TICON: A Slide-Level Tile Contextualizer for Histopathology Representation Learning

TL;DR

TICON is a transformer-based model that contextualizes tile embeddings in histopathology images, significantly improving performance on various tasks and establishing new state-of-the-art results with fewer training data.

Contribution

Introduces TICON, a unified transformer-based model that contextualizes tile embeddings for diverse pathology tasks, outperforming existing models and reducing data requirements.

Findings

TICON achieves state-of-the-art results on multiple benchmarks.

Contextualized embeddings improve task performance.

Pretraining on fewer slides outperforms larger models.

Abstract

The interpretation of small tiles in large whole slide images (WSI) often needs a larger image context. We introduce TICON, a transformer-based tile representation contextualizer that produces rich, contextualized embeddings for ''any'' application in computational pathology. Standard tile encoder-based pipelines, which extract embeddings of tiles stripped from their context, fail to model the rich slide-level information essential for both local and global tasks. Furthermore, different tile-encoders excel at different downstream tasks. Therefore, a unified model is needed to contextualize embeddings derived from ''any'' tile-level foundation model. TICON addresses this need with a single, shared encoder, pretrained using a masked modeling objective to simultaneously unify and contextualize representations from diverse tile-level pathology foundation models. Our experiments demonstrate that TICON-contextualized embeddings significantly improve performance across many different tasks, establishing new state-of-the-art results on tile-level benchmarks (i.e., HEST-Bench, THUNDER, CATCH) and slide-level benchmarks (i.e., Patho-Bench). Finally, we pretrain an aggregator on TICON to form a slide-level foundation model, using only 11K WSIs, outperforming SoTA slide-level foundation models pretrained with up to 350K WSIs.