Cancer Detection

ColoPath-Detect

ColoPath-Detect is a SYNTHETIC/DEMO cancer detection model for colorectal polyp histopathology detection. Outputs are deterministic demo values — NOT for clinical use. Trained (synthetically) on de-identified imaging data.

Imaging EMBL-Synthetic License: BSD-3-Clause v4.9.0 RTG 4.1 DL 36,436
SYNTHETIC DEMOAll outputs are deterministic demo data — not for clinical use, not real medical inference.

Metrics

MetricValueSplit
F10.95Synthetic hold-out
Calibration (ECE)0.068Synthetic
InputsOutputs
H&E slide tilePolyp class + attention

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-005-colopath-detect/predict",
    headers={"Authorization": "Bearer <API_KEY>"},
    json={"input": "<h&e slide tile>"})
print(r.json())  # -> synthetic demo prediction

See the API reference · JSON: /api/models/bf-005-colopath-detect

Version history

VersionStatusNotes
v4.9.0CurrentSynthetic release note 0

Community contributions: 103 synthetic contributors have submitted evaluations and fine-tunes.