Public

Digital Breast Tomosynthesis (DBT) — Public Tier

(3 scenes)

Full-access development tier with all data visible.

Measurements (y), ideal forward operator (H), spec ranges, ground truth (x_true), and true mismatch spec.

Load HDF5 → compare reconstruction vs x_true → check consistency → iterate.

Reconstructed signals (x_hat) and corrected spec as HDF5.

✓

True spec visible — use these exact values for Scenario III oracle reconstruction.

Parameter	Spec Range	True Value	Unit
angular_range_error	-0.4 – 0.8	0.2	degtotal
detector_motion_blur	-0.1 – 0.2	0.05	px
scatter_fraction	0.24 – 0.42	0.33	-

Method: CPU_baseline — Mismatch parameter: nominal

14.88 dB

SSIM 0.2885

11.68 dB

SSIM 0.0479

14.89 dB

SSIM 0.1290

Per-scene breakdown (4 scenes)

Scene	PSNR I	SSIM I	PSNR II	SSIM II	PSNR III	SSIM III
scene_00	14.80	0.2898	11.69	0.0458	14.77	0.1268
scene_01	15.05	0.2857	11.70	0.0477	14.91	0.1282
scene_02	14.99	0.2846	11.68	0.0506	14.96	0.1312
scene_03	14.69	0.2938	11.67	0.0475	14.91	0.1299

#	Method	Score	PSNR	SSIM	Consistency	Trust	Source
1	DiffusionDBT + gradient	0.860	38.09	0.982	0.93	✓ Certified	Gao et al., MICCAI 2024
2	PhysDBT + gradient	0.844	36.67	0.977	0.93	✓ Certified	Nett et al., IEEE TMI 2024
3	SwinDBT + gradient	0.833	35.81	0.972	0.93	✓ Certified	Li et al., Med. Phys. 2023
4	TransDBT + gradient	0.792	32.9	0.952	0.91	✓ Certified	Wang et al., MICCAI 2022
5	DuDoRNet-DBT + gradient	0.760	30.82	0.929	0.9	✓ Certified	Zhou et al., CVPR 2020
6	DnCNN-DBT + gradient	0.710	28.22	0.885	0.87	✓ Certified	Chen et al., IEEE TMI 2018
7	SART-DBT + gradient	0.655	25.46	0.816	0.87	✓ Certified	Andersen & Kak, Ultrason. Imaging 1984
8	TV-DBT + gradient	0.604	22.98	0.73	0.91	✓ Certified	Sidky et al., Med. Phys. 2014
9	FBP-DBT + gradient	0.570	21.48	0.667	0.94	✓ Certified	Sechopoulos, Med. Phys. 2013

y H_ideal spec_ranges x_true true_spec

Format: HDF5

Scenes: 3

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

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