Veterinary Informatics

Pathology foundation models trained mostly on human tissue identify a slide's source dataset almost perfectly within species, and species recall falls from 0.79 to 0.20 once whole sources are held out. Open-weight language models running inside UW turn archived free-text pathology reports into labeled slide cohorts. Anatomic availability constrains how we can provide educational access to students. We explore how Gaussian-splat capture can be leveraged to educate future veterinarians.