<ul><li>Foundation models pretrained on large-scale datasets are revolutionizing the field of computational pathology (CPath).</li><li>Existing foundation models excel at certain clinical task types but struggle to handle the full breadth of tasks in the field.</li><li>To improve the generalization of pathology foundation models, a unified knowledge distillation framework is proposed, combining expert and self-knowledge distillation.</li><li>The Generalizable Pathology Foundation Model (GPFM) achieved an impressive average rank of 1.6 in six distinct clinical task types.</li></ul>

Towards A Generalizable Pathology Foundation Model via Unified Knowledge Distillation

Discover more