Deep Learning Model to Detect Diabetic Retinopathy in 45° Images Using Ground Truth from Ultra-Widefield Imaging.
Source check: Source checked. Not independent scientific confirmation.
Finding: Deep learning is trained to detect diabetic-retinopathy lesions in masked 45° images using labels from ultra-widefield imaging, with comparison across three image/label conditions in 2,610 participants and 5,180 retinal images.
Technology: Multiple image conditions and reference labels test lesion detection; regional population and cross-sectional data bound generalization.
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- Multiple image conditions and reference labels test lesion detection; regional population and cross-sectional data bound generalization.
- Test and result
- Deep learning is trained to detect diabetic-retinopathy lesions in masked 45° images using labels from ultra-widefield imaging, with comparison across three image/label conditions in 2,610 participants and 5,180 retinal images. Multiple image conditions and reference labels test lesion detection; regional population and cross-sectional data bound generalization.
- Limitation / still unknown
- nopathy lesions in masked 45° images using labels from ultra-widefield imaging, with comparison across three image/label conditions in 2,610 participants and 5,180 retinal images.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://europepmc.org/article/MED/42088785 · https://pubmed.ncbi.nlm.nih.gov/42088785/
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.
Review date: 22 Nov 2026. Review scope: Primary result-bearing material for the stated method, result and evaluation, with bibliographic version information..
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 2/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.