EUVIMEDEUVIMED entdecken
Crossref

Imbalanced Multiclassification Challenges in Whole Slide Image: Cross-Patient Pseudo Bags Generation and Curriculum Contrastive Learning With Dynamic Rebalancing

Yonghuang Wu, Xuan Xie, Chengqian Zhao, Pengfei Song, Feiyu Yin, Guoqing Wu, Jinhua Yu

IEEE Transactions on Image Processing · 2026

DOI: 10.1109/tip.2026.3654402 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2026. Verfasst von Yonghuang Wu und 6 weiteren Autor:innen. Hauptthemen laut MEDLINE: Image Interpretation, Computer-Assisted, Histocytochemistry, Machine Learning. Die Arbeit nennt 44 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National natural science foundation of China, Shanghai Science and Technology Commission Explorer Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The multi-classification of histopathological images under imbalanced sample conditions remains a long-standing unresolved challenge in computational pathology. In this paper, we propose for the first time a cross-patient pseudo-bag generation technique to address this challenge. Our key innovation lies in a cross-patient pseudo-bag generation framework that extracts complementary pathological features to construct distributionally consistent pseudo-bags. To resolve the critical challenge of distributional alignment in pseudo-bag generation, we propose an affinity-driven curriculum contrastive learning strategy, integrating sample affinity metrics with progressive training to stabilize representation learning. Unlike prior methods focused on bag-level embeddings, our framework pioneers a paradigm shift toward multi-instance feature distribution mining, explicitly modeling inter-bag heterogeneity to address class imbalance. Our method demonstrates significant performance improvements on three datasets with multiple classification difficulties, outperforming the second-best method by an average of 1.95 percentage points in F1 score and 2.07 percentage points in ACC.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Image Interpretation, Computer-AssistedHistocytochemistryMachine LearningHumansClassification AlgorithmsAlgorithmsRepresentation Machine LearningDatabases, Factual

Förderung

  • National Key Research and Development Program of China
  • National natural science foundation of China
  • Shanghai Science and Technology Commission Explorer Project
  • AI for Science Foundation of Fudan University

Zitieren

APA

Wu, Y., Xie, X., Zhao, C., Song, P., Yin, F., Wu, G., & Yu, J. (2026). Imbalanced Multiclassification Challenges in Whole Slide Image: Cross-Patient Pseudo Bags Generation and Curriculum Contrastive Learning With Dynamic Rebalancing. IEEE Transactions on Image Processing. https://doi.org/10.1109/tip.2026.3654402

Vancouver

Wu Y, Xie X, Zhao C, Song P, Yin F, Wu G, et al. Imbalanced Multiclassification Challenges in Whole Slide Image: Cross-Patient Pseudo Bags Generation and Curriculum Contrastive Learning With Dynamic Rebalancing. IEEE Transactions on Image Processing. 2026. doi:10.1109/tip.2026.3654402

BibTeX
@article{Wu2026,
  author = {Wu, Yonghuang and Xie, Xuan and Zhao, Chengqian and Song, Pengfei and Yin, Feiyu and Wu, Guoqing and Yu, Jinhua},
  title = {Imbalanced Multiclassification Challenges in Whole Slide Image: Cross-Patient Pseudo Bags Generation and Curriculum Contrastive Learning With Dynamic Rebalancing},
  journal = {IEEE Transactions on Image Processing},
  year = {2026},
  doi = {10.1109/tip.2026.3654402}
}
Kostenlos starten →