EyeModelHub
Home Subspecialties Oculoplastics Model card
§Model Card

Blepharoptosis AI Platform (DenseNet121)

Binary classification of blepharoptosis from single-eye crops of clinical photographs

Hung J.Y. · 2021 · USA, Taiwan · doi:10.1016/j.ijmedinf.2021.104402
Open DOI
Classification CNN External photo Internally validated
More attributes
Anatomy · Periorbital soft tissueConditions · BlepharoptosisSingle-centern = NR patients · 434 images images
§01Overview

Brief overview

This study developed a convolutional neural network (CNN) system to identify blepharoptosis from standard clinical photographs without manual annotation or external reference markers. Using 434 retrospectively collected single-eye images from a tertiary ophthalmic center in Taiwan, the authors compared 22 CNN configurations including DenseNet, ResNet, VGG, AlexNet, and SqueezeNet architectures with and without ImageNet pretraining. The best-performing model, DenseNet121 without pretraining, achieved 90.1% sensitivity, 82.4% specificity, and AUROC 0.95 on internally validated test data using 5-fold cross-validation. Images were labeled by consensus of oculoplastic surgeons. No external validation, prospective deployment, open-source code, or public model weights were reported. The dataset consisted entirely of Asian patients, limiting generalizability.

§02Performance
Headline performance

Best model (DenseNet121, no pretraining): sensitivity 0.90; specificity 0.82; accuracy 0.89; AUROC 0.95.

121
Best model (DenseNet
0.82
specificity
0.89
accuracy
Full metrics — as reported
Best model (DenseNet121, no pretraining): sensitivity 0.90; specificity 0.82; accuracy 0.89; AUROC 0.95.
Pretrained models trained faster but offered similar accuracy.
Calibration · Uncertainty
Not reported.
Bias · Fairness
Not reported.
§03Data & Validation
Study designDiagnostic accuracy study
Center typeSingle-center
PatientsNot reported
Images / eyes434 images
Split~72/18/10 + 5-fold cross-validation
Reporting frameworks None stated
Age range>18
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 none
License Not specified
§05Quality Review · APPRAISE-AI
Total score
44 /100 Moderate
ClinicalDataMethodRobust.Report.Repro.
Sub-domain scores
Clinical relevance 4/4 100%
Data quality 11/24 46%
Methodological conduct 4/20 20%
Robustness of results 4/20 20%
Reporting quality 12/12 100%
Reproducibility 9/20 45%
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_hung_2021
Full author listPerera, C., Chen, K. W., Myung, D., Chiu, H. K., Fuh, C. S., Hsu, C. R., Liao, S. L., & Kossler, A. L.
JournalInt J Med Inform
DOI10.1016/j.ijmedinf.2021.104402
ConditionsBlepharoptosis
Architecture
Model internals
Architecture familyCNN
Architecture detailMultiple CNN architectures (best: DenseNet121).
Funding & conflicts
Disclosures
FundingNational Eye Institute (P30 EY026877); Research to Prevent Blindness (RPB); Computational and storage resources were sponsored by Taiwan National Center for High-performance Computing (NCHC)
Conflicts of interestNo conflicts
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