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

Siemen Brussee, Pieter A. Valkema, Jurre A. J. Weijer, Thom Doeleman, Anne M. R. Schrader +1 more
12/19/2025
cs.CVcs.LGcs.NE

Official code: Sbrussee/PathBench-MIL (29 stars, GPL-3.0, last commit 2026-01-09).

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

View on arXivView PDF

Code Implementations(1)

Sbrussee/PathBench-MILOfficial100%
GPL-3.0

PathBench-MIL: A comprehensive, flexible Benchmarking / AutoML framework for multiple instance learning in Histopathology

296Shell, PythonApr 18, 20249 months agoGPL-3.0
automated-machine-learningautomlbenchmarkbenchmarkingcomputational-pathology+4 more

Similar Papers

xMIL: Insightful Explanations for Multiple Instance Learning in Histopathology

82% match1 repo402024

Towards a Visual-Language Foundation Model for Computational Pathology

79% match2023

HistGen: Histopathology Report Generation via Local-Global Feature Encoding and Cross-modal Context Interaction

79% match1 repo852024

torchmil: A PyTorch-based library for deep Multiple Instance Learning

78% match1 repo902025

Quilt-LLaVA: Visual Instruction Tuning by Extracting Localized Narratives from Open-Source Histopathology Videos

78% match2023

Pathology-knowledge Enhanced Multi-instance Prompt Learning for Few-shot Whole Slide Image Classification

78% match2024

Cite this paper

@article{brussee2025pathbenchmil,
  title  = {PathBench-MIL: A Comprehensive AutoML and Benchmarking Framework for Multiple Instance Learning in Histopathology},
  author = {Siemen Brussee and Pieter A. Valkema and Jurre A. J. Weijer and Thom Doeleman and Anne M. R. Schrader and Jesper Kers},
  year   = {2025},
  eprint = {2512.17517},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2512.17517v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2512.17517.svg)](https://codeofpaper.com/paper/2512.17517)

Discussion