Preoperative Counselling Diffusion Model (DALL·E2)
Generate illustrative preoperative cosmetic outcome images for patient counselling in oculoplastics.
▸ More attributes
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.
No quantitative evaluation. Satisfactory images required 1–3 attempts; end-to-end workflow >3 minutes per case.
No quantitative evaluation. Satisfactory images required 1–3 attempts; end-to-end workflow >3 minutes per case.
| Study design | Methodological/development-only |
|---|---|
| Center type | Single-center |
| Patients | 2 |
| Images / eyes | Not reported |
| Split | Not reported |
| Reporting frameworks | None stated |
| Age range | 48-54 |
|---|---|
| Sex (% female) | Not reported |
| Race / ethnicity reported | N |
| Subgroup performance | N |
- Concept
- Prototype
- Internal val.
- External val.
- Regulator
- Clinical
▸ 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.
Bibliographic record ▸
| Model ID | oculoplastics_balas_2024 |
|---|---|
| Full author list | Micieli, J., Wulc, A. & Ing, E. |
| Journal | Can J Ophthalmol |
| DOI | 10.1016/j.jcjo.2023.09.006 |
| Conditions | Ptosis, Thyroid-associated orbitopathy |
Model internals ▸
| Architecture family | Diffusion |
|---|---|
| Architecture detail | Text-to-image diffusion model (DALL·E 2) |
Disclosures ▸
| Funding | Not reported |
|---|---|
| Conflicts of interest | No conflicts |
Status, version, reviewers ▸
| Card status | Published |
|---|---|
| Card version | v1.0.0 |
| First added | 2026-04-28 |
| Last reviewed | 2026-04-28 |
| Reviewers | attribution opt-in pending |
Card changelog ▸
- 2026-04-28 initial publication (v1.0.0)