegmenTUM thigh muscles, VSDFullBodyBoneReconstruction.