Public

CT + Fluorescence (FLIT) — Public Tier

(3 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
optical_property_assignment_error -6.0 – 12.0 3.0 -
autofluorescence -10.0 – 20.0 5.0 -
registration_(ct_to_optical) -0.6 – 1.2 0.3 mm

InverseNet Baseline Scores

Method: CPU_baseline — Mismatch parameter: nominal

Scenario I (Ideal)

7.72 dB

SSIM 0.3738

Scenario II (Mismatch)

7.66 dB

SSIM 0.2292

Scenario III (Oracle)

16.33 dB

SSIM 0.4587

Per-scene breakdown (4 scenes)
Scene PSNR I SSIM I PSNR II SSIM II PSNR III SSIM III
scene_00 7.57 0.3615 7.52 0.2249 16.28 0.4660
scene_01 7.70 0.3833 7.81 0.2328 16.28 0.4522
scene_02 7.97 0.3846 7.55 0.2285 16.43 0.4500
scene_03 7.63 0.3655 7.75 0.2308 16.33 0.4667

Public Tier Leaderboard

# Method Score PSNR SSIM Consistency Trust Source
1 DiffusionXRF + gradient 0.867 38.4 0.983 0.95 ✓ Certified Song et al., ICLR 2021 (XRF adapt.)
2 SwinXRF + gradient 0.841 36.25 0.975 0.94 ✓ Certified Liu et al., ICCV 2021 (XRF adapt.)
3 PhysXRF-Net + gradient 0.828 35.68 0.972 0.91 ✓ Certified Raissi et al., J. Comput. Phys. 2019 (XRF)
4 PnP-XRF + gradient 0.817 34.39 0.964 0.94 ✓ Certified Chan et al., IEEE TIP 2016 (XRF adapt.)
5 U-Net-XRF + gradient 0.802 33.47 0.957 0.92 ✓ Certified Ronneberger et al., MICCAI 2015 (XRF adapt.)
6 DnCNN-XRF + gradient 0.768 30.74 0.927 0.95 ✓ Certified Zhang et al., IEEE TIP 2017 (XRF adapt.)
7 TV-XRFCT + gradient 0.724 28.32 0.887 0.93 ✓ Certified Larsson et al., Phys. Med. Biol. 2020
8 MLEM-XRF + gradient 0.654 24.78 0.795 0.94 ✓ Certified Jaszczak et al., IEEE TNS 1981 (XRF adapt.)
9 FBP-XRF + gradient 0.531 20.47 0.621 0.89 ✓ Certified Boisseau & Grodzins, Hyperfine Int. 1987

Visible Data Fields

y H_ideal spec_ranges x_true true_spec

Dataset

Format: HDF5
Scenes: 3

Scoring Formula

0.4 × PSNR_norm + 0.4 × SSIM + 0.2 × (1 − ‖y − Ĥx̂‖/‖y‖)

PSNR: 40% SSIM: 40% Consistency: 20%
Back to CT + Fluorescence (FLIT)