Cancer Detection

DermoScan-Mel

DermoScan-Mel is a SYNTHETIC/DEMO cancer detection model for melanoma vs benign nevus classification. Outputs are deterministic demo values — NOT for clinical use. Trained (synthetically) on de-identified imaging data.

Imaging Genoma Institute License: Apache-2.0 v3.5.7 RTG 4.8 DL 272,825
SYNTHETIC DEMOAll outputs are deterministic demo data — not for clinical use, not real medical inference.

Metrics

MetricValueSplit
Accuracy0.832Synthetic hold-out
Calibration (ECE)0.043Synthetic
InputsOutputs
Dermoscopy imageMelanoma probability

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-003-dermoscan-mel/predict",
    headers={"Authorization": "Bearer <API_KEY>"},
    json={"input": "<dermoscopy image>"})
print(r.json())  # -> synthetic demo prediction

See the API reference · JSON: /api/models/bf-003-dermoscan-mel

Version history

VersionStatusNotes
v3.5.0ArchivedSynthetic release note 0
v3.5.1ArchivedSynthetic release note 1
v3.5.2ArchivedSynthetic release note 2
v3.5.3ArchivedSynthetic release note 3
v3.5.4ArchivedSynthetic release note 4
v3.5.5ArchivedSynthetic release note 5
v3.5.6ArchivedSynthetic release note 6
v3.5.7CurrentSynthetic release note 7

Community contributions: 93 synthetic contributors have submitted evaluations and fine-tunes.