Public

Elastography — 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
shear_speed -0.3 – 0.6 0.15 m/s
push_duration -10.0 – 20.0 5.0 μs
tissue_viscosity -15.0 – 30.0 7.5 %

InverseNet Baseline Scores

Method: CPU_baseline — Mismatch parameter: nominal

Scenario I (Ideal)

17.82 dB

SSIM 0.3159

Scenario II (Mismatch)

13.13 dB

SSIM 0.0462

Scenario III (Oracle)

16.47 dB

SSIM 0.1205

Per-scene breakdown (4 scenes)
Scene PSNR I SSIM I PSNR II SSIM II PSNR III SSIM III
scene_00 16.80 0.3126 12.50 0.0439 15.94 0.1205
scene_01 19.39 0.3156 13.98 0.0487 17.30 0.1144
scene_02 18.67 0.3153 13.50 0.0480 16.71 0.1239
scene_03 16.41 0.3201 12.53 0.0440 15.92 0.1231

Public Tier Leaderboard

# Method Score PSNR SSIM Consistency Trust Source
1 DiffElasto + gradient 0.857 38.02 0.982 0.92 ✓ Certified Gao et al., MICCAI 2024
2 PhysElasto + gradient 0.841 36.43 0.976 0.93 ✓ Certified Chen et al., Magn. Reson. Med. 2024
3 SwinElasto + gradient 0.828 35.51 0.971 0.92 ✓ Certified Wang et al., IEEE TMI 2023
4 TransElasto + gradient 0.782 32.22 0.945 0.91 ✓ Certified Li et al., Magn. Reson. Med. 2022
5 ElastoNet + gradient 0.745 29.99 0.917 0.89 ✓ Certified Tzschatzsch et al., IEEE TMI 2021
6 DnCNN-Elasto + gradient 0.693 26.97 0.857 0.9 ✓ Certified Guo et al., Med. Phys. 2019
7 AIDE + gradient 0.638 24.6 0.789 0.88 ✓ Certified Oliphant et al., Magn. Reson. Med. 2001
8 DI-Elasto + gradient 0.623 23.56 0.753 0.93 ✓ Certified Van Houten et al., Magn. Reson. Med. 2001
9 LFE-Elasto + gradient 0.516 20.02 0.6 0.88 ✓ Certified Manduca et al., Magn. Reson. Imaging 2001

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 Elastography