EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Classifying the AMi-Br Mitotic Figure Dataset with AUCMEDI

Daniel Hieber, Friederike Liesche-Starnecker, Johannes Schobel, Rüdiger Pryss, Frank Kramer, Dominik Müller

Studies in Health Technology and Informatics · 2025

DOI: 10.3233/shti251413 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Studies in Health Technology and Informatics, 2025. Verfasst von Daniel Hieber und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Neuropathology, Pathology, Medical Faculty, University of Augsburg. Hauptthemen laut MEDLINE: Breast Neoplasms, Mitosis, Deep Learning, Mitotic Index. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

Mitotic figure (MF) density has been established as a key biomarker for certain tumors. Recently, the differentiation between atypical MFs (AMF) and normal MFs (NMFs) has gained increased interest in research, as AMFs density could be an independent biomarker. This results in the challenge of finding an automated, deterministic way to differentiate between AMFs and NMFs.

Methods

In this study, the AUCMEDI deep learning framework is applied to the recently published AMi-Br dataset to get a first bearing on the complexity of the task at hand. The dataset includes eight mitotic subclasses derived from breast cancer samples, four for NMFs and four for AMF. Using a patient-level cross-validation strategy and a ConvNeXt-based ensemble, we trained and evaluated an eight-class subtype classification model.

Results

Our results show high specificity across all classes (≥ 90%), but sensitivity varies significantly between mitotic subclasses (0–82%), reflecting the dataset’s inherent challenges. The mean AUC of 85.90% outperforms the binary classification baseline (69.8%).

Conclusion

The results highlight the promise of progress in subclass-level mitotic analysis while pointing to areas for further model refinement.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Breast NeoplasmsMitosisDeep LearningMitotic IndexHumansFemaleArea Under Curve

Stichwörter der Autor:innen

Atypical Mitotic FiguresClassificationComputational PathologyComputer VisionDeep Learning

Autor:innen und Institutionen

  • Department of Neuropathology, Pathology, Medical Faculty, University of Augsburg.
  • DigiHealth Institute, Neu-Ulm University of Applied Sciences.
  • Institute of Medical Data Science, University Hospital of Würzburg.
  • Faculty of Applied Computer Science, University of Augsburg.
  • Institute for Digital Medicine, University Hospital Augsburg.

Zitieren

APA

Hieber, D., Liesche-Starnecker, F., Schobel, J., Pryss, R., Kramer, F., & Müller, D. (2025). Classifying the AMi-Br Mitotic Figure Dataset with AUCMEDI. Studies in Health Technology and Informatics. https://doi.org/10.3233/shti251413

Vancouver

Hieber D, Liesche-Starnecker F, Schobel J, Pryss R, Kramer F, Müller D. Classifying the AMi-Br Mitotic Figure Dataset with AUCMEDI. Studies in Health Technology and Informatics. 2025. doi:10.3233/shti251413

BibTeX
@article{Hieber2025,
  author = {Hieber, Daniel and Liesche-Starnecker, Friederike and Schobel, Johannes and Pryss, Rüdiger and Kramer, Frank and Müller, Dominik},
  title = {Classifying the AMi-Br Mitotic Figure Dataset with AUCMEDI},
  journal = {Studies in Health Technology and Informatics},
  year = {2025},
  doi = {10.3233/shti251413}
}
Kostenlos starten →