VLEER: Vision and Language Embeddings for Explainable Whole Slide Image Representation
This work addresses the need for interpretable and effective WSI representations in computational pathology, though it is incremental as it applies existing vision-language models to a new scale (WSI) rather than introducing a new paradigm.
The authors tackled the problem of whole slide image (WSI) analysis in computational pathology by introducing VLEER, a method that leverages pre-trained vision-language models for representation, achieving better performance than conventional vision features on three datasets and offering interpretability through textual annotations.
Recent advances in vision-language models (VLMs) have shown remarkable potential in bridging visual and textual modalities. In computational pathology, domain-specific VLMs, which are pre-trained on extensive histopathology image-text datasets, have succeeded in various downstream tasks. However, existing research has primarily focused on the pre-training process and direct applications of VLMs on the patch level, leaving their great potential for whole slide image (WSI) applications unexplored. In this study, we hypothesize that pre-trained VLMs inherently capture informative and interpretable WSI representations through quantitative feature extraction. To validate this hypothesis, we introduce Vision and Language Embeddings for Explainable WSI Representation (VLEER), a novel method designed to leverage VLMs for WSI representation. We systematically evaluate VLEER on three pathological WSI datasets, proving its better performance in WSI analysis compared to conventional vision features. More importantly, VLEER offers the unique advantage of interpretability, enabling direct human-readable insights into the results by leveraging the textual modality for detailed pathology annotations, providing clear reasoning for WSI-level pathology downstream tasks.