Knowledge-enhanced pretraining for vision-language pathology foundation model on cancer diagnosis

Vision-language foundation models have shown great promise in computational pathology but remain primarily data-driven, lacking explicit integration of medical knowledge. We introduce K nowledg E - E nhanced P athology ( KEEP ), a foundation model that systematically incorporates disease knowledge into pretraining for cancer diagnosis. KEEP leverages a comprehensive disease knowledge graph encompassing 11,454 diseases and 139,143 attributes to reorganize millions of pathology image-text pairs into 143,000 semantically structured groups aligned with disease ontology hierarchies. This knowledge-enhanced pretraining aligns visual and textual representations within hierarchical semantic spaces, enabling a deeper understanding of disease relationships and morphological patterns. Across 18 public benchmarks (over 14,000 whole-slide images) and 4 institutional rare cancer datasets (926 cases), KEEP consistently outperformed existing foundation models, showing substantial gains for rare subtypes. These results establish knowledge-enhanced vision-language modeling as a powerful paradigm for advancing computational pathology. • KEEP, a foundation model fusing disease knowledge into pretraining for cancer diagnosis • Hierarchical disease knowledge enhances pathology vision-language pretraining • Knowledge injection improves cancer segmentation, detection, and subtyping • Knowledge integration promotes rare cancer diagnosis and generalization Zhou et al. Develop KEEP, a knowledge-enhanced foundation model that integrates disease knowledge into pathology vision-language pretraining. By combining medical knowledge with large-scale image-text data, the approach improves diagnostic accuracy and generalization, particularly for rare cancers, highlighting how knowledge integration advances computational pathology and AI-driven cancer diagnosis.