fidoptSynthSR
SynthSR 1.0, a U-Net trained on scans synthesised from brain label maps to turn a brain MR of any contrast, orientation and resolution into a 1 mm MPRAGE-like T1, run as its authors' predict_command_line.py runs it; brought back onto the input's grid and scaled onto the input's intensities.
SynthesisCPUversion SynthSR 9e63935, models/SynthSR_v10_210712.h5 of the repository (sha256 2fd59e96)brain · MR, 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-synthesis:SynthSR -i image.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 |
|---|---|---|---|
| Motion-corrupted to still brain MR, corpus-aligned | 1 | of 1 | 1 of 1 |
| MR to MR, another contrast, field strength or scanner, synthesis | not ranked yet | 1 of 5 |
Results
| Dataset | # | Read by | Score | Failed | Time s |
|---|---|---|---|---|---|
| Paired 3T-7T brain MRI (UNC), 3T T1w to 7T T1w | 1 | MAE | 465.9 | 0 | |
| MR-ART (OpenNeuro ds004173), motion-corrupted T1w to still T1w | 1 | MAE | 108.8 | 0 |
- Reference
- Iglesias et al., Science Advances 2023