Deep learning for real-time detection of nasopharyngeal carcinoma during nasopharyngeal endoscopy.
Source check: Source checked. Not independent scientific confirmation.
Finding: A YOLO-based detector identified suspected nasopharyngeal carcinoma in endoscopy frames across three centers, including a held-out external center. The evaluation is retrospective and establishes frame-level diagnostic performance, not improved patient outcomes.
Technology: A YOLO-based object detector identifies suspected nasopharyngeal carcinoma regions in nasopharyngeal endoscopy frames.
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- The detector identified suspected NPC regions in endoscopy frames and was evaluated on data from an external center.
- Test and result
- The multicenter study reports frame-level detection performance, including external-center testing, for NPC lesions during endoscopy.
- Limitation / still unknown
- Retrospective evaluation of 2,429 frames from 690 patients across three centers, with internal and external testing; no outcome-impact evidence is established.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://europepmc.org/articles/PMC10502364
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 full-text Methods and Results in Europe PMC and publication record..
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 4/5 · 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.