EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Continual Learning for Histopathology Image Classification in Class-Incremental Learning

Yuanyuan Wu iD, Yu Zhao, Anca Ralescu

Diagnostics · 02.06.2026 · 16 (11) · 1711

DOI: 10.3390/diagnostics16111711 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Diagnostics, online erschienen am 02.06.2026. Verfasst von Yuanyuan Wu und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, University of Cincinnati, 2901 Woodside Drive, Cincinnati, OH 45221, USA. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 76 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Continual learning (CL) is increasingly important for developing adaptive clinical AI models; however, its application to histopathology remains challenging due to privacy constraints, expanding diagnostic categories, and staining variability. We investigate CL for histopathology image classification under a class-incremental learning (CIL) scenario, where new diagnostic categories are introduced sequentially.

Methods

We benchmark representative regularization-, replay-, architecture-, and prompt-based CL methods on the NCT-CRC-HE-100K dataset, with additional validation on CRC-HE-7K. We compare four normalization strategies and analyze the effects of replay buffer size and training epochs. In addition to average accuracy and forgetting, we conduct clinical relevance and error analysis using confusion matrices, ROC curves, and misclassification cases, then assess training dynamics and computational efficiency.

Results

Dataset-level normalization consistently achieves the best performance among the evaluated normalization strategies. Among replay-based methods, DER++ achieves strong performance when previous-task images can be stored and replayed, reaching an average accuracy of 94.77±1.82 and forgetting of 3.66±1.73 with a buffer size of 500 and 50 training epochs. However, it requires higher memory usage, longer training time, and storage of previous samples. Among prompt-based methods, DualPrompt performs best with 5 epochs, reaching an average accuracy of 88.97±0.60 and forgetting of 7.70±1.21 while showing smoother training behavior and lower computational cost.

Conclusions

Replay-based methods achieve higher accuracy and lower forgetting when exemplar storage and sufficient computational resources are available, but introduce higher computational and privacy costs. Prompt-based methods provide a competitive exemplar-free alternative under privacy- and resource-constrained settings. Dataset-level normalization is also important for stable CL performance in histopathology CIL.

Schlagwörter

Stichwörter der Autor:innen

catastrophic forgettingclass-incremental learningcontinual learningdigital pathologyhistopathologyprompt-based learning

Autor:innen und Institutionen

  • Department of Computer Science, University of Cincinnati, 2901 Woodside Drive, Cincinnati, OH 45221, USA.

ORCID-Profile: Yuanyuan Wu

Zitieren

APA

Wu, Y., Zhao, Y., & Ralescu, A. (2026). Continual Learning for Histopathology Image Classification in Class-Incremental Learning. Diagnostics, 16(11), 1711. https://doi.org/10.3390/diagnostics16111711

Vancouver

Wu Y, Zhao Y, Ralescu A. Continual Learning for Histopathology Image Classification in Class-Incremental Learning. Diagnostics. 2026;16(11):1711. doi:10.3390/diagnostics16111711

BibTeX
@article{Wu2026,
  author = {Wu, Yuanyuan and Zhao, Yu and Ralescu, Anca},
  title = {Continual Learning for Histopathology Image Classification in Class-Incremental Learning},
  journal = {Diagnostics},
  year = {2026},
  volume = {16},
  number = {11},
  pages = {1711},
  doi = {10.3390/diagnostics16111711}
}
Kostenlos starten →