Orbital Trauma Planning Platform (Mimics-Romexis)
Real-time automated segmentation of orbital fractures to support diagnosis and surgical planning
▸ More attributes
Brief overview
This study prospectively evaluates two FDA-cleared commercial AI segmentation engines — Materialise Mimics Viewer and Planmeca Romexis Smart Tool — for real-time orbital and maxillofacial fracture segmentation in 53 emergency-department CT cases. Both tools achieved Dice similarity of 0.92–0.93 against a semi-automated reference, with ~6× faster segmentation than the manual workflow. Expert readers rated clinical utility at 4.4/5. The work demonstrates that commercially available, regulator-cleared AI can already deliver clinically usable orbital segmentation; it does not characterize generalization, calibration, or subgroup performance, and the underlying model weights are proprietary.
Segmentation time ~10 min (AI) vs ~63 min (semi-automated); DSC 0.92–0.93; Jaccard 0.88–0.89; Hausdorff Distance ~0.92 mm; expert clinical utility score 4.4/5.
Segmentation time ~10 min (AI) vs ~63 min (semi-automated); DSC 0.92–0.93; Jaccard 0.88–0.89; Hausdorff Distance ~0.92 mm; expert clinical utility score 4.4/5.
| Study design | Prospective cohort |
|---|---|
| Center type | Single-center |
| Patients | 53 |
| Images / eyes | 53 CT images |
| Split | All 53 cases used as the prospective evaluation cohort |
| Reporting frameworks | None stated |
| Age range | Mean 37 |
|---|---|
| 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_shhadeh_2025 |
|---|---|
| Full author list | Daoud, S., Redenski, I., Oren, D., Zoabi, A., Kablan, F., & Srouji, S. |
| Journal | Diagnostics (Basel) |
| DOI | 10.3390/diagnostics15080984 |
| Conditions | Facial bone fracture, orbital injuries, foreign body localization |
Model internals ▸
| Architecture family | Commercial API |
|---|---|
| Architecture detail | FDA-approved commercial AI tools (Materialise Mimics Viewer; Planmeca Romexis Smart Tool). |
Disclosures ▸
| Funding | Department of Oral and Maxillofacial Surgery, Galilee College of Dental Sciences, Galilee Medical Center, Nahariya 2210001, Israel |
|---|---|
| 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)