MammoNet-Screen
MammoNet-Screen is a SYNTHETIC/DEMO cancer detection model for breast cancer screening from mammography. Outputs are deterministic demo values — NOT for clinical use. Trained (synthetically) on de-identified imaging data.
Imaging
NeuroScan Labs
License: BioFoundry Research
v1.0.2
RTG 4.4
DL 339,658
Metrics
| Metric | Value | Split |
|---|---|---|
| AUC | 0.939 | Synthetic hold-out |
| Calibration (ECE) | 0.034 | Synthetic |
| Inputs | Outputs |
|---|---|
| Mammogram (2-view) | BI-RADS score + lesion map |
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-002-mammonet-screen/predict",
headers={"Authorization": "Bearer <API_KEY>"},
json={"input": "<mammogram (2-view)>"})
print(r.json()) # -> synthetic demo prediction
See the API reference · JSON: /api/models/bf-002-mammonet-screen
Version history
| Version | Status | Notes |
|---|---|---|
| v1.0.0 | Archived | Synthetic release note 0 |
| v1.0.1 | Archived | Synthetic release note 1 |
| v1.0.2 | Current | Synthetic release note 2 |
Community contributions: 50 synthetic contributors have submitted evaluations and fine-tunes.