Accelerating Data Processing and Benchmarking of AI Models for Pathology

TL;DR

This paper introduces software tools for processing, benchmarking, and evaluating AI models in pathology, aiming to enhance transparency, reproducibility, and progress in the field.

Contribution

It presents a new suite of tools for whole-slide image processing and benchmarking of foundation models in computational pathology.

Findings

Enhanced transparency and reproducibility in pathology AI models

Curated publicly available tasks for benchmarking

Facilitated progress in computational pathology

Abstract

Advances in foundation modeling have reshaped computational pathology. However, the increasing number of available models and lack of standardized benchmarks make it increasingly complex to assess their strengths, limitations, and potential for further development. To address these challenges, we introduce a new suite of software tools for whole-slide image processing, foundation model benchmarking, and curated publicly available tasks. We anticipate that these resources will promote transparency, reproducibility, and continued progress in the field.