Conversational Pathology Copilot
Loupe is a chat-first copilot for whole-slide imaging. Ask while you read; it calls pathology vision models and literature tools, returning verifiable reasoning, structured quantification, and one-tap annotation drafts — pathologist always in control.
Why Loupe
Ask in plain language; get answers backed by a visible tool trace.
IHC positivity, H-score, differential & PubMed — rendered inline.
Agents batch-draft; you accept/reject, with budgets & audit.
Adoption telemetry, cost & approval rate — measurable, tunable.
How a case moves through Loupe
Loupe isn’t a bag of features — it threads AI through the real diagnostic flow, with the pathologist deciding at every step.
01 Ingest & triage
Upload or import WSIs via DICOMweb. Loupe scores QC, writes a scan-time pre-read, and groups by organ — so you start with the slide that matters.
02 Conversational read-out
Select a region and ask. Loupe reads the tile, computes stats, quantifies IHC (e.g. ER 92%, H-score 285), cites PubMed, and shows the differential it weighed — not just a verdict.
03 Autonomous agents
“Map every invasive front and flag tumor budding.” The agent plans and runs within iteration / time / token budgets, drafting annotations per slide — dispatch across a whole case at once.
04 Human review & adopt
The task page shows the plan, budgets and activity trace; accept/reject drafts singly or in bulk, with a verifier surfacing low-confidence ones — and your reasons feed the next run.
05 Compare in sync
Put a case’s slides (H&E + MMR PMS2/MSH6, or H&E + ER) into a pan/zoom-synced comparison — here MSH6 loss flags mismatch-repair deficiency for Lynch workup.
06 Telemetry & governance
Track classifier adoption by confidence and over time, per-label acceptance, and agent cost & approval rate — so the whole deployment can be governed and tuned.
In detail
Uniform close-ups — every load-bearing number, clearly legible.
Editions & deploy
Async FastAPI + SQLAlchemy, React 19 + OpenSeadragon, OpenSlide pipeline, pluggable multi-LLM; Docker / GPU / HTTPS deploys and DICOMweb import.
| Capability | Commercial | Education |
|---|---|---|
| Chat read-out · annotations · report draft | ✓ | ✓ |
| Agents · telemetry · comparison | ✓ | ✓ |
| Pathology foundation models UNI / CONCH | — | ✓ (CC-BY-NC-ND) |
| Similar-tile search | color/texture fingerprint | ✓ UNI embeddings |
| Image / use | smallest · cloud-defensible | weights baked · non-commercial |
Gemini / OpenAI / MiniMax / Kimi via one compatible layer.
JWT auth, rate-limit, full audit log, TLS proxy.
OpenSlide formats · DZI tiles · DICOMweb import.