Cancer Detection

HemeBlast-Leuk

HemeBlast-Leuk is a SYNTHETIC/DEMO cancer detection model for acute leukemia blast cell classification. Outputs are deterministic demo values — NOT for clinical use. Trained (synthetically) on de-identified imaging data.

Imaging MayoBio Labs License: BioFoundry Research v2.4.9 RTG 5.0 DL 248,532
SYNTHETIC DEMOAll outputs are deterministic demo data — not for clinical use, not real medical inference.

Metrics

MetricValueSplit
Accuracy0.858Synthetic hold-out
Calibration (ECE)0.025Synthetic
InputsOutputs
Blood smear microscopyBlast % + subtype

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-009-hemeblast-leuk/predict",
    headers={"Authorization": "Bearer <API_KEY>"},
    json={"input": "<blood smear microscopy>"})
print(r.json())  # -> synthetic demo prediction

See the API reference · JSON: /api/models/bf-009-hemeblast-leuk

Version history

VersionStatusNotes
v2.4.0ArchivedSynthetic release note 0
v2.4.1ArchivedSynthetic release note 1
v2.4.2ArchivedSynthetic release note 2
v2.4.3ArchivedSynthetic release note 3
v2.4.4ArchivedSynthetic release note 4
v2.4.5ArchivedSynthetic release note 5
v2.4.6ArchivedSynthetic release note 6
v2.4.7ArchivedSynthetic release note 7
v2.4.8ArchivedSynthetic release note 8
v2.4.9CurrentSynthetic release note 9

Community contributions: 22 synthetic contributors have submitted evaluations and fine-tunes.