EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

NucFuseRank: Dataset Fusion and Performance Ranking for Nuclei Instance Segmentation

Nima Torbati iD, Anastasia Meshcheryakova iD, Ramona Woitek iD, Sepideh Hatamikia iD, Diana Mechtcheriakova iD, Amirreza Mahbod iD

Bioengineering · 31.07.2026 · 13 (8) · 886

DOI: 10.3390/bioengineering13080886 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioengineering, online erschienen am 31.07.2026. Verfasst von Nima Torbati und 5 weiteren Autor:innen. Beteiligte Einrichtung: Research Center for Medical Image Analysis and Artificial Intelligence, Department of Medicine, Faculty of Medicine and Dentistry, Danube Private Uni…. Die Arbeit nennt 61 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Vienna Science and Technology Fund (WWTF) and the State of Lower Austria, Vienna Science and Technology Fund, State of Lower Austria.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Nuclei instance segmentation in hematoxylin and eosin (H&E)-stained images plays an important role in automated histological image analysis, with various applications in downstream tasks. While several machine learning and deep learning approaches have been proposed for nuclei instance segmentation, most research in this field focuses on developing new segmentation algorithms and benchmarking them on a limited number of arbitrarily selected public datasets. In this work, rather than focusing on model development, we focused on the datasets used for this task. Based on an extensive literature review, we identified manually annotated, publicly available datasets of H&E-stained images for nuclei instance segmentation and standardized them into a unified input and annotation format. Using two state-of-the-art segmentation models, one based on convolutional neural networks (CNNs) and one based on a hybrid CNN and vision transformer architecture, we systematically evaluated and ranked these datasets based on their nuclei instance segmentation performance. Furthermore, we proposed a unified test set (NucFuse-test) for fair cross-dataset evaluation and a unified training set (NucFuse-train) for improved segmentation performance by merging images from multiple datasets. To the best of our knowledge, this is the first study to systematically benchmark and rank publicly available datasets for nuclei instance segmentation. By evaluating and ranking the datasets, performing comprehensive analyses, generating fused datasets, conducting external validation, and making our implementation publicly available, we provided a new protocol for training, testing, and evaluating nuclei instance segmentation models on H&E-stained histological images.

Schlagwörter

Stichwörter der Autor:innen

H&E-stained imagescomputational pathologydataset rankingdeep learningmedical image analysisnuclei instance segmentation

Autor:innen und Institutionen

  • Research Center for Medical Image Analysis and Artificial Intelligence, Department of Medicine, Faculty of Medicine and Dentistry, Danube Private University, 3500 Krems an der Donau, Austria.
  • Department of Pathophysiology and Allergy Research, Center of Pathophysiology, Infectiology and Immunology, Medical University of Vienna, 1090 Vienna, Austria.
  • Comprehensive Center for AI in Medicine (CAIM), Medical University of Vienna, 1090 Vienna, Austria.
  • Research Center for Medical Data Sciences and Artificial Intelligence (MeDSAI), Department of Medicine, Faculty of Medicine and Dentistry, Danube Private University, 3500 Krems an der Donau, Austria.
  • Austrian Center for Medical Innovation and Technology, 2700 Wiener Neustadt, Austria.

ORCID-Profile: Nima Torbati, Anastasia Meshcheryakova, Ramona Woitek, Sepideh Hatamikia, Diana Mechtcheriakova, Amirreza Mahbod

Förderung

  • Vienna Science and Technology Fund (WWTF) and the State of Lower Austria
  • Vienna Science and Technology Fund
  • State of Lower Austria

Zitieren

APA

Torbati, N., Meshcheryakova, A., Woitek, R., Hatamikia, S., Mechtcheriakova, D., & Mahbod, A. (2026). NucFuseRank: Dataset Fusion and Performance Ranking for Nuclei Instance Segmentation. Bioengineering, 13(8), 886. https://doi.org/10.3390/bioengineering13080886

Vancouver

Torbati N, Meshcheryakova A, Woitek R, Hatamikia S, Mechtcheriakova D, Mahbod A. NucFuseRank: Dataset Fusion and Performance Ranking for Nuclei Instance Segmentation. Bioengineering. 2026;13(8):886. doi:10.3390/bioengineering13080886

BibTeX
@article{Torbati2026,
  author = {Torbati, Nima and Meshcheryakova, Anastasia and Woitek, Ramona and Hatamikia, Sepideh and Mechtcheriakova, Diana and Mahbod, Amirreza},
  title = {NucFuseRank: Dataset Fusion and Performance Ranking for Nuclei Instance Segmentation},
  journal = {Bioengineering},
  year = {2026},
  volume = {13},
  number = {8},
  pages = {886},
  doi = {10.3390/bioengineering13080886}
}
Kostenlos starten →