Synthetic Contrast-Free Late Gadolinium Enhancement (LGE) via Diffusion-Based Framework in Acute MI for Image Quality and Quantitative Scar Analysis
Authors' conclusion
SNE demonstrated strong agreement with LGE in quantitative assessment of acute myocardial infarction scar, with comparable or improved image quality.
Study context
- Population
- Patients with acute MI, 3 centres, January 2014 to July 2024
- Participants
- 331 patients
- Exposure
- Synthetic native enhancement vs standard LGE
- Outcome
- Image quality (Likert score)
Methodological detailsdevelopment and validation of a diffusion model, 3 centres, internal and external cohorts
- Development and validation of a diffusion model
- 3 centres
- Internal and external cohorts
Main finding
As reported in the abstract
| Group | Internal | External |
|---|---|---|
| Synthetic native enhancement (SNE) | 4.250 [4.000-4.750] | 4.250 [4.000-4.750] |
| LGE | 4.000 [3.750-4.500] | 4.000 [3.500-4.250] |
Internal
Synthetic native enhancement (SNE)4.250 [4.000-4.750]
LGE4.000 [3.750-4.500]
External
Synthetic native enhancement (SNE)4.250 [4.000-4.750]
LGE4.000 [3.500-4.250]
- SNE vs LGE: P < 0.05 — significantly higher quality with SNE
Observational data: associations, not effects.
Further findings
| Outcome | SNE | LGE | P value |
|---|---|---|---|
| Contrast ratio (blood pool vs myocardium)Improved contrast ratios with SNE | P < 0.05 | ||
| Internal | 9.010 [6.938-12.761] | 8.767 [6.361-11.745] | |
| External | 16.871 [12.546-24.237] | 13.472 [9.380-19.599] |
Agreement with LGE for scar size
- Internal R
- 0.839
- External R
- 0.816
- P
- P < 0.001
- Bias, internal
- 2.490%
- Bias, external
- 2.222%
Agreement with LGE for transmurality
- Internal R
- 0.792
- External R
- 0.758
- P
- P < 0.001
- Bias, internal
- 2.984%
- Bias, external
- 2.225%
Original publication
Synthetic Contrast-Free LGE via Diffusion-Based Framework in Acute MI for Image Quality and Quantitative Scar Analysis. Circ Cardiovasc Imaging. Published 29 December 2025. doi:10. 1161/ circimaging. 125. 018967
Composed by AI from the published abstract and checked against it. How Briefs are made →