LabRunner
Specimen custody · Research access · Lab AI

Every specimen accounted for. Every slide put to work.

LabRunner follows tissue from the moment it leaves the patient, through the courier van and the lab, to the moment it answers a research question. The lab keeps custody and control at every step, and researchers finally get the material, and the answers, they came for.

Why we built it

You can track a pizza to your door. Why not a breast biopsy?

A specimen carries the diagnosis. If it is mislabelled or lost, that information can be gone for good, even when the surgery and the recovery went well. The patient and their family live with the consequence.

Parcels get a scan at every hand-off. Most specimens still move on paper logs and memory. LabRunner gives each one a chain of custody you can read at a glance: where it is, who touched it, and when.

A parcel
A typical specimen
With LabRunner
Products

One trail, six products

ATLAS and PRISM open the lab's archive to research, with AI estimates the lab reviews before anyone sees them. SAMS, SAMS+, TRACE and ARK keep every specimen accounted for: in the lab, on the road and in our archive.

Research and AIThe focus: put the archive to work for research
TILES VOTE MSI SCORE MSSMSI-HIGH
Research use only

PRISM

Pathology Research Insights from Slide Models

AI estimates from the slide image, released only after a person at the lab has looked.

  • MSI from H&E today; breast, lung and more on the roadmap
  • Researchers watch the run live, then get maps and scores
  • Citable methods, and questions answered by AI or the lab
colon · MSI-high 03886124CASES MATCHNO NAMES SHOWN THE ARCHIVE LAB DECIDES S-7QK2 S-M4TDPSEUDONYMS ONLY
For researchers

ATLAS

Archive Tissue Lookup And Search

A research window onto the lab's archive. Researchers find tissue by counts, ask for it, and the lab decides.

  • Search by tumour type, biomarker, stage and year
  • Counts only: small groups hidden, no patient details
  • Requests run through the lab's own custody trail
Lab operationsEvery specimen accounted for: in the lab, on the road and in our archive
TOWER 3 · DRAWER 4 pos 22 SCAN · FILE
For the lab

SAMS

Slide Archive and Management System

Custody and real-time tracking for pathology, from accessioning to the archive and back.

  • Every slide and block located to tower, drawer and position
  • Handset scans for filing, pulls and returns
  • Send-outs, overdue chasers and a full audit trail
MICROTOME NEW SLIDE IMAGED Ready · lab notified LIVE
For the lab, plus services

SAMS+

Everything in SAMS, plus the lab work around it

New sections and images from the archive on request, and custody that follows a slide beyond the lab's walls.

  • Slide imaging, re-cuts and unstained slides
  • Microtome sectioning from archived blocks
  • External chain of custody, with live monitoring and notifications
CLINIC LAB GPS · LIVE
On the road

TRACE

Transport, Routing And Chain-of-custody Engine

Specimens and slides tracked between sites with couriers and GPS, so nothing goes missing on the way.

  • Live courier location by GPS
  • A scan at pickup, hand-off and arrival
  • Checked in against what was sent, on the same custody trail
LAB SHELF ARK VAULT S26-04817 DIGITISED Request · slide A1 Delivered
Archive as a service

ARK

Archive, Retrieval and Keeping

We store your slides, tissue blocks and paperwork, so your lab doesn't have to. Anything you need comes back on demand.

  • Secure off-site storage for slides, tissue blocks and documents
  • Paperwork digitised and searchable, matched to each case
  • Pick-up and delivery on demand, tracked end to end with TRACE
How it works

From the patient to a research answer, with the lab in control

  1. 1TRACECollected and sentLabelled, packed and tracked by GPS on the way to the lab.
  2. 2SAMSTracked through the labEvery hand-off scanned: accessioning, grossing, slides, sign-out.
  3. 3SAMSFiled in the archiveShelf and position known, any time.
  4. 4ATLASFound by a researcherCounts only, under pseudonyms.
  5. 5LabApproved by the labA person decides; pulled under the custody trail.
  6. 6PRISMAI estimate runOn the approved slides, counts shown live.
  7. 7LabReviewed, then releasedMaps, scores and methods go to the researcher.
Tracked stepA person at the lab decides
PRISM · MSI from H&E

Every tile casts a vote, and you can see where

MSI-high colon cancers respond differently to treatment, and the standard tests take extra tissue and time. Our model estimates MSI status from the routine H&E slide, for research, and shows which parts of the tissue drove the estimate.

AI map of a public colon slide, mostly red: leaning MSI-high
1.00 leaning MSI-high · published test: MSI-high · 5,996 tiles
AI map of a public colon slide with blue across the tumour: leaning MSS
0.00 leaning MSS · published test: MSS · 6,000 tiles
pushes toward MSI-highpushes toward MSSPublic TCGA slides TCGA-AA-3710 and TCGA-NH-A50T, each scored by models that never saw its hospital.
A tile of colon tissue, 224 pixels square

Cut into tiles

Each slide becomes thousands of small squares of tissue, 224 pixels at about 20x. Background is skipped.

Fingerprinted

An advanced pathology foundation model reads each tile and captures what the tissue looks like as a compact numeric fingerprint.

Weighed and voted

Our AI attention model, trained on public slides, learns which tiles matter. Their pushes add up to the score.

Questions get answered, by the AI or by the lab

Researchers can ask about their released results in plain English. Gemini answers from the released scores, the model card and the methods, nothing else. Anything only the lab can see goes to the lab with one button, and the lab's reply arrives in the same thread.

What does borderline mean for my slides?
AIBorderline is a score from 0.40 to 0.60, where the model is close to undecided. Two of your slides fall there, so treat them as uncertain rather than as a lean either way.
Ask the lab
From the labOn slide 4 the red and blue are mixed through the tumour. We would confirm it with mismatch-repair staining.

Illustration. The lab reads every question.

Evidence so far

Tested the hard way: on hospitals the model never saw

0.81AUC on unseen hospitals (95% range 0.73 to 0.89)
Colonfirst tissue; breast and lung next
22hospitals, each held out in turn
543labelled TCGA colorectal patients available for the next phase
Phase 1 · done

Feasibility

MSI on public colon slides, tested hospital by hospital, and the full loop from request to released map running end to end.

Phase 2 · next

Scale and validate

More public slides and hospitals, external validation on an independent cohort, and new tissues, starting with breast and lung.

Phase 3

Each lab's own slides

Local validation on a partner lab's scanner and stain, using its own mismatch-repair results as labels. A model that gets better with every lab that joins.

These are research results on public data. The AI estimate is not a validated clinical test and is not used for patient care. Demonstrations use made-up (synthetic) cases.

Principles

Built so the lab never loses control

The lab decides

Approving a request, starting an AI run and releasing a result are each done by a person at the lab. Nothing leaves on its own.

Privacy by design

Researchers see counts, never people. Slides travel under pseudonyms only the lab can reverse, and small groups stay hidden.

Honest about the AI

Every result carries its model card, its tested accuracy and its limits. Borderline means borderline.

One trail for everything

Clinical custody and research use run on the same signed record, so a slide on loan is never a slide lost.

Our story

Built by people who have seen what a lost specimen costs

"An irreplaceable biopsy deserves at least the care we give a parcel."

LabRunner grew out of our own work in specimen tracking and management, with more than forty years of combined experience in the industry behind it.

We started with patient safety: making sure every specimen is where it should be. Along the way we saw how much the archive could do for research, and how often researchers got the worst of the deal: long waits, little material, and results they could not explain.

So we built the rest of the trail. Custody first, then research access, then AI the lab can stand behind.

See it on your own workflow

We will walk you through custody, research access and the lab AI with synthetic data, and talk about what your lab needs.

LabsTrack every specimen; open your archive to research on your terms.
ResearchersFind tissue, request it, and get AI estimates you can cite.
PartnersHelp validate the next models on your own slides.
Write to
renee.hoyle@labrunner.app
Open email
Tell us about your lab and what you would like to see.