Deep learning system for distinguishing optic neuritis from non-arteritic anterior ischemic optic neuropathy at acute phase based on fundus photographs.
Source check: Source checked. Not independent scientific confirmation.
Finding: EfficientNet-B0 deep-learning system (ONION) differentiating acute optic neuritis from NAION on fundus photographs, n=871 eyes, with a held-out test set (AUC 0.902) and a retinal-expert comparison. AI role: ONION EfficientNet-B0 deep-learning image classifier. The article appeared in Frontiers In Medicine.
Technology: ONION EfficientNet-B0 deep-learning image classifier
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- ONION EfficientNet-B0 deep-learning image classifier
- Test and result
- EfficientNet-B0 deep-learning system (ONION) differentiating acute optic neuritis from NAION on fundus photographs, n=871 eyes, with a held-out test set (AUC 0.902) and a retinal-expert comparison.
- Limitation / still unknown
- The result is limited to the described dataset, cohort, experimental system, or validation design; generalization beyond that scope and downstream real-world benefit are not established. Author affiliation was not stated in the reviewed abstract or metadata.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://www.frontiersin.org/journals/medicine/articles/10.3389/fmed.2023.1188542/full · https://pubmed.ncbi.nlm.nih.gov/37457581/
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: 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.