Theia by Prodius · Organoid quality control

Organoid QC before you spend a stain.

Upload one bright-field photo. Theia finds each organoid, measures it, and answers keep, discard or cannot decide, with the reason.

KeepDiscardCannot decide
Render: milky budding organoids floating on paper white, five ringed in thin graphite hairlines and one in orange. Not a micrograph.Render, not a micrograph
Each object
found and measured
One call each
with its rule

Built for

  • Organoid labs
  • Pharma screening teams
  • Biobanks and core facilities
  • Investors
01 / The QC call

Three answers, each with its rule.

Keep, discard or cannot decide, per organoid and per image, with the value that decided it. A blurry or empty image gets cannot decide, never a guess.

01

Decided by eye

Which wells go on to a stain or a sequencing run is decided at the eyepiece, and the decision is not recorded. Organoid cultures vary from batch to batch, so the same well can get a different call on a different day. [8]

02

Tools measure, they do not decide

Published organoid tools report area, circularity, solidity and counts. None of them returns keep or discard for an organoid, and none refuses an image it cannot measure. [1, 2]

03

Blur has no standard cut

Focus measures depend on the microscope and the content of the image, so a blur threshold has to be calibrated per instrument. No published cut exists for bright-field organoid images. [6, 5]

04

The stakes are rising

FDA's 2025 roadmap names organoids among the alternatives to animal testing. A culture that fails quality control after the expensive step costs the study, not just the well. [10]

One image, step by step

  • 1Upload

    stored once under its hash

  • 2Gate

    contrast, then focus

  • 3Find

    each organoid, split where two touch

  • 4Measure

    size, shape, edge, overlap

  • 5Call

    keep, discard, cannot decide

02 / How it works

Every answer names its rule and its version.

Render: six translucent layers stacked apart, from a plate holding four organoids through a grid, spheres, outline rings and a dot grid to a slab with an orange edge. Not a micrograph.Render, not a micrograph
  1. 01Upload
  2. 02Gates
  3. 03Measure
  4. 04Answer
  1. 01

    Upload one photo

    PNG, JPEG or TIFF, 8 or 16 bit. The file is stored once under its hash and never changed. Give the pixel size if you know it; without it the size rules abstain.

    Write-once, content-addressed

  2. 02

    The gates run first

    An empty well or a blurry image stops here with cannot decide and the measurement that stopped it. Noise never gets a keep or discard.

    Contrast gate, focus gate

  3. 03

    Each organoid is measured

    Objects are found, split where two touch, and measured: equivalent diameter, circularity, solidity, whether the frame cuts them, whether boxes overlap.

    Size, shape, edge, overlap

  4. 04

    Three answers, each with its rule

    Keep, discard or cannot decide, per organoid and for the image, with the rule and the value that decided it and the pipeline version that produced it.

    A person can overrule any call

Review and audit

A person overrules any call with a reason; the pipeline's call stays visible and the log is append-only.

Three answers

Keep, discard or cannot decide, per organoid and per image, with the rule and the measured value.

Recorded pipeline

A versioned spec with a hash: gates, segmentation, measurements and rules, each threshold with its source.

Image store

Every upload stored once under its sha256, read-only, with its pixel size.

03 / Applications

Where it applies first.

Lead use case

Before the stain

Decide which wells are worth a stain, a passage or a sequencing run, from the photo you already take.

Render: a frosted glass slide with one budding organoid under a thin crosshair and corner brackets, a small orange glow at its centre. Not a micrograph.Render

Drug testing

Start a dose-response from organoids that passed the same recorded rules, so a difference between wells is the compound, not the starting culture.

Passaging and expansion

A size and shape record for every passage, so a line's drift shows up in numbers instead of in memory.

Biobanks and shared images

Ship a QC call with every image you share, produced by a named pipeline version, so the receiving lab knows what it got.

Render: an organoid drawn as a graphite stipple point cloud, with one bud in orange. Not a micrograph.Render
04 / Why now

Regulatory pull

FDA is phasing out mandatory animal testing.

The FDA Modernization Act 2.0 removed the requirement in 2022. FDA's 2025 roadmap names organoids, organ chips and AI models as alternatives. More organoid studies means more wells to judge. [9, 10]

Organoids everywhere

Every organoid lab already has the photo.

Since the first adult stem cell organoids, bright-field imaging has been the daily check on a culture. The input to a QC call exists in every lab; the call does not. [7, 8]

Open data

Labelled bright-field images are public now.

Thousands of annotated organoid images have been released with permissive licenses, enough to train and test a detector on public data before any lab shares a single image. [3, 2, 1]

Honest rules

The first pipeline is written down, not learned.

Pipeline v0.1 is classical: a threshold, a focus measure, shape rules. Every threshold carries its source or the word ours, and the version hash pins every number on screen. [4, 5]

05 / Where we are

Where we are.

Five stages, from a written-down pipeline to rules per organoid type.

  1. 01 · We are here

    Classical pipeline v0.1

    Gates, segmentation and shape rules with every threshold sourced. Runs on example data and public images.

  2. 02 · Next

    Learned detector v0.2

    A small detector trained only on permissively licensed public images, shipped as a new recorded version with a held-out test.

  3. 03 · Later

    First lab pilot

    Real images from one lab, with their own pixel size, instrument and organoid type.

  4. 04 · Later

    Rules per organoid type

    Size and shape floors set per type with the lab, each with its source.

  5. 05 · Later

    More readouts

    Time series and plate scans, once a single image is trusted.

We are early stage. Stage 01 runs on example data and one public image.

06 / Questions

Questions we get.

What works today?

Pipeline v0.1: a contrast gate, a focus gate, classical segmentation and size and shape rules. It runs on example data and on one public bright-field image. We publish no accuracy number until a held-out test prints one.

What does cannot decide mean?

The pipeline could not measure what the rule needs: the image is blurry or empty, the organoid touches the frame, two objects overlap, or a value sits within 10% of its cut. It is an answer, not a failure, and it goes to a person.

Which organoids?

The first rules are type-agnostic: size, circularity, solidity, edge and overlap. Floors per organoid type come with the first lab partners, each with its source.

What happens to my images?

Each upload is stored once under its sha256 and never rewritten. Every result names the pipeline version and its hash. Decisions and the audit log are append-only.

Set the first rules with us.

For organoid labs, screening teams and biobanks that want a recorded QC call, and investors who want to see the plan.

Render: a graphite stipple terrain rising from a perspective grid. Not a micrograph.Render