Tissue Concepts v2: A Supervised Foundation Model For Whole Slide Images
This work addresses the high computational cost of training foundation models for pathologists, though it is incremental as it extends a previous supervised model to whole slide images.
The paper tackles the resource-intensive training of foundation models in computational pathology by introducing Tissue Concepts v2 (TCv2), a supervised foundation model for whole slide images that uses slide-level labels and multitask learning, achieving superior performance in cancer subtyping benchmarks with reduced training resources compared to self-supervised methods.
Foundation models (FMs) are transforming the field of computational pathology by offering new approaches to analyzing histopathology images. Typically relying on weeks of training on large databases, the creation of FMs is a resource-intensive process in many ways. In this paper, we introduce the extension of our supervised foundation model, Tissue Concepts, to whole slide images, called Tissue Concepts v2 (TCv2), a supervised foundation model for whole slide images to address the issue above. TCv2 uses supervised, end-to-end multitask learning on slide-level labels. Training TCv2 uses a fraction of the training resources compared to self-supervised training. The presented model shows superior performance compared to SSL-trained models in cancer subtyping benchmarks and is fully trained on freely available data. Furthermore, a shared trained attention module provides an additional layer of explainability across different tasks.