AI service — AI Medical · Radiology
Chest X-ray screening
Score chest radiographs for common findings, order a reading queue, and index an archive for retrieval and zero-shot classification.
Send us your data volume, throughput and latency targets and any constraint we should design around. You get a proposed configuration, a benchmark on your own data, and a known cost per unit of work before you commit.
This is the highest-volume examination in radiology and the cheapest place to apply a model. Classifiers return probabilities across a fixed finding list, image encoders return embeddings for your own endpoints, and image-text models allow a finding to be specified in words rather than trained.
Radiographs arrive as DICOM or PNG and come back as scored findings or embeddings. Report drafting is a separate service — this one is about detection, triage and search across volume.
Every output is clinical decision support, not a diagnosis: a qualified professional reviews and signs it. Where clinical use requires regulatory approval in your jurisdiction, that approval remains yours to hold — we provide the infrastructure, the model operations and the audit trail behind it.
What we size for
We build the chest x-ray screening pipeline around the workload you actually have: data format, accuracy target, latency, throughput, concurrency, retention and scheduling. Start with a pilot, then scale production capacity without changing a line of your integration.
Common use cases
- Worklist ordering — Rank a reading queue so likely-abnormal studies are read first.
- Zero-shot finding search — Query an archive for a finding without training a classifier for it.
- Local classifier training — Train your own endpoint on embeddings from your own labelled studies.
More Radiology services
- CT analysisCT analysis service →
- MRI analysisMRI analysis service →
- Breast cancer screeningBreast cancer screening service →
- Lung cancer screeningLung cancer screening service →