EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Beyond accuracy: Quantifying the reliability of multiple instance learning for whole slide image classification

Hassan Keshvarikhojasteh iD, Marc Aubreville, Christof A Bertram, Josien P W Pluim, Mitko Veta

PLOS One · 2025

DOI: 10.1371/journal.pone.0337261 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, 2025. Verfasst von Hassan Keshvarikhojasteh und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biomedical Engineering, Eindhoven University of Technology, Eindhoven, The Netherlands. Hauptthemen laut MEDLINE: Machine Learning, Image Processing, Computer-Assisted. Die Arbeit nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: BigPicture.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Machine learning models have become integral to many fields, but their reliability, defined as producing dependable, trustworthy, and domain-consistent predictions, remains a critical concern. Multiple Instance Learning (MIL) models designed for Whole Slide Image (WSI) classification in computational pathology are rarely evaluated in terms of reliability, leaving a key gap in understanding their suitability for high-stakes applications like clinical decision-making. In this paper, we address this gap by introducing three quantitative metrics for reliability assessment and applying them to several widely used MIL architectures across three region-wise annotated pathology datasets. Our findings indicate that the mean pooling instance (MEAN-POOL-INS) model demonstrates superior reliability compared to other networks, despite its simple architectural design and computational efficiency. These findings underscore the need of reliability evaluation alongside predictive performance in MIL models and establish MEAN-POOL-INS as a strong, trustworthy baseline for future research.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningImage Processing, Computer-AssistedHumansReproducibility of ResultsMultiple-Instance Learning Algorithms

Autor:innen und Institutionen

  • Department of Biomedical Engineering, Eindhoven University of Technology, Eindhoven, The Netherlands.
  • Flensburg Artificial Intelligence Research Group (FLAIR), Flensburg University of Applied Sciences, Flensburg, Germany.
  • University of Veterinary Medicine Vienna, Vienna, Austria.

ORCID-Profile: Hassan Keshvarikhojasteh

Förderung

  • BigPicture

Zitieren

APA

Keshvarikhojasteh, H., Aubreville, M., Bertram, C. A., Pluim, J. P. W., & Veta, M. (2025). Beyond accuracy: Quantifying the reliability of multiple instance learning for whole slide image classification. PLOS One. https://doi.org/10.1371/journal.pone.0337261

Vancouver

Keshvarikhojasteh H, Aubreville M, Bertram CA, Pluim JPW, Veta M. Beyond accuracy: Quantifying the reliability of multiple instance learning for whole slide image classification. PLOS One. 2025. doi:10.1371/journal.pone.0337261

BibTeX
@article{Keshvarikhojasteh2025,
  author = {Keshvarikhojasteh, Hassan and Aubreville, Marc and Bertram, Christof A and Pluim, Josien P W and Veta, Mitko},
  title = {Beyond accuracy: Quantifying the reliability of multiple instance learning for whole slide image classification},
  journal = {PLOS One},
  year = {2025},
  doi = {10.1371/journal.pone.0337261}
}
Kostenlos starten →