Functional Near-Infrared Spectroscopy (fNIRS)

Functional Near-Infrared Spectroscopy (fNIRS)

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-DOT 0.829 35.62 0.971 ✓ Certified Yoo et al., IEEE TMI 2020
🥈 PnP-DOT 0.784 33.34 0.956 ✓ Certified Yoo et al., IEEE TMI 2020
🥉 MBLL 0.707 29.95 0.916 ✓ Certified Cope & Delpy, Med. Biol. Eng. Comput. 1988
4 Tikhonov-DOT 0.617 26.61 0.848 ✓ Certified Arridge, Inverse Probl. 1999

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-DOT + gradient 0.715
0.790
32.8 dB / 0.951
0.704
27.86 dB / 0.878
0.652
25.52 dB / 0.818
✓ Certified Yoo et al., IEEE TMI 2020
🥈 PnP-DOT + gradient 0.710
0.784
32.22 dB / 0.945
0.710
28.51 dB / 0.891
0.635
24.74 dB / 0.794
✓ Certified Yoo et al., IEEE TMI 2020
🥉 MBLL + gradient 0.690
0.728
28.43 dB / 0.890
0.675
27.28 dB / 0.865
0.666
26.13 dB / 0.836
✓ Certified Cope & Delpy, Med. Biol. Eng. Comput. 1988
4 Tikhonov-DOT + gradient 0.601
0.660
25.07 dB / 0.804
0.585
22.65 dB / 0.717
0.558
22.45 dB / 0.709
✓ Certified Arridge, Inverse Probl. 1999

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-DOT + gradient 0.790 32.8 0.951
2 PnP-DOT + gradient 0.784 32.22 0.945
3 MBLL + gradient 0.728 28.43 0.89
4 Tikhonov-DOT + gradient 0.660 25.07 0.804
Spec Ranges (4 parameters)
Parameter Min Max Unit
source_detector_coupling 0.9 1.2 -
scalp_brain_distance_variation -1.0 2.0 mm
motion_artifact_(head) -2.0 4.0 -
systemic_physiology_contamination -6.0 12.0 -
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 PnP-DOT + gradient 0.710 28.51 0.891
2 DL-DOT + gradient 0.704 27.86 0.878
3 MBLL + gradient 0.675 27.28 0.865
4 Tikhonov-DOT + gradient 0.585 22.65 0.717
Spec Ranges (4 parameters)
Parameter Min Max Unit
source_detector_coupling 0.88 1.18 -
scalp_brain_distance_variation -1.2 1.8 mm
motion_artifact_(head) -2.4 3.6 -
systemic_physiology_contamination -7.2 10.8 -
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 MBLL + gradient 0.666 26.13 0.836
2 DL-DOT + gradient 0.652 25.52 0.818
3 PnP-DOT + gradient 0.635 24.74 0.794
4 Tikhonov-DOT + gradient 0.558 22.45 0.709
Spec Ranges (4 parameters)
Parameter Min Max Unit
source_detector_coupling 0.93 1.23 -
scalp_brain_distance_variation -0.7 2.3 mm
motion_artifact_(head) -1.4 4.6 -
systemic_physiology_contamination -4.2 13.8 -
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

M → R → P → D

M Modulation
R Rotation
P Propagation
D Detector

Mismatch Parameters

Symbol Parameter Description Nominal Perturbed
s_c source_detector_coupling Source-detector coupling (-) 1.0 1.1
s_d scalp_brain_distance_variation Scalp-brain distance variation (mm) 0.0 1.0
m_a motion_artifact_(head) Motion artifact (head) (-) 0.0 2.0
s_p systemic_physiology_contamination Systemic physiology contamination (-) 0.0 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.