PathBench-MIL: A Comprehensive AutoML and Benchmarking Framework for Multiple Instance Learning in Histopathology

TL;DR

PathBench-MIL is an open-source AutoML framework that automates and benchmarks multiple instance learning pipelines in histopathology, facilitating reproducible and rapid experimentation.

Contribution

It introduces a comprehensive, modular AutoML and benchmarking framework specifically designed for MIL in histopathology, integrating visualization and standardization tools.

Findings

Automates end-to-end MIL pipeline construction

Provides reproducible benchmarking of numerous MIL models

Enables rapid experimentation and standardization

Abstract

We introduce PathBench-MIL, an open-source AutoML and benchmarking framework for multiple instance learning (MIL) in histopathology. The system automates end-to-end MIL pipeline construction, including preprocessing, feature extraction, and MIL-aggregation, and provides reproducible benchmarking of dozens of MIL models and feature extractors. PathBench-MIL integrates visualization tooling, a unified configuration system, and modular extensibility, enabling rapid experimentation and standardization across datasets and tasks. PathBench-MIL is publicly available at https://github.com/Sbrussee/PathBench-MIL