Emmanuel Eric Pazo

← Publications

Validation of the Eyerobo FC Portable Fundus Camera for Diabetic Retinopathy Screening Using Public Datasets and Deep Learning

Emmanuel Eric Pazo, Xiangying Liu, Shoukuan Liu, Qinru Zhang, Mingxuan Zhang, Zhihui Zhang, Salissou Moutari, Muhammad Usama, Xinjun Ren

Ophthalmology and Therapy, 2026 · article · doi:10.1007/s40123-026-01353-w · cited by 3 · Open access (CC BY-NC)

Retina & vascular imagingAI & deep learning

Abstract

To validate the diagnostic performance of the Eyerobo FC, a new portable non-mydriatic fundus camera for diabetic retinopathy (DR) screening, against an established desktop fundus camera benchmark using a transfer-learning approach in which artificial intelligence (AI)-based detection algorithms trained on desktop images were applied to Eyerobo FC images. This prospective validation study employed a three-tier experimental design. Tier 1 involved training a deep learning model (EfficientNet-B4) on standard desktop camera images from EyePACS and APTOS 2019 datasets. Tier 2 established the reference standard by evaluating the trained model on the Messidor-2 dataset (N = 1748 eyes) captured with a Topcon TRC NW6 desktop camera (sensitivity 92.7%, 95% CI 91.2–94.2%; AUC 0.952, 95% CI 0.943–0.961). Tier 3 validated the same AI model (without retraining) on images from the Eyerobo FC in a prospective cohort (N = 104 eyes: 52 referable DR, 52 non-referable). The primary outcome was noninferiority of sensitivity and specificity (margin $$\Delta$$ = 10%) compared with the desktop benchmark. Statistical analysis included bootstrap resampling (1000 iterations) for confidence intervals and a one-sided Z-test for the difference of proportions to assess noninferiority. In a balanced cohort of 104 eyes (52 referable DR, 52 non-referable), the Eyerobo FC achieved sensitivity of 92.3% (95% CI 84.4–98.2%) and specificity of 94.2% (95% CI 87.0–100%), demonstrating noninferior performance compared with the desktop benchmark (sensitivity 92.7%, specificity 94.3%). The sensitivity difference of $$-0.4$$ percentage points and the specificity difference of $$-0.1$$ percentage points were both within the noninferiority margin. AUC was 0.977 (95% CI 0.945–0.997) versus 0.952 for the desktop benchmark. The AI model correctly classified 97 of 104 eyes (93.3% accuracy, 95% CI 88.5–98.1%), with 4 false negatives and 3 false positives. Noninferiority was statistically confirmed for both sensitivity and specificity (P < 0.05). Inter-grader agreement was excellent (Cohen’s kappa = 0.917). Nonmydriatic image gradability rate was 94.4%. Grad-CAM visualization confirmed appropriate model attention to hemorrhages, exudates, and microaneurysms rather than artifacts. The Eyerobo fundus camera demonstrates noninferior diagnostic performance (sensitivity 92.3%, specificity 94.2%, AUC 0.977) compared with desktop systems when evaluated with AI algorithms trained exclusively on desktop images. These findings support deploying portable AI-assisted screening in resource-constrained and point-of-care settings, with successful cross-domain transfer learning enabling algorithmic generalizability across imaging platforms.

Keywords: diabetic retinopathy screening; transfer learning; deep learning; EfficientNet-B4; non-inferiority; referable diabetic retinopathy; Messidor-2; EyePACS

Access

How to cite

Pazo, E. E., Liu, X., Liu, S., Zhang, Q., Zhang, M., Zhang, Z., Moutari, S., Usama, M., Ren, X. (2026). Validation of the Eyerobo FC Portable Fundus Camera for Diabetic Retinopathy Screening Using Public Datasets and Deep Learning. Ophthalmology and Therapy. https://doi.org/10.1007/s40123-026-01353-w

@article{pazo2026validation,
  title = {{Validation of the Eyerobo FC Portable Fundus Camera for Diabetic Retinopathy Screening Using Public Datasets and Deep Learning}},
  author = {Pazo, Emmanuel Eric and Liu, Xiangying and Liu, Shoukuan and Zhang, Qinru and Zhang, Mingxuan and Zhang, Zhihui and Moutari, Salissou and Usama, Muhammad and Ren, Xinjun},
  journal = {Ophthalmology and Therapy},
  year = {2026},
  doi = {10.1007/s40123-026-01353-w},
  url = {https://doi.org/10.1007/s40123-026-01353-w},
}

Related work