Unlocking adaptive digital pathology through dynamic feature learning

TL;DR

This paper introduces PathFiT, a dynamic feature learning method that enhances the adaptability and performance of foundation models in digital pathology across diverse tasks and imaging modalities.

Contribution

PathFiT provides a plug-and-play solution for improving foundation models' flexibility and relevance in clinical pathology applications.

Findings

Achieved state-of-the-art results on 34 out of 35 tasks.

Significant performance improvements on 23 tasks.

Outperformed existing methods by 10.20% on specialized imaging tasks.

Abstract

Foundation models have revolutionized the paradigm of digital pathology, as they leverage general-purpose features to emulate real-world pathological practices, enabling the quantitative analysis of critical histological patterns and the dissection of cancer-specific signals. However, these static general features constrain the flexibility and pathological relevance in the ever-evolving needs of clinical applications, hindering the broad use of the current models. Here we introduce PathFiT, a dynamic feature learning method that can be effortlessly plugged into various pathology foundation models to unlock their adaptability. Meanwhile, PathFiT performs seamless implementation across diverse pathology applications regardless of downstream specificity. To validate PathFiT, we construct a digital pathology benchmark with over 20 terabytes of Internet and real-world data comprising 28 H\&E-stained tasks and 7 specialized imaging tasks including Masson's Trichrome staining and immunofluorescence images. By applying PathFiT to the representative pathology foundation models, we demonstrate state-of-the-art performance on 34 out of 35 tasks, with significant improvements on 23 tasks and outperforming by 10.20% on specialized imaging tasks. The superior performance and versatility of PathFiT open up new avenues in computational pathology.