Hidden

Brachytherapy Imaging — 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
source_position_error -0.28 – 0.92 mm
attenuation_coefficient 0.193 – 0.223 1/cm
detector_gain_drift 0.993 – 1.023 -
scatter_fraction 0.136 – 0.196 -

Hidden Tier Leaderboard

# Method Score PSNR SSIM Consistency Trust Source
1 DiffusionSeed + gradient 0.729 30.38 0.922 0.78 ✓ Certified Gao et al., Med. Phys. 2024
2 Learned Primal-Dual + gradient 0.707 29.18 0.903 0.77 ✓ Certified Adler & Oktem, IEEE TMI 2018
3 DuDoTrans + gradient 0.705 28.72 0.895 0.8 ✓ Certified Wang et al., IEEE TMI 2022
4 CTFormer + gradient 0.691 27.62 0.873 0.83 ✓ Certified Wang et al., MICCAI 2023
5 RED-CNN + gradient 0.671 26.21 0.838 0.87 ✓ Certified Chen et al., IEEE TMI 2017
6 Metal-AR-Net + gradient 0.660 25.59 0.82 0.88 ✓ Certified Zhang & Yu, IEEE TMI 2018
7 FBPConvNet + gradient 0.625 24.74 0.794 0.8 ✓ Certified Jin et al., IEEE TIP 2017
8 FDK + gradient 0.594 23.87 0.764 0.75 ✓ Certified Feldkamp et al., J. Opt. Soc. Am. A 1984
9 TV-ADMM + gradient 0.549 21.6 0.673 0.82 ✓ Certified Boyd et al., Found. Trends Mach. Learn. 2011

Dataset

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 Brachytherapy Imaging