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

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Brussee, Siemen, Valkema, Pieter A., Weijer, Jurre A. J., Doeleman, Thom, Schrader, Anne M. R., Kers, Jesper
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866918256210608128
author Brussee, Siemen
Valkema, Pieter A.
Weijer, Jurre A. J.
Doeleman, Thom
Schrader, Anne M. R.
Kers, Jesper
author_facet Brussee, Siemen
Valkema, Pieter A.
Weijer, Jurre A. J.
Doeleman, Thom
Schrader, Anne M. R.
Kers, Jesper
contents 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
format Preprint
id arxiv_https___arxiv_org_abs_2512_17517
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PathBench-MIL: A Comprehensive AutoML and Benchmarking Framework for Multiple Instance Learning in Histopathology
Brussee, Siemen
Valkema, Pieter A.
Weijer, Jurre A. J.
Doeleman, Thom
Schrader, Anne M. R.
Kers, Jesper
Computer Vision and Pattern Recognition
Machine Learning
Neural and Evolutionary Computing
Software Engineering
Tissues and Organs
I.4.10; I.5.1; I.5.2; I.2.5; I.2.8; I.6.5; I.6.4; J.3
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
title PathBench-MIL: A Comprehensive AutoML and Benchmarking Framework for Multiple Instance Learning in Histopathology
topic Computer Vision and Pattern Recognition
Machine Learning
Neural and Evolutionary Computing
Software Engineering
Tissues and Organs
I.4.10; I.5.1; I.5.2; I.2.5; I.2.8; I.6.5; I.6.4; J.3
url https://arxiv.org/abs/2512.17517