SPECT/CT

Single Photon Emission CT / Computed Tomography

Join the Competition Contribute to Benchmark

Standard reconstruction benchmark — forward model perfectly known, no calibration needed. Score = 0.5 × clip((PSNR−15)/30, 0, 1) + 0.5 × SSIM

# Method Score PSNR (dB) SSIM Source
🥇 DL-SPECT 0.851 36.72 0.977 ✓ Certified Ramon et al., IEEE TMI 2020
🥈 MAP-OSEM 0.787 33.49 0.957 ✓ Certified Nuyts et al., 2002
🥉 AC-OSEM 0.721 30.53 0.925 ✓ Certified CT-based attenuation correction
4 OSEM 0.508 24.8 0.690 ✓ Certified Hudson & Larkin, IEEE TMI 1994

Dataset: PWM Benchmark (4 algorithms)

Blind Reconstruction Challenge — forward model has unknown mismatch, must calibrate from data. Score = 0.4 × PSNR_norm + 0.4 × SSIM + 0.2 × (1 − ‖y − Ĥx̂‖/‖y‖)

# Method Overall Score Public
PSNR / SSIM
 Dev
PSNR / SSIM
 Hidden
PSNR / SSIM
 Trust Source
🥇 DL-SPECT + gradient 0.730
0.807
34.38 dB / 0.964
0.724
28.75 dB / 0.896
0.660
26.74 dB / 0.852
✓ Certified Ramon et al., IEEE TMI 2020
🥈 MAP-OSEM + gradient 0.717
0.784
32.07 dB / 0.943
0.699
28.57 dB / 0.892
0.667
27.19 dB / 0.863
✓ Certified Nuyts et al., 2002
🥉 AC-OSEM + gradient 0.695
0.710
27.88 dB / 0.878
0.690
27.77 dB / 0.876
0.686
27.46 dB / 0.869
✓ Certified CT-based attenuation correction
4 OSEM + gradient 0.532
0.576
21.91 dB / 0.686
0.513
20.06 dB / 0.602
0.508
20.3 dB / 0.613
✓ Certified Hudson & Larkin, IEEE TMI 1994

Complete score requires all 3 tiers (Public + Dev + Hidden).

Join the competition →
Scoring: 0.4 × PSNR_norm + 0.4 × SSIM + 0.2 × (1 − ‖y − Ĥx̂‖/‖y‖) PSNR 40% · SSIM 40% · Consistency 20%
Public 3 scenes

Full-access development tier with all data visible.

What you get & how to use

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.

Public Leaderboard
# Method Score PSNR SSIM
1 DL-SPECT + gradient 0.807 34.38 0.964
2 MAP-OSEM + gradient 0.784 32.07 0.943
3 AC-OSEM + gradient 0.710 27.88 0.878
4 OSEM + gradient 0.576 21.91 0.686
Spec Ranges (4 parameters)
Parameter Min Max Unit
ct_registration_shift -5.0 10.0 pixels
hu_to_mu_scale -12.0 24.0 %
scatter_fraction -0.35 0.7
collimator_blur -1.0 9.5 pixels
View Details →
Dev 3 scenes

Blind evaluation tier — no ground truth available.

What you get & how to use

What you get: Measurements (y), ideal forward operator (H), and spec ranges only.

How to use: Apply your pipeline from the Public tier. Use consistency as self-check.

What to submit: Reconstructed signals and corrected spec. Scored server-side.

Dev Leaderboard
# Method Score PSNR SSIM
1 DL-SPECT + gradient 0.724 28.75 0.896
2 MAP-OSEM + gradient 0.699 28.57 0.892
3 AC-OSEM + gradient 0.690 27.77 0.876
4 OSEM + gradient 0.513 20.06 0.602
Spec Ranges (4 parameters)
Parameter Min Max Unit
ct_registration_shift -6.0 9.0 pixels
hu_to_mu_scale -14.4 21.6 %
scatter_fraction -0.42 0.63
collimator_blur -1.7 8.8 pixels
Submit Reconstruction View Details →
Hidden 3 scenes

Fully blind server-side evaluation — no data download.

What you get & how to use

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.

Hidden Leaderboard
# Method Score PSNR SSIM
1 AC-OSEM + gradient 0.686 27.46 0.869
2 MAP-OSEM + gradient 0.667 27.19 0.863
3 DL-SPECT + gradient 0.660 26.74 0.852
4 OSEM + gradient 0.508 20.3 0.613
Spec Ranges (4 parameters)
Parameter Min Max Unit
ct_registration_shift -3.5 11.5 pixels
hu_to_mu_scale -8.4 27.6 %
scatter_fraction -0.245 0.805
collimator_blur 0.05 10.55 pixels
Submit Algorithm View Details →

Blind Reconstruction Challenge

Challenge

Given measurements with unknown mismatch and spec ranges (not exact params), reconstruct the original signal. A method must be evaluated on all three tiers for a complete score. Scored on a composite metric: 0.4 × PSNR_norm + 0.4 × SSIM + 0.2 × (1 − ‖y − Ĥx̂‖/‖y‖).

Input

Measurements y, ideal forward model H, spec ranges

Output

Reconstructed signal x̂

Spec DAG — Forward Model Pipeline

R(θ) → D(μ_ct) → H(coll) → D(g, η)

R Radon Transform (θ)
D CT Attenuation Map (μ_ct)
H Collimator PSF (coll)
D Detector + Noise (g, η)

Mismatch Parameters

Symbol Parameter Description Nominal Perturbed
Δs ct_registration_shift CT-SPECT registration error (pixels) 0 5.0
Δμ hu_to_mu_scale HU-to-μ calibration error (%) 0 12.0
f_s scatter_fraction Scatter fraction 0 0.35
σ_c collimator_blur Collimator blur FWHM (pixels) 2.5 6.0

Credits System

40%
Platform Profit Pool
Revenue allocated to benchmark rewards
30%
Winner Share
Top algorithm receives from pool
$100
Min Withdrawal
Minimum payout threshold
Spec Primitives Reference (11 primitives)
P Propagation

Free-space or medium propagation kernel (Fresnel, Rayleigh-Sommerfeld).

M Mask / Modulation

Spatial or spatio-temporal amplitude modulation (coded aperture, SLM pattern).

Π Projection

Geometric projection operator (Radon transform, fan-beam, cone-beam).

F Fourier Sampling

Sampling in the Fourier / k-space domain (MRI, ptychography).

C Convolution

Shift-invariant convolution with a point-spread function (PSF).

Σ Summation / Integration

Summation along a physical dimension (spectral, temporal, angular).

D Detector

Sensor readout with gain g and noise model η (Gaussian, Poisson, mixed).

S Structured Illumination

Patterned illumination (block, Hadamard, random) applied to the scene.

W Wavelength Dispersion

Spectral dispersion element (prism, grating) with shift α and aperture a.

R Rotation / Motion

Sample or gantry rotation (CT, electron tomography).

Λ Wavelength Selection

Spectral filter or monochromator selecting a wavelength band.