RetinaScan-DR
RetinaScan-DR is a SYNTHETIC/DEMO medical imaging model for diabetic retinopathy grading. Outputs are deterministic demo values — NOT for clinical use. Trained (synthetically) on de-identified imaging data.
Imaging
Insilico BioFoundry
License: MIT
v1.5.0
RTG 4.4
DL 11,704
Metrics
| Metric | Value | Split |
|---|---|---|
| Quad-Kappa | 0.83 | Synthetic hold-out |
| Calibration (ECE) | 0.051 | Synthetic |
| Inputs | Outputs |
|---|---|
| Fundus photograph | DR severity grade |
Run a synthetic prediction
Returns a deterministic synthetic result — clearly labeled, not for clinical use.
API integration
Call this model from your pipeline (demo — no real key required):
import requests
r = requests.post("https://api.biofoundry.ai/v1/models/bf-037-retinascan-dr/predict",
headers={"Authorization": "Bearer <API_KEY>"},
json={"input": "<fundus photograph>"})
print(r.json()) # -> synthetic demo prediction
See the API reference · JSON: /api/models/bf-037-retinascan-dr
Version history
| Version | Status | Notes |
|---|---|---|
| v1.5.0 | Current | Synthetic release note 0 |
Community contributions: 27 synthetic contributors have submitted evaluations and fine-tunes.