EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

PSCount: A deep learning tool for automated polystyrene particle counting in brightfield microscopy images

Seoleun Shin, Ji Youn Lee

SoftwareX · 2026-06 · 34 · 102695

DOI: 10.1016/j.softx.2026.102695 ↗

Kurz gefasst

Fachartikel in der Zeitschrift SoftwareX, 2026-06. Verfasst von Seoleun Shin und 1 weiteren Autor:innen. Die Arbeit nennt 21 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Science and ICT, South Korea, Korea Research Institute of Standards and Science.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

PSCount has been developed for automated counting of polystyrene particles in brightfield microscopy images. Built upon a fine-tuned foundation model, PSCount achieves high accuracy in particle detection and counting, including the separation of clustered particles. Evaluated on 24 test images containing 87–224 particles per image, the software reduces the mean absolute error from 65.5 to 2.1 particles per image compared to the base model, demonstrating effective domain adaptation with minimal training data (19 images). PSCount provides researchers with a reproducible and efficient alternative to manual counting methods.

Förderung

  • Ministry of Science and ICT, South Korea
  • Korea Research Institute of Standards and Science

Zitieren

APA

Shin, S., & Lee, J. Y. (2026). PSCount: A deep learning tool for automated polystyrene particle counting in brightfield microscopy images. SoftwareX, 34, 102695. https://doi.org/10.1016/j.softx.2026.102695

Vancouver

Shin S, Lee JY. PSCount: A deep learning tool for automated polystyrene particle counting in brightfield microscopy images. SoftwareX. 2026;34:102695. doi:10.1016/j.softx.2026.102695

BibTeX
@article{Shin2026,
  author = {Shin, Seoleun and Lee, Ji Youn},
  title = {PSCount: A deep learning tool for automated polystyrene particle counting in brightfield microscopy images},
  journal = {SoftwareX},
  year = {2026},
  volume = {34},
  pages = {102695},
  doi = {10.1016/j.softx.2026.102695}
}
Kostenlos starten →