fidoptDemons
ITK's fast symmetric forces Demons as SimpleITK's Demons notebook runs it: 20 iterations, field smoothing 2, pyramid 4, 2, 1; on MR the moving histogram is first matched to the fixed one, as SimpleITK's Demons examples do.
RegistrationCPUversion SimpleITK 2.5.6, notebook 190ad08, examples 9b49b9cCT, MRApache-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-registration:Demons -i fixed.nii.gz -i moving.nii.gz -o out
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 |
|---|---|---|---|
| Abdomen CT, same patient | 1 | of 1 | 3 of 3 |
| Abdomen CT, inter-patient | 1 | of 1 | 3 of 3 |
| Thorax and abdomen MR, breathing, same patient | 1 | of 2 | 1 of 1 |
| Hand MR, two poses, same patient | 1 | of 2 | 1 of 1 |
| Tumours under treatment, same patient | 1 | of 2 | 1 of 1 |
| Ex vivo medial temporal lobe MRI, between donors | 1 | of 1 | 1 of 1 |
| Head and neck MR during treatment, tumour centres | 1 | of 1 | 1 of 1 |
| Brain MR, same patient | 2 | of 2 | 1 of 1 |
| Abdomen MR, inter-patient | 2 | of 2 | 2 of 2 |
| Abdomen CT, same patient, files without their voxel size | 2 | of 2 | 2 of 2 |
| Mouse brain MR, between animals | 2 | of 2 | 1 of 1 |
| Repeat chest CT, same patient, tumour truth | 3 | of 5 | 1 of 1 |
| Pediatric T1 MRI with automatic regional labels | 3 | of 4 | 1 of 1 |
| Repeat scans, same patient | 5 | of 5 | 1 of 1 |
| Brain MR, inter-subject | not ranked yet | 3 of 4 | |
| Chest and body CT, inter-patient | not ranked yet | 1 of 2 | |
| Head, neck and spine, inter-patient | not ranked yet | 3 of 4 | |
| Same patient, truth made by a program | not ranked yet | 5 of 8 |
Results
| Dataset | # | Read by | Score | Change | SDlogJ | Failed | Time s |
|---|---|---|---|---|---|---|---|
| ACDC | 3 | Dice | 0.731 | +0.173 | 0.035 | 0 | 1 |
| Pediatric T1 MRI with and without previous ADHD diagnosis | 3 | Dice | 0.485 | +0.073 | 0.054 | 0 | 9 |
| AFIDs | 1 | Dice | 0.477 | +0.107 | 0.072 | 0 | 15 |
| AMOS CT/CT | 1 | Dice | 0.293 | +0.113 | 0.964 | 0 | 32 |
| AMOS MR/MR | 2 | Dice | 0.358 | +0.093 | 0.112 | 0 | 14 |
| Abdominal-DIR-QA | 1 | Dice | 0.712 | +0.281 | 0.088 | 0 | 44 |
| Baby Open Brains (BOBs) | 2 | Dice | 0.719 | +0.123 | 0.051 | 0 | 6 |
| BraTS-Reg | 1 | TRE mm | 4.79 | −1.54 | 0.026 | 0 | 7 |
| Breast-MRI-NACT-Pilot | 2 | Dice | 0.642 | +0.133 | 0.098 | 0 | 5 |
| Colorectal-Liver-Metastases, liver and veins | 1 | Dice | 0.310 | +0.094 | 0.235 | 0 | 18 |
| CC-Tumor-Heterogeneity | 1 | TRE mm | 7.17 | −1.98 | 0.138 | 0 | 4 |
| Ex vivo medial temporal lobe MRI (Penn) | 1 | Dice | 0.393 | +0.067 | 0.061 | 0 | 46 |
| Weekly ADC on the MR-Linac, head and neck | 1 | TRE mm | 6.57 | +2.29 | 0.053 | 0 | 3 |
| HNTS-MRG 2024 | 2 | TRE mm | 3.93 | −0.28 | 0.076 | 0 | 19 |
| HQColon | 1 | Dice | 0.695 | +0.178 | 0.074 | 0 | 149 |
| PIANO hand MRI | 1 | TRE mm | 33.53 | −1.65 | 0.106 | 0 | 17 |
| Human Inner Ear Anatomy | 1 | Dice | 0.411 | +0.015 | 0.058 | 0 | 87 |
| OAIZIB-CM | 2 | Dice | 0.511 | +0.106 | 0.090 | 0 | 19 |
| LCTSC | 2 | Dice | 0.691 | +0.239 | 0.111 | 0 | 32 |
| LUMIR (Learn2Reg 2024), training images | 2 | Dice | 0.594 | +0.133 | 0.026 | 0 | 6 |
| LUNA25 | 3 | TRE mm | 2.83 | −4.25 | 0.077 | 0 | 37 |
| Liver-DIR-QA | 2 | Dice | 0.658 | +0.219 | 0.100 | 0 | 35 |
| CT follow-up of liver metastases | 2 | Dice | 0.846 | +0.112 | 0.066 | 0 | 10 |
| PLC-CECT | 2 | Dice | 0.948 | +0.042 | 0.033 | 0 | 32 |
| Lung-DIR-QA | 2 | TRE mm | 9.79 | −3.20 | 0.061 | 0 | 64 |
| M-CRIB 2.0 and M-CRIB-WM | 2 | Dice | 0.473 | +0.114 | 0.046 | 0 | 13 |
| MSLesSeg | 1 | Dice | 0.727 | −0.073 | 0.034 | 0 | 12 |
| Mindboggle-101 | 1 | Dice | 0.407 | +0.109 | 0.026 | 0 | 9 |
| MMB-MRI | 2 | Dice | 0.626 | −0.098 | 0.023 | 0 | 2 |
| PDDCA | 2 | Dice | 0.344 | +0.143 | 0.120 | 0 | 31 |
| PROMISE12 | 5 | Dice | 0.627 | +0.011 | 0.542 | 0 | 5 |
| PSMA-PET-CT-Lesions follow-up (Learn2Reg 2026 PSMAReg) | 4 | TRE mm | 5.50 | −2.08 | 0.082 | 0 | 59 |
| Pancreas-CT, 8 organs | 1 | Dice | 0.368 | +0.085 | 0.084 | 0 | 53 |
| Pediatric thoracic dynamic MRI | 1 | Dice | 0.898 | +0.054 | 0.030 | 0 | 2 |
| Pelvic landmarks CT/CT (LUMC) | 5 | Dice | 0.728 | +0.112 | 0.087 | 0 | 31 |
| QIN-PROSTATE-Repeatability | 5 | Dice | 0.519 | −0.125 | 1.180 | 0 | 7 |
| QUADRA_HC, whole-body CT test-retest | 5 | Dice | 0.811 | +0.259 | 0.052 | 0 | 45 |
| RIDER Lung CT | 3 | Dice | 0.781 | +0.045 | 0.054 | 0 | 52 |
| RibSeg v2 | 1 | Dice | 0.142 | +0.099 | 0.088 | 0 | 81 |
| Spine-generic multi-subject | 3 | Dice | 0.632 | +0.302 | 0.067 | 0 | 6 |
| Tongue musculature MRI | 2 | Dice | 0.553 | +0.055 | 0.021 | 0 | 10 |
| TotalSegmentator MRI | 3 | Dice | 0.271 | +0.087 | 0.109 | 0 | 6 |
| TrackRAD2025, two frames of a sagittal cine MR sequence | 1 | Dice | 0.773 | +0.238 | 0.051 | 0 | 0 |
| UCSD-BMETS-Longitudinal | 2 | Dice | 0.690 | −0.101 | 0.022 | 0 | 61 |
| UltraCortex | 4 | Dice | 0.555 | +0.058 | 0.051 | 0 | 36 |
- Reference
- Thirion, Medical Image Analysis 1998