Kestrel: 300M-Param Pathology Vision Foundation Model Pretrained on 400M Slide Patches

kjgeras · x · 2026-07-06

The underlying pathology signal for the AI test comes from Kestrel, a 303M-parameter ViT-L model. It uses the DINOv2 method for self-supervised pretraining on 400M pathology image patches from 45,000 slides, learning morphological features directly from H&E images rather than relying on hand-crafted features.

Related event: Multimodal AI Pathology Test Outperforms Gold Standard in Breast Cancer Recurrence Prediction(11 posts)→

Original post →

More from Research

Research channel →