EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Instance causal multiple instance learning for whole slide image classification

Haixing Li, Chao Weng iD, Wanying Huang, Ming Xu

PLOS One · 11.11.2026 · 21 (11) · e0362621

DOI: 10.1371/journal.pone.0362621 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 11.11.2026. Verfasst von Haixing Li und 3 weiteren Autor:innen. Beteiligte Einrichtung: Shenyang University of Technology, Shenyang, China. Hauptthemen laut MEDLINE: Image Processing, Computer-Assisted. Die Arbeit nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Liaoning Provincial Postdoctoral Science Foundation, University of Science and Technology Liaoning, Department of Education of Liaoning Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Whole slide images (WSIs) are characterized by extremely high resolution and usually lack fine-grained annotations, making multiple instance learning (MIL) the dominant paradigm for weakly supervised WSI classification. Although existing MIL methods have achieved substantial progress in feature extraction and instance aggregation, most of them overlook the influence of confounding factors, thereby learning spurious associations that impair generalization performance. To address this issue, we develop an Instance Causal Multiple Instance Learning (ICMIL) framework for WSI classification, which aims to reduce the model’s reliance on potentially spurious instance-level associations. Specifically, unlike conventional likelihood-based strategies, the proposed method introduces a backdoor-adjustment-inspired prototype module during instance aggregation, where clustered prototypes are used as proxy contextual patterns to mitigate the influence of potential confounding cues. We conduct extensive experiments on two publicly available WSI datasets, Camelyon16 and TCGA-NSCLC. The results demonstrate that the proposed ICMIL framework achieves competitive performance and generally improves existing baselines, while also exhibiting a plug-and-play property.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Image Processing, Computer-AssistedMultiple-Instance Learning AlgorithmsHumansClassification Algorithms

Autor:innen und Institutionen

  • Shenyang University of Technology, Shenyang, China.
  • Shengjing Hospital of China Medical University, Shenyang, China.

ORCID-Profile: Chao Weng

Förderung

  • Liaoning Provincial Postdoctoral Science Foundation
  • University of Science and Technology Liaoning
  • Department of Education of Liaoning Province

Zitieren

APA

Li, H., Weng, C., Huang, W., & Xu, M. (2026). Instance causal multiple instance learning for whole slide image classification. PLOS One, 21(11), e0362621. https://doi.org/10.1371/journal.pone.0362621

Vancouver

Li H, Weng C, Huang W, Xu M. Instance causal multiple instance learning for whole slide image classification. PLOS One. 2026;21(11):e0362621. doi:10.1371/journal.pone.0362621

BibTeX
@article{Li2026,
  author = {Li, Haixing and Weng, Chao and Huang, Wanying and Xu, Ming},
  title = {Instance causal multiple instance learning for whole slide image classification},
  journal = {PLOS One},
  year = {2026},
  volume = {21},
  number = {11},
  pages = {e0362621},
  doi = {10.1371/journal.pone.0362621}
}
Kostenlos starten →