Simulation-trained deep learning detected mucus plugs on non-contrast CT
Source check: Source checked. Not independent scientific confirmation.
Finding: Using simulated training data without manually annotated training images, nnU-Net detected and segmented airway mucus plugs on non-contrast CT. Detection sensitivity was 0.837 (95% CI 0.818–0.854) on a test set of 98 plug-positive scans. The study does not establish prospective clinical benefit, multisite transportability or improved patient outcomes.
Technology: Simulation-trained nnU-Net
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- Simulation-generated annotations trained nnU-Net to detect and segment mucus plugs in CT scans.
- Test and result
- Using simulated training data without manually annotated training images, nnU-Net detected and segmented airway mucus plugs on non-contrast CT. Detection sensitivity was 0.837 (95% CI 0.818–0.854) on a test set of 98 plug-positive scans.
- Limitation / still unknown
- The study does not establish prospective clinical benefit, multisite transportability or improved patient outcomes.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://pmc.ncbi.nlm.nih.gov/articles/PMC12938545/
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review date: 22 Nov 2026. Review scope: Original full-text Methods and Results reviewed from the primary paper or preprint; first result-bearing version checked from the supplied source review; author affiliations checked against exact-DOI metadata where available..
No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.
Editorial assessment: Impact 2/5 · Validation 2/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.