Knowledge-enhanced Visual-Language Pretraining for Computational Pathology
This work addresses the problem of limited annotated data in computational pathology for researchers and clinicians, though it is incremental as it builds on existing visual-language pretraining methods.
The paper tackles visual representation learning for computational pathology by developing a knowledge-enhanced visual-language pretraining approach that leverages a curated pathology knowledge tree with 50,470 attributes for 4,718 diseases. The method demonstrates significant performance improvements on downstream tasks like cross-modal retrieval and zero-shot classification on pathology patches and whole slide images.
In this paper, we consider the problem of visual representation learning for computational pathology, by exploiting large-scale image-text pairs gathered from public resources, along with the domain-specific knowledge in pathology. Specifically, we make the following contributions: (i) We curate a pathology knowledge tree that consists of 50,470 informative attributes for 4,718 diseases requiring pathology diagnosis from 32 human tissues. To our knowledge, this is the first comprehensive structured pathology knowledge base; (ii) We develop a knowledge-enhanced visual-language pretraining approach, where we first project pathology-specific knowledge into latent embedding space via a language model, and use it to guide the visual representation learning; (iii) We conduct thorough experiments to validate the effectiveness of our proposed components, demonstrating significant performance improvement on various downstream tasks, including cross-modal retrieval, zero-shot classification on pathology patches, and zero-shot tumor subtyping on whole slide images (WSIs).