EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

PostFocus: automated selective post-acquisition high-throughput focus restoration using diffusion model for label-free time-lapse microscopy

Kwan-Ling Wu, Melisa J Montalvo, Prashant S Menon, Badrinath Roysam, Navin Varadarajan iD

Bioinformatics · 2024

DOI: 10.1093/bioinformatics/btae467 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, 2024. Verfasst von Kwan-Ling Wu und 4 weiteren Autor:innen. Beteiligte Einrichtung: William A. Brookshire Department of Chemical and Biomolecular Engineering, University of Houston, Houston, TX 77204, United States. Hauptthemen laut MEDLINE: Time-Lapse Imaging, Algorithms, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 82 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIGMS NIH HHS, NIH HHS, National Institutes of Health.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation High-throughput time-lapse imaging is a fundamental tool for efficient living cell profiling at single-cell resolution. Label-free phase-contrast video microscopy enables noninvasive, nontoxic, and long-term imaging. The tradeoff between speed and throughput, however, implies that despite the state-of-the-art autofocusing algorithms, out-of-focus cells are unavoidable due to the migratory nature of immune cells (velocities >10 μm/min). Here, we propose PostFocus to (i) identify out-of-focus images within time-lapse sequences with a classifier, and (ii) deploy a de-noising diffusion probabilistic model to yield reliable in-focus images. Results De-noising diffusion probabilistic model outperformed deep discriminative models with a superior performance on the whole image and around cell boundaries. In addition, PostFocus improves the accuracy of image analysis (cell and contact detection) and the yield of usable videos. Availability and implementation Open-source code and sample data are available at: https://github.com/kwu14victor/PostFocus.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Time-Lapse ImagingAlgorithmsImage Processing, Computer-AssistedHumansMicroscopy, VideoSingle-Cell Analysis

Autor:innen und Institutionen

  • William A. Brookshire Department of Chemical and Biomolecular Engineering, University of Houston, Houston, TX 77204, United States.
  • Department of Electrical and Computer Engineering, University of Houston, Houston, TX 77204, United States.

ORCID-Profile: Navin Varadarajan

Förderung

  • NIGMS NIH HHS
  • NIH HHS
  • National Institutes of Health

Zitieren

APA

Wu, K. L., Montalvo, M. J., Menon, P. S., Roysam, B., & Varadarajan, N. (2024). PostFocus: automated selective post-acquisition high-throughput focus restoration using diffusion model for label-free time-lapse microscopy. Bioinformatics. https://doi.org/10.1093/bioinformatics/btae467

Vancouver

Wu KL, Montalvo MJ, Menon PS, Roysam B, Varadarajan N. PostFocus: automated selective post-acquisition high-throughput focus restoration using diffusion model for label-free time-lapse microscopy. Bioinformatics. 2024. doi:10.1093/bioinformatics/btae467

BibTeX
@article{Wu2024,
  author = {Wu, Kwan-Ling and Montalvo, Melisa J and Menon, Prashant S and Roysam, Badrinath and Varadarajan, Navin},
  title = {PostFocus: automated selective post-acquisition high-throughput focus restoration using diffusion model for label-free time-lapse microscopy},
  journal = {Bioinformatics},
  year = {2024},
  doi = {10.1093/bioinformatics/btae467}
}
Kostenlos starten →