Public
Electrical Impedance Tomography (EIT) — Public Tier
(5 scenes)Full-access development tier with all data visible.
What you get
Measurements (y), ideal forward operator (H), spec ranges, ground truth (x_true), and true mismatch spec.
How to use
Load HDF5 → compare reconstruction vs x_true → check consistency → iterate.
What to submit
Reconstructed signals (x_hat) and corrected spec as HDF5.
Parameter Specifications
✓
True spec visible — use these exact values for Scenario III oracle reconstruction.
| Parameter | Spec Range | True Value | Unit |
|---|---|---|---|
| contact_impedance | 80.0 – 140.0 | 110.0 | ohm |
| electrode_position_error | -0.4 – 0.8 | 0.2 | mm |
| background_conductivity | 0.16 – 0.28 | 0.22 | S/m |
| current_amplitude_drift | 0.99 – 1.02 | 1.005 | - |
InverseNet Baseline Scores
Method: CPU_baseline — Mismatch parameter: nominal
Scenario I (Ideal)
7.84 dB
SSIM 0.3015
Scenario II (Mismatch)
7.79 dB
SSIM 0.1872
Scenario III (Oracle)
10.90 dB
SSIM 0.3562
Per-scene breakdown (4 scenes)
| Scene | PSNR I | SSIM I | PSNR II | SSIM II | PSNR III | SSIM III |
|---|---|---|---|---|---|---|
| scene_00 | 7.64 | 0.2894 | 7.60 | 0.1899 | 10.75 | 0.3635 |
| scene_01 | 7.65 | 0.3040 | 7.61 | 0.1843 | 10.73 | 0.3514 |
| scene_02 | 8.07 | 0.3073 | 8.04 | 0.1884 | 11.13 | 0.3560 |
| scene_03 | 8.02 | 0.3052 | 7.90 | 0.1863 | 10.99 | 0.3542 |
Public Tier Leaderboard
| # | Method | Score | PSNR | SSIM | Consistency | Trust | Source |
|---|---|---|---|---|---|---|---|
| 1 | D-bar CNN + gradient | 0.706 | 27.47 | 0.869 | 0.92 | ✓ Certified | Hamilton & Hauptmann, IEEE TMI 2018 |
| 2 | EIT-Former + gradient | 0.705 | 27.9 | 0.879 | 0.87 | ✓ Certified | EIT reconstruction transformer, 2024 |
| 3 | TV-ADMM + gradient | 0.611 | 23.02 | 0.732 | 0.94 | ✓ Certified | Borsic et al., Physiol. Meas. 2010 |
| 4 | Gauss-Newton + gradient | 0.474 | 18.53 | 0.526 | 0.89 | ✓ Certified | Cheney et al., SIAM Rev. 1999 |
Visible Data Fields
y
H_ideal
spec_ranges
x_true
true_spec
Dataset
Format: HDF5
Scenes: 5
Scoring Formula
0.4 × PSNR_norm + 0.4 × SSIM + 0.2 × (1 − ‖y − Ĥx̂‖/‖y‖)
PSNR: 40%
SSIM: 40%
Consistency: 20%