EyeModelHub
Home Subspecialties Oculoplastics Model card
§Model Card

Cornea Exposure Rate AI System (AnigmaView)

Automated measurement of the Corneal Exposure Ratio (CER) from standardized photographs

Park J. · 2025 · Republic of Korea · doi:10.3390/jcm14051691
Open DOI
Measurement/Regression CNN External photo Internally validated
More attributes
Anatomy · Periorbital soft tissueConditions · PtosisConditions · blepharoptosisSingle-centern = 50 patients · 100 eyes images
§01Overview

Brief overview

This study validated an AI-driven CER measurement tool for assessing ptosis surgery outcomes, showing excellent agreement with manual measurements and perfect repeatability. Generalizability is limited by the single-center, ethnically homogenous cohort and reliance on proprietary software.

§02Performance
Headline performance

AI vs manual ImageJ: ICC 0.98–0.99 (excellent).

Full metrics — as reported
AI vs manual ImageJ: ICC 0.98–0.99 (excellent).
Repeatability ICC = 1.00.
Pre-to-post CER changes matched manual results (≈20–28% improvement depending on severity subgroup).
Calibration · Uncertainty
Not reported.
Bias · Fairness
Not reported.
§03Data & Validation
Study designProspective cohort
Center typeSingle-center
Patients50
Images / eyes100 eyes
SplitNot reported
Reporting frameworks None stated
Age range>19
Sex (% female)Not reported
Race / ethnicity reportedN
Subgroup performanceN
§04Deployment
Deployment maturity
  1. Concept
  2. Prototype
  3. Internal val.
  4. External val.
  5. Regulator
  6. Clinical
Regulatory status
None No FDA / Health Canada / CE clearance.
Artifacts & license
Code repository none
Pretrained weights none
Live demo
License Proprietary
§05Quality Review · APPRAISE-AI
Total score
50 /100 Moderate
ClinicalDataMethodRobust.Report.Repro.
Sub-domain scores
Clinical relevance 4/4 100%
Data quality 15/24 63%
Methodological conduct 7/20 35%
Robustness of results 7/20 35%
Reporting quality 10/12 83%
Reproducibility 7/20 35%
Why this score?

The APPRAISE-AI tool grades AI/ML medical studies across 24 items in 6 subdomains, scored independently by two reviewers. The total reflects the methodological transparency of the publication — not the underlying clinical value of the model.

How to read this: high scores in clinical relevance and reporting with low scores in methodological conduct, robustness, or reproducibility is the dominant pattern in ophthalmic AI today.

Quality bands: Low <40 · Moderate 40–59 · High 60–79 · Very High 80+. Most published ophthalmic AI sits in the Low–Moderate band; studies that break into High typically combine multi-center datasets, prospective evaluation, and open-source release.

§06Full Metadata
Citation & identification
Bibliographic record
Model IDoculoplastics_park_2025
Full author listYang, H., Cho, K., Park, J., Kim, S., Seo, M., Shin, Y., Im, G., Kim, M., Song, S. H., & Seo, C. W.
JournalJ Clin Med
DOI10.3390/jcm14051691
ConditionsPtosis, blepharoptosis
Architecture
Model internals
Architecture familyCNN
Architecture detailDeepLabV3+–based segmentation pipeline integrated into the Anigma-view v1.0.6 software
Funding & conflicts
Disclosures
FundingK-Health National Medical AI Service and Establishing Industrial Ecosystem Project by the Special Account for Regional Balanced Development of the Ministry of Science and ICT and the Daejeon Metropolitan City, 2024 (H0503-24-1001)
Conflicts of interestAuthors Chang-Wook Seo, Kyungmin Cho, JungJin Park, Seonghyeon Kim, Myunggyun Seo, Yerim Shin, Gyeonghun Im, and Minju Kim are employees of Anigma Technologies Inc., Daejeon, Republic of Korea. Author Seung-Han Song serves as an outside director of Anigma Technologies Inc.
Card lifecycle
Status, version, reviewers
Card statusPublished
Card versionv1.0.0
First added2026-04-28
Last reviewed2026-04-28
Reviewersattribution opt-in pending
Update history
Card changelog
  • 2026-04-28 initial publication (v1.0.0)
← Back to Oculoplastics