Skip to content
Aiosyn

Objective tissue read-outs for yourpreclinical study

Aiosyn’s computational pathology solutions provide CROs and biopharma organizations with cutting-edge tools to identify new and existing pathology-based biomarkers, enhancing biological understanding and streamlining drug development efforts.

Discuss your studyCustom AI development
  • Every structure on the section, not a sampled field
  • Same slide, same read-out, every run
  • Validated with preclinical CROs and pathologists
Stained sectionAI read-out
Drag the handle. Left: the stained section. Right: every structure the model classified across it, edge to edge.

Bringing a new drug to market takes 10 to 15 years

Bringing a new drug to market typically takes between 10 and 15 years and on average $1.3 billion. However, the emergence of transformational technologies such as artificial intelligence and computer vision offers the potential to simplify and accelerate the drug development process, transforming how biomarkers are discovered and developed.

A hand carrying a rack of stained histology slides through a laboratory.

Tissue measured as continuous quantities

Aiosyn’s computational pathology solutions provide CROs and biopharma organizations with cutting-edge tools to identify new and existing pathology-based biomarkers, enhancing biological understanding and streamlining drug development efforts.

Two Aiosyn colleagues at a screen showing a whole-slide image with the model's detections beside the code that produced them.

Our current focus areas

We build AI solutions for various applications, based and validated on real preclinical cohorts. Explore our focus areas below, or reach out to discuss a different tissue or endpoint.

AI read-out of an aortic-root cross-section, with the atherosclerotic lesion delineated across the whole section.

Atherosclerosis

Lesion burden measured across the full aortic-root cross-section rather than estimated from a scored grade.

Explore atherosclerosis
AI read-out of a brain section with individual neurons detected and the anatomical regions distinguished.

Brain

Every neuron detected across the section and attributed to the region it sits in, so density is comparable between animals.

Explore brain read-outs
AI read-out of a PAS-stained kidney section with glomeruli, tubuli and arteries segmented.

NephroPath, for kidney

Every glomerulus on the section found and scored, with tubuli and arteries segmented alongside them.

Explore NephroPath
AI read-out of a liver section with fibrotic tissue and inflammatory foci highlighted.

Liver

Fibrosis measured as an extent across the whole section instead of a stage, so smaller differences stay visible.

Explore liver read-outs

A different tissue or endpoint

Custom AI development builds the model on your own images, for a tissue, stain or endpoint of your interest.

See how that works

More tissue measured, more statistical power

A manual score samples a few fields per section, and varies with the reader.

  • The same read-out on every run

    One fixed method, applied to every section in the cohort.

  • Across 100% of the tissue

    Every structure on the section is quantified rather than a handful of sampled fields, so the same question can be put to a leaner cohort.

  • Read-outs inside a week

    Where an existing model applies to your tissue, a standard suite analysis returns read-outs within a week.

Validated on real preclinical cohorts

We co-develop and validate our models with pathologists and other experts in the field

Figure from the published study: a raw PAS-stained kidney section beside Aiosyn's multi-class AI prediction, with a legend for arteries, tubuli, and glomeruli.

Peer-reviewed study

Physiogenex

AI read-outs across whole kidney sections detected a treatment effect that manual scoring missed

In a peer-reviewed diabetic nephropathy study with Physiogenex, the AI counted every glomerulus and tubule across the whole kidney section and revealed a dapagliflozin treatment effect.

Briand F, et al. · European Journal of Pharmaceutical Sciences · 2026

Read the study write-up
AI versus pathologist lesion area Scatter of 80 cases comparing Aiosyn AI lesion-area read-outs with expert pathologist scoring; points cluster along the line of perfect agreement (Pearson r = 0.96). 0 0 400 400 800 800 1200 1200 1600 1600 y = x r = 0.96 · R² = 0.91 · n = 80 Pathologist lesion area (×10³ µm²) AI lesion area (×10³ µm²)

Method validation

Across 80 cases, AI lesion-area read-outs matched expert pathologist scoring

Developed with TNO, the AI measures atherosclerotic lesion area across the full aortic-root cross-section of every animal in the cohort.

Atherosclerosis · aortic-root cross-sections

Explore atherosclerosis read-outs

From slide to read-out

Three steps, no new scanning workflow, and fully traceable from case to result.

  1. 1

    Share your slides

    Whole-slide images in the formats you already scan. No change to how your sections are prepared or digitized.

  2. 2

    The AI reads every section

    Structures are segmented and cells detected across the full tissue, on every slide in the cohort, under one fixed method.

  3. 3

    Read-outs come back quantified

    A report of per-animal and per-group read-outs, ready for your statistics and traceable back to the images they came from.

Let's talk about your cohort

Tell us the tissue, the stain and the endpoint you need measured. We will tell you which read-outs apply and what they would look like on your own sections.

Discuss your study