Hidden
DOT — Hidden Tier
(3 scenes)Fully blind server-side evaluation — no data download.
What you get
No data downloadable. Algorithm runs server-side on hidden measurements.
How to use
Package algorithm as Docker container / Python script. Submit via link.
What to submit
Containerized algorithm accepting y + H, outputting x_hat + corrected spec.
Parameter Specifications
🔒
True spec hidden — blind evaluation, only ranges available.
| Parameter | Spec Range | Unit |
|---|---|---|
| mu_a | -7.0 – 23.0 | % |
| mu_s | -5.6 – 18.4 | % |
| source_pos | -0.7 – 2.3 | mm |
Hidden Tier Leaderboard
| # | Method | Score | PSNR | SSIM | Consistency | Trust | Source |
|---|---|---|---|---|---|---|---|
| 1 | DiffusionDOT + gradient | 0.739 | 29.98 | 0.917 | 0.86 | ✓ Certified | Gao et al., NeurIPS 2024 |
| 2 | PhysDOT + gradient | 0.701 | 28.25 | 0.886 | 0.82 | ✓ Certified | Chen et al., Opt. Express 2024 |
| 3 | TransDOT + gradient | 0.697 | 27.8 | 0.877 | 0.84 | ✓ Certified | Li et al., IEEE TMI 2022 |
| 4 | SwinDOT + gradient | 0.666 | 26.85 | 0.854 | 0.78 | ✓ Certified | Wang et al., Biomed. Opt. Express 2023 |
| 5 | FEM-DOT + gradient | 0.595 | 23.25 | 0.741 | 0.83 | ✓ Certified | Schweiger et al., J. Biomed. Opt. 2005 |
| 6 | DOT-Net + gradient | 0.433 | 17.55 | 0.478 | 0.83 | ✓ Certified | Guo et al., Biomed. Opt. Express 2021 |
| 7 | Born-Approx + gradient | 0.396 | 16.38 | 0.42 | 0.82 | ✓ Certified | Arridge, Inverse Probl. 1999 |
| 8 | DnCNN-DOT + gradient | 0.390 | 15.97 | 0.4 | 0.85 | ✓ Certified | Yoo et al., Sci. Rep. 2019 |
| 9 | TV-DOT + gradient | 0.251 | 11.42 | 0.211 | 0.76 | ✓ Certified | Borsic et al., IEEE TMI 2010 |
Dataset
Scenes: 3
Scoring Formula
0.4 × PSNR_norm + 0.4 × SSIM + 0.2 × (1 − ‖y − Ĥx̂‖/‖y‖)
PSNR: 40%
SSIM: 40%
Consistency: 20%