EyeModelHub
Home Subspecialties Oculoplastics Model card
§Model Card

Preoperative Counselling Diffusion Model (DALL·E2)

Generate illustrative preoperative cosmetic outcome images for patient counselling in oculoplastics.

Balas M. · 2024 · Canada · doi:10.1016/j.jcjo.2023.09.006
Open DOI
Generation Diffusion External photo Concept
More attributes
Anatomy · Periorbital soft tissueAnatomy · OrbitConditions · PtosisConditions · Thyroid-associated orbitopathySingle-centern = 2 patients · NR images
§01Overview

Brief overview

OpenAI DALL·E 2 was used as a text-to-image generative AI platform for simulated postoperative counselling in oculoplastics. Using publicly available pre- and postoperative photographs from 2 patients with ptosis and thyroid eye disease, investigators masked periocular regions and entered text prompts to generate predicted postoperative appearances. Images were manually selected based on perceived similarity to actual surgical outcomes, with generation completed in minutes through the web-based editor. The study was a proof-of-concept demonstration without quantitative validation metrics, external testing, or clinical deployment. No code, model weights, or calibration analyses were released.

§02Performance
Headline performance

No quantitative evaluation. Satisfactory images required 1–3 attempts; end-to-end workflow >3 minutes per case.

Full metrics — as reported
No quantitative evaluation. Satisfactory images required 1–3 attempts; end-to-end workflow >3 minutes per case.
Calibration · Uncertainty
Not reported.
Bias · Fairness
Not reported.
§03Data & Validation
Study designMethodological/development-only
Center typeSingle-center
Patients2
Images / eyesNot reported
SplitNot reported
Reporting frameworks None stated
Age range48-54
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
14 /100 Low
ClinicalDataMethodRobust.Report.Repro.
Sub-domain scores
Clinical relevance 4/4 100%
Data quality 0/24 0%
Methodological conduct 0/20 0%
Robustness of results 0/20 0%
Reporting quality 9/12 75%
Reproducibility 1/20 5%
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_balas_2024
Full author listMicieli, J., Wulc, A. & Ing, E.
JournalCan J Ophthalmol
DOI10.1016/j.jcjo.2023.09.006
ConditionsPtosis, Thyroid-associated orbitopathy
Architecture
Model internals
Architecture familyDiffusion
Architecture detailText-to-image diffusion model (DALL·E 2)
Funding & conflicts
Disclosures
FundingNot reported
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