EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

A deep active learning framework for mitotic figure detection with minimal manual annotation and labelling

Eric Liu iD, August Lin, Pramath Kakodkar, Yayuan Zhao, Boyu Wang, Charles Ling, Qi Zhang iD

Histopathology · 2025-10 · 87 (4) · 536-547

DOI: 10.1111/his.15506 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Histopathology, online erschienen am 03.07.2025. Verfasst von Eric Liu und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, Western University, London, Ontario, Canada. Hauptthemen laut MEDLINE: Deep Learning, Brain Neoplasms, Glioblastoma, Mitosis. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 20 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Western Dean's Office Research Opportunities Fellowship, Pathology Internal Funds for Academic Development (PIFAD) of Western University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Aims

Accurately and efficiently identifying mitotic figures (MFs) is crucial for diagnosing and grading various cancers, including glioblastoma (GBM), a highly aggressive brain tumour requiring precise and timely intervention. Traditional manual counting of MFs in whole slide images (WSIs) is labour‐intensive and prone to interobserver variability. Our study introduces a deep active learning framework that addresses these challenges with minimal human intervention. Methods and results We utilized a dataset of GBM WSIs from The Cancer Genome Atlas (TCGA). Our framework integrates convolutional neural networks (CNNs) with an active learning strategy. Initially, a CNN is trained on a small, annotated dataset. The framework then identifies uncertain samples from the unlabelled data pool, which are subsequently reviewed by experts. These ambiguous cases are verified and used for model retraining. This iterative process continues until the model achieves satisfactory performance. Our approach achieved 81.75% precision and 82.48% recall for MF detection. For MF subclass classification, it attained an accuracy of 84.1%. Furthermore, this approach significantly reduced annotation time ‐ approximately 900 min across 66 WSIs ‐ cutting the effort nearly in half compared to traditional methods.

Conclusions

Our deep active learning framework demonstrates a substantial improvement in both efficiency and accuracy for MF detection and classification in GBM WSIs. By reducing reliance on large annotated datasets, it minimizes manual effort while maintaining high performance. This methodology can be generalized to other medical imaging tasks, supporting broader applications in the healthcare domain.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningBrain NeoplasmsGlioblastomaMitosisHumansNeural Networks, Computer

Stichwörter der Autor:innen

active learningdeep learningdigital pathologyglioblastomamitotic figures

Autor:innen und Institutionen

  • Department of Computer Science, Western University, London, Ontario, Canada.
  • Department of Pathology and Lab Medicine, Western University, London, Ontario, Canada.
  • Department of Pathology and Lab Medicine, University of Saskatchewan, Saskatoon, Saskatchewan, Canada.

ORCID-Profile: Eric Liu, Qi Zhang

Förderung

  • Western Dean's Office Research Opportunities Fellowship
  • Pathology Internal Funds for Academic Development (PIFAD) of Western University

Zitieren

APA

Liu, E., Lin, A., Kakodkar, P., Zhao, Y., Wang, B., Ling, C., & Zhang, Q. (2025). A deep active learning framework for mitotic figure detection with minimal manual annotation and labelling. Histopathology, 87(4), 536-547. https://doi.org/10.1111/his.15506

Vancouver

Liu E, Lin A, Kakodkar P, Zhao Y, Wang B, Ling C, et al. A deep active learning framework for mitotic figure detection with minimal manual annotation and labelling. Histopathology. 2025;87(4):536-547. doi:10.1111/his.15506

BibTeX
@article{Liu2025,
  author = {Liu, Eric and Lin, August and Kakodkar, Pramath and Zhao, Yayuan and Wang, Boyu and Ling, Charles and Zhang, Qi},
  title = {A deep active learning framework for mitotic figure detection with minimal manual annotation and labelling},
  journal = {Histopathology},
  year = {2025},
  volume = {87},
  number = {4},
  pages = {536--547},
  doi = {10.1111/his.15506}
}
Kostenlos starten →