EUVIMEDEUVIMED entdecken
Crossref

Self-Supervised Representation Distribution Learning for Reliable Data Augmentation in Histopathology WSI Classification

Kunming Tang, Zhiguo Jiang, Kun Wu, Jun Shi, Fengying Xie, Wei Wang, Haibo Wu, Yushan Zheng

IEEE Transactions on Medical Imaging · 2025-01 · 44 (1) · 462-474

DOI: 10.1109/tmi.2024.3447672 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Medical Imaging, 2025-01. Verfasst von Kunming Tang und 7 weiteren Autor:innen. Hauptthemen laut MEDLINE: Supervised Machine Learning, Image Interpretation, Computer-Assisted, Histocytochemistry. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 57 Literaturangaben. Gefördert von: Beijing Natural Science Foundation, National Natural Science Foundation of China, Fundamental Research Funds for the Central Universities.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Multiple instance learning (MIL) based whole slide image (WSI) classification is often carried out on the representations of patches extracted from WSI with a pre-trained patch encoder. The performance of classification relies on both patch-level representation learning and MIL classifier training. Most MIL methods utilize a frozen model pre-trained on ImageNet or a model trained with self-supervised learning on histopathology image dataset to extract patch image representations and then fix these representations in the training of the MIL classifiers for efficiency consideration. However, the invariance of representations cannot meet the diversity requirement for training a robust MIL classifier, which has significantly limited the performance of the WSI classification. In this paper, we propose a Self-Supervised Representation Distribution Learning framework (SSRDL) for patch-level representation learning with an online representation sampling strategy (ORS) for both patch feature extraction and WSI-level data augmentation. The proposed method was evaluated on three datasets under three MIL frameworks. The experimental results have demonstrated that the proposed method achieves the best performance in histopathology image representation learning and data augmentation and outperforms state-of-the-art methods under different WSI classification frameworks. The code is available at https://github.com/lazytkm/SSRDL.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Supervised Machine LearningImage Interpretation, Computer-AssistedHistocytochemistryHumansAlgorithmsDatabases, Factual

Förderung

  • Beijing Natural Science Foundation
  • National Natural Science Foundation of China
  • Fundamental Research Funds for the Central Universities
  • Emergency Key Program of Guangzhou Laboratory
  • Joint Fund for Medical Artificial Intelligence
  • National Key Research and Development Program of China

Zitieren

APA

Tang, K., Jiang, Z., Wu, K., Shi, J., Xie, F., Wang, W., Wu, H., & Zheng, Y. (2025). Self-Supervised Representation Distribution Learning for Reliable Data Augmentation in Histopathology WSI Classification. IEEE Transactions on Medical Imaging, 44(1), 462-474. https://doi.org/10.1109/tmi.2024.3447672

Vancouver

Tang K, Jiang Z, Wu K, Shi J, Xie F, Wang W, et al. Self-Supervised Representation Distribution Learning for Reliable Data Augmentation in Histopathology WSI Classification. IEEE Transactions on Medical Imaging. 2025;44(1):462-474. doi:10.1109/tmi.2024.3447672

BibTeX
@article{Tang2025,
  author = {Tang, Kunming and Jiang, Zhiguo and Wu, Kun and Shi, Jun and Xie, Fengying and Wang, Wei and Wu, Haibo and Zheng, Yushan},
  title = {Self-Supervised Representation Distribution Learning for Reliable Data Augmentation in Histopathology WSI Classification},
  journal = {IEEE Transactions on Medical Imaging},
  year = {2025},
  volume = {44},
  number = {1},
  pages = {462--474},
  doi = {10.1109/tmi.2024.3447672}
}
Kostenlos starten →