Benchmarking Embedding Aggregation Methods in Computational Pathology: A Clinical Data Perspective

TL;DR

This paper benchmarks ten slide-level aggregation methods for digital pathology images across nine clinical tasks, revealing the superiority of domain-specific embeddings and highlighting the need for adaptable aggregation techniques.

Contribution

It provides a comprehensive comparison of aggregation methods in computational pathology, emphasizing the importance of domain-specific models and spatial-aware techniques.

Findings

Domain-specific FMs outperform ImageNet models.

Spatial-aware aggregators improve ImageNet-based models.

No single model is best for all tasks.

Abstract

Recent advances in artificial intelligence (AI), in particular self-supervised learning of foundation models (FMs), are revolutionizing medical imaging and computational pathology (CPath). A constant challenge in the analysis of digital Whole Slide Images (WSIs) is the problem of aggregating tens of thousands of tile-level image embeddings to a slide-level representation. Due to the prevalent use of datasets created for genomic research, such as TCGA, for method development, the performance of these techniques on diagnostic slides from clinical practice has been inadequately explored. This study conducts a thorough benchmarking analysis of ten slide-level aggregation techniques across nine clinically relevant tasks, including diagnostic assessment, biomarker classification, and outcome prediction. The results yield following key insights: (1) Embeddings derived from domain-specific (histological images) FMs outperform those from generic ImageNet-based models across aggregation methods. (2) Spatial-aware aggregators enhance the performance significantly when using ImageNet pre-trained models but not when using FMs. (3) No single model excels in all tasks and spatially-aware models do not show general superiority as it would be expected. These findings underscore the need for more adaptable and universally applicable aggregation techniques, guiding future research towards tools that better meet the evolving needs of clinical-AI in pathology. The code used in this work is available at \url{https://github.com/fuchs-lab-public/CPath_SABenchmark}.