A

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

arXiv (Cornell University)

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

Authors 6

  1. Leiden University Medical Center

    Affiliation as printed

    Department of Pathology , Leiden University Medical Center

  2. Leiden University Medical Center

    Affiliation as printed

    Department of Pathology , Leiden University Medical Center

  3. Leiden University Medical Center

    Affiliation as printed

    Department of Pathology , Leiden University Medical Center

  4. Leiden University Medical Center · University Medical Center Utrecht

    Affiliation as printed

    Department of Pathology , Leiden University Medical Center

    Department of Pathology , Utrecht University Medical Center

  5. Leiden University Medical Center

    Affiliation as printed

    Department of Pathology , Leiden University Medical Center

  6. Leiden University Medical Center · Amsterdam UMC Location University of Amsterdam · Amsterdam University Medical Centers

    Affiliation as printed

    Department of Pathology , Amsterdam University Medical Center 19-12 -2025

    Department of Pathology , Leiden University Medical Center

Cited by 1 stored of 1

1 result

References 4

4 results