Skip to main content
Rase AI Intelligence Newsletter

Healthcare, biotechnology & medical AI Research

Phikon-v2 represents histology images for computational pathology research

Owkin’s Phikon-v2 is a visual feature extractor for research on digitized histology. It turns image content into numerical representations that can be used in downstream studies. [1][2]

Research output
Documented histology-image feature extractor and author research preprint. [1][2]

What the researchers found

The authors submitted the first version of their Phikon-v2 preprint on September 13, 2024. The Owkin model card documents the published model. [1][2]

Why it matters

Using a reusable representation helps researchers compare subsequent machine-learning analyses with a common feature extractor. [1][2]

Who can use the findings

The project is relevant to machine-learning and computational pathology research teams. [1][2]

Key dates

  1. Owkin authors submit the Phikon-v2 preprint [1]

Practical uses

The authors provide model documentation and a research evaluation alongside the feature extractor. [1][2]

Limits of the evidence

Results in the author manuscript cover the evaluated research tasks. They do not provide validation for a clinical deployment. [1][2]

Sources and verification

Catalog evidence checked How we verify records

  1. Primary source Owkin authors’ Phikon-v2 preprint, first version
  2. Primary source owkin/phikon-v2
  3. Other source Phikon-v2, A large and public feature extractor for biomarker prediction

Related profiles

Healthcare, biotechnology & medical AI

Sleep Analysis Module (SAM)

Neurotronics (Nihon Kohden)

The module estimates sleep time from a signal captured during its intended sleep-testing workflow.

High confidenceEvidence checked

Healthcare, biotechnology & medical AI

Heartvue.Proton

Heartvue.ai

It is software for analyzing cardiac MRI images within its documented intended-use scope.

Medium confidenceEvidence checked

Healthcare, biotechnology & medical AI

ThinkSono Guidance

ThinkSono

Provides guidance during acquisition of lower-extremity compression ultrasound images for review by healthcare professionals.

High confidenceEvidence checked