EUVIMEDEUVIMED entdecken
Crossref

RA-UNet: Achieving robust blood cell segmentation in Complex microscopic environments

Murat Toptaş iD, Buket Toptaş iD, Davut Hanbay iD

Technology and Health Care · 18.11.2026

DOI: 10.1177/09287329261509252 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Technology and Health Care, online erschienen am 18.11.2026. Verfasst von Murat Toptaş und 2 weiteren Autor:innen. Beteiligte Einrichtung: Software Engineering. Department, Engineering and Natural Science Faculty, Bandırma Onyedi Eylül University, Balıkesir, Turkey. Die Arbeit nennt 74 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Tracking, classifying, and segmenting cell images are critical clinical tasks essential in diagnosing various diseases such as leukemia and in performing blood counts. While deep neural architectures are preferred for these tasks, the presence of noise in images, overlapping cells, and indistinct cell boundaries make it a challenging endeavor.

Objective

In this article, an attention mechanism based on U-Net has been developed for cell segmentation. This attention mechanism enhances detail capture while suppressing irrelevant information.

Methods

The proposed model has been tested on four publicly available cell datasets and evaluated using seven different performance metrics. The performance of the proposed model was benchmarked against state-of-the-art methods.

Results

The proposed model demonstrated the best overall performance on the dataset named Dataset-III, while it was most successful on Dataset-I. The experimental results were evaluated both quantitatively and qualitatively.

Conclusion

The outcomes have substantiated the efficacy and potential of the proposed model to provide a competitive approach.

Schlagwörter

Stichwörter der Autor:innen

Attention mechanismU-Netcell segmentationdeep learning

Autor:innen und Institutionen

  • Software Engineering. Department, Engineering and Natural Science Faculty, Bandırma Onyedi Eylül University, Balıkesir, Turkey.
  • Computer Engineering. Department, Engineering Faculty, Inonu University, 44280, Malatya, Turkey.

ORCID-Profile: Murat Toptaş, Buket Toptaş, Davut Hanbay

Zitieren

APA

Toptaş, M., Toptaş, B., & Hanbay, D. (2026). RA-UNet: Achieving robust blood cell segmentation in Complex microscopic environments. Technology and Health Care. https://doi.org/10.1177/09287329261509252

Vancouver

Toptaş M, Toptaş B, Hanbay D. RA-UNet: Achieving robust blood cell segmentation in Complex microscopic environments. Technology and Health Care. 2026. doi:10.1177/09287329261509252

BibTeX
@article{Topta2026,
  author = {Toptaş, Murat and Toptaş, Buket and Hanbay, Davut},
  title = {RA-UNet: Achieving robust blood cell segmentation in Complex microscopic environments},
  journal = {Technology and Health Care},
  year = {2026},
  doi = {10.1177/09287329261509252}
}
Kostenlos starten →