Dev

Intravascular Ultrasound (IVUS) — Dev Tier

(3 scenes)

Blind evaluation tier — no ground truth available.

Measurements (y), ideal forward operator (H), and spec ranges only.

Apply your pipeline from the Public tier. Use consistency as self-check.

Reconstructed signals and corrected spec. Scored server-side.

🔒

True spec hidden — estimate parameters from spec ranges below.

Parameter	Spec Range	Unit
catheter_rotation_non_uniformity	-2.4 – 3.6	-
ring_down_artifact	-4.8 – 7.2	-
sound_speed_in_plaque	1501.6 – 1597.6	m/s

#	Method	Score	PSNR	SSIM	Consistency	Trust	Source
1	BeamFormer + gradient	0.734	29.36	0.907	0.89	✓ Certified	Li et al., ICCV 2024
2	UltrasoundFormer + gradient	0.730	30.18	0.92	0.8	✓ Certified	Park et al., CVPR 2024
3	ScoreUS + gradient	0.727	29.63	0.911	0.83	✓ Certified	Johnson et al., ECCV 2025
4	DiffUS + gradient	0.725	29.29	0.905	0.85	✓ Certified	Chen et al., NeurIPS 2024
5	AttentionBeam + gradient	0.709	28.27	0.886	0.86	✓ Certified	Xu et al., ECCV 2024
6	BeamDATA + gradient	0.709	28.47	0.89	0.84	✓ Certified	Smith et al., ICCV 2024
7	Phase-ADMM-Net + gradient	0.680	26.45	0.844	0.89	✓ Certified	Hou et al., IEEE TMI 2022
8	PnP-TV + gradient	0.651	25.19	0.808	0.88	✓ Certified	TV regularization for ultrasound
9	DAS-CF + gradient	0.610	23.94	0.766	0.82	✓ Certified	Capon filter, IEEE 1969
10	PnP-ADMM + gradient	0.602	23.78	0.761	0.8	✓ Certified	Goudarzi et al., 2020
11	MU-Net + gradient	0.574	22.82	0.724	0.78	✓ Certified	Hyun et al., IEEE TUFFC 2022
12	PW-DAS + gradient	0.568	21.77	0.68	0.89	✓ Certified	Plane wave synthesis baseline
13	ABLE + gradient	0.547	21.02	0.647	0.89	✓ Certified	Luijten et al., IEEE TMI 2020
14	DAS + gradient	0.534	21.2	0.655	0.8	✓ Certified	Analytical baseline

y H_ideal spec_ranges

Format: HDF5

Scenes: 3

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

PSNR: 40% SSIM: 40% Consistency: 20%