ThyroNod-US
ThyroNod-US is a SYNTHETIC/DEMO cancer detection model for thyroid nodule ti-rads classification. Outputs are deterministic demo values — NOT for clinical use. Trained (synthetically) on de-identified imaging data.
Imaging
DeepCell AI
License: CC-BY-4.0
v1.1.8
RTG 4.5
DL 405,191
Metrics
| Metric | Value | Split |
|---|---|---|
| AUC | 0.926 | Synthetic hold-out |
| Calibration (ECE) | 0.026 | Synthetic |
| Inputs | Outputs |
|---|---|
| Ultrasound frame | TI-RADS category |
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-011-thyronod-us/predict",
headers={"Authorization": "Bearer <API_KEY>"},
json={"input": "<ultrasound frame>"})
print(r.json()) # -> synthetic demo prediction
See the API reference · JSON: /api/models/bf-011-thyronod-us
Version history
| Version | Status | Notes |
|---|---|---|
| v1.1.0 | Archived | Synthetic release note 0 |
| v1.1.1 | Archived | Synthetic release note 1 |
| v1.1.2 | Archived | Synthetic release note 2 |
| v1.1.3 | Archived | Synthetic release note 3 |
| v1.1.4 | Archived | Synthetic release note 4 |
| v1.1.5 | Archived | Synthetic release note 5 |
| v1.1.6 | Archived | Synthetic release note 6 |
| v1.1.7 | Archived | Synthetic release note 7 |
| v1.1.8 | Current | Synthetic release note 8 |
Community contributions: 110 synthetic contributors have submitted evaluations and fine-tunes.