Comparable cases, with honesty
Finds similar cases and says plainly how similar, and how uncertain, each one is.
Tesryn Lab · Health research
Reconstruction Research Studio
A research workbench for breast reconstruction after mastectomy: comparable cases, plain explanations, and room for clinicians to steer it.
Research prototype First built for a clinical research collaboration · 2026
01 — What it is
For researchers exploring decision support in post-mastectomy reconstruction. Given a described case, it finds comparable cases, says how sure it is, and explains the match in plain language. Clinicians use a no-code studio to rate results blind, review wording, build scenarios and run experiments, with an assistant that drafts but never decides. A companion simulation studies how tissue and implant shape interact, on generated geometry only.
The moment it earns its keepA clinician sits down with a described case and sees comparable ones, in words they would use with a patient, with the uncertainty said out loud.
What it proves we can do
02 — What it can do
Four things it does.
Built for clinicians who don't code
Blind rating, wording review, scenarios and experiments, all without writing code.
An assistant that drafts, a person who clicks
Suggestions from the assistant do nothing until a person approves them.
Fast physical simulation
Soft-tissue simulation quick enough to explore many shapes and settings interactively.
03 — How it connects
What it shares with the rest of the Lab.
The same things we know how to do keep coming back in different industries. This is where this one sits: what it proves, and what else proves the same thing.
Every claim traced to its source Nothing is asserted without the passage, part number or measurement behind it. Also proved by Podcast Maker, Engineering Library, Part Finder, Application Engineering, Research Benchmark, Research Runtime.
Saying how sure it is, in plain words Confidence expressed so a non-specialist can weigh it, not hidden in a number. Also proved by Magnetic Digital Twin.
Plain language, no training day One action per screen, words the user already uses, and errors that say what to do next. Also proved by Tesryn Signal, Part Finder, Referral Engine, Command Center, Tesryn Launch, Referral Platform, Insurance-aware Intake.
Simulation you can decide with Fields, forces, heat and soft tissue, solved fast enough to explore and checked against known answers. Also proved by Magnetic Digital Twin.
A person approves before it's real Automation can prepare anything and finish nothing. The last step is always a person. Also proved by Tesryn Signal, Podcast Maker, CAD Workbench, Application Engineering, Command Center, Tesryn Launch.
The whole map — six sections, and everything that proves them.
04 — What it's held to
- Every record in it is synthetic and fictional. No patient data is used, and none is accepted.
- Anything that would need real patient data stays switched off.
What it isn't. Not a medical device. Not for diagnosis, treatment or surgical planning, and not clinically validated.
05 — The recipe stays in the lab
We'll tell you what it can do. Not how it's built.
Yours would be your own build, on your systems, and you'd own it outright: code, documentation, no lock-in. What we bring to it is the practice — we've solved this shape of problem before, so you're not paying for the first attempt. The method stays ours. And if what you need isn't here at all, that's the usual case — it's how every skill on this page started.