Analytical Validation of Digital Mouse Detection, Identification, and Activity in the Envision Platform

The foundation of the JAX Envision™ platform is a set of machine learning algorithms that detect and identify individual mice within their home cage.

Using an analytical validation framework, Envision demonstrates strong detection and identification efficiency and accuracy across a broad range of mouse strains and microenvironmental conditions.

When mice are clearly visible, the JAX Envision platform detects and identifies mice with accuracy of 99.9% and 95.2%, respectively, against a human annotated validation dataset.

The results of this validation highlight how the JAX Envision platform enables continuous experimental monitoring with highly accurate detection and tracking of individual mice in a cage for weeks to months at a time.