A Survey of Pathology Foundation Model: Progress and Future Directions

TL;DR

This survey reviews recent advances in Pathology Foundation Models, categorizing their development and evaluation, and discusses challenges and future directions for automated cancer diagnosis using histopathology images.

Contribution

It introduces a hierarchical taxonomy for PFMs and systematically categorizes evaluation tasks, providing a comprehensive framework for analysis and benchmarking.

Findings

PFMs significantly improve feature extraction and aggregation in computational pathology.

Identification of key challenges like data scalability and model adaptation.

Provision of a structured taxonomy and benchmarking criteria for future research.

Abstract

Computational pathology, which involves analyzing whole slide images for automated cancer diagnosis, relies on multiple instance learning, where performance depends heavily on the feature extractor and aggregator. Recent Pathology Foundation Models (PFMs), pretrained on large-scale histopathology data, have significantly enhanced both the extractor and aggregator, but they lack a systematic analysis framework. In this survey, we present a hierarchical taxonomy organizing PFMs through a top-down philosophy applicable to foundation model analysis in any domain: model scope, model pretraining, and model design. Additionally, we systematically categorize PFM evaluation tasks into slide-level, patch-level, multimodal, and biological tasks, providing comprehensive benchmarking criteria. Our analysis identifies critical challenges in both PFM development (pathology-specific methodology, end-to-end pretraining, data-model scalability) and utilization (effective adaptation, model maintenance), paving the way for future directions in this promising field. Resources referenced in this survey are available at https://github.com/BearCleverProud/AwesomeWSI.