Dev

Contrast-Enhanced Ultrasound (CEUS) — 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
bubble_concentration	-1.2 – 1.8	relative
nonlinear_harmonic_extraction	-2.4 – 3.6	-
motion_between_frames	-1.2 – 1.8	mm

#	Method	Score	PSNR	SSIM	Consistency	Trust	Source
1	CEUSF-Transformer + gradient	0.761	31.34	0.935	0.87	✓ Certified	Huang et al., IEEE TMI 2023
2	DiffusionCEUS + gradient	0.745	31.01	0.931	0.81	✓ Certified	Chen et al., Nat. Methods 2024
3	SUPER-ULM + gradient	0.738	30.96	0.93	0.78	✓ Certified	Rigo et al., IEEE TUFFC 2023
4	PINN-CEUS + gradient	0.715	28.92	0.899	0.83	✓ Certified	Lowerison et al., Nat. Commun. 2022
5	DeepULM + gradient	0.715	28.72	0.895	0.85	✓ Certified	van Sloun et al., IEEE TUFFC 2021
6	AM-CEUS + gradient	0.629	24.49	0.785	0.85	✓ Certified	Mor-Avi et al., JACC 2002
7	ULM-Net + gradient	0.586	23.28	0.742	0.78	✓ Certified	Christensen-Jeffries et al., Nat. Biomed. Eng. 2020
8	Pulse-Inversion + gradient	0.535	20.73	0.633	0.87	✓ Certified	Simpson et al., Ultrasound Med. Biol. 1999
9	CNN-Bubble + gradient	0.474	18.75	0.537	0.86	✓ Certified	Youn et al., IEEE TUFFC 2020

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%