AI Science Tracker
EN

Toward automated severe pharyngitis detection with smartphone camera using deep learning networks

Department of Ophthalmology, Aerospace Medical Center, Republic of Korea Air Force, Cheongju, South Korea · 20 Aug 2020 · biology

Discovery

Toward automated severe pharyngitis detection with smartphone camera using deep learning networks

Source check: Source checked. Not independent scientific confirmation.

Finding: CycleGAN-generated images augmented a 339-image throat dataset for transfer-learned classifiers; ResNet50 achieved test ROC-AUC 0.988 and four-fold ROC-AUC 0.992 for severe pharyngitis detection. The small image set limits generalization, and clinical benefit was not tested.

Technology: CycleGAN generates training images for transfer-learned ResNet50, Inception-v3 and MobileNet-v2 throat-image classifiers.

Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.

AI contribution
CycleGAN generates training images for transfer-learned ResNet50, Inception-v3 and MobileNet-v2 throat-image classifiers.
Test and result
The stated cohort, comparison, and case-specific outcome were checked in the primary Results.
Limitation / still unknown
The applicable validation design and limits are stated in the case reason; no clinical benefit beyond the study is claimed.
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/PMC7440230/ · https://pubmed.ncbi.nlm.nih.gov/32871294/

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.

Open in the full catalog for filters, charts and related discoveries. Browse biology discoveries.