EUVIMEDEUVIMED entdecken
Crossref

ReSCU-Nets: Recurrent U-Nets for segmentation of three-dimensional microscopy data

Raymond Hawkins iD, Negar Balaghi iD, Katheryn E Rothenberg iD, Michelle Ly iD, Rodrigo Fernandez-Gonzalez iD

Journal of Cell Biology · 2025

DOI: 10.1083/jcb.202506102 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Cell Biology, 2025. Verfasst von Raymond Hawkins und 4 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Biomedical Engineering, University of Toronto , Toronto, Canada. Hauptthemen laut MEDLINE: Imaging, Three-Dimensional, Microscopy, Neural Networks, Computer, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 70 Literaturangaben. Gefördert von: Natural Sciences and Engineering Research Council of Canada, Ontario Graduate Scholarship, CIHR.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Segmenting multidimensional microscopy data requires high accuracy across many images (e.g., time points or Z slices) and is thus a labor-intensive part of biological image processing pipelines. We present ReSCU-Nets, recurrent convolutional neural networks that use the segmentation results from the previous image in a sequence as a prompt to segment the current image. We demonstrate that ReSCU-Nets outperform state-of-the-art image segmentation models, including nnU-Net and the Segment Anything Model, in different segmentation tasks on time-lapse microscopy sequences. Furthermore, ReSCU-Nets enable human-in-the loop corrections that prevent propagation of segmentation errors throughout image sequences. Using ReSCU-Nets, we investigate the role of gap junctions during Drosophila embryonic wound healing. We show that pharmacological blocking of gap junctions slows down wound closure by disrupting cytoskeletal polarity and cell shape changes necessary to repair the wound. Our results demonstrate that ReSCU-Nets enable the analysis of the molecular and cellular dynamics of tissue morphogenesis from multidimensional microscopy data.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Imaging, Three-DimensionalMicroscopyNeural Networks, ComputerImage Processing, Computer-AssistedAnimalsGap JunctionsWound HealingDrosophila melanogasterTime-Lapse Imaging

Autor:innen und Institutionen

  • Institute of Biomedical Engineering, University of Toronto , Toronto, Canada.
  • Translational Biology and Engineering Program, Ted Rogers Centre for Heart Research, University of Toronto , Toronto, Canada.
  • Department of Cell and Systems Biology, University of Toronto, Toronto, Canada.
  • Developmental and Stem Cell Biology Program, The Hospital for Sick Children , Toronto, Canada.

ORCID-Profile: Raymond Hawkins, Negar Balaghi, Katheryn E Rothenberg, Michelle Ly, Rodrigo Fernandez-Gonzalez

Förderung

  • Natural Sciences and Engineering Research Council of Canada
  • Ontario Graduate Scholarship
  • CIHR
  • Ted Rogers Centre for Heart Research
  • Canada Foundation for Innovation
  • Canada Research Chair in Quantitative Cell Biology and Morphogenesis
  • NVIDIA
  • Canadian Institutes of Health Research

Zitieren

APA

Hawkins, R., Balaghi, N., Rothenberg, K. E., Ly, M., & Fernandez-Gonzalez, R. (2025). ReSCU-Nets: Recurrent U-Nets for segmentation of three-dimensional microscopy data. Journal of Cell Biology. https://doi.org/10.1083/jcb.202506102

Vancouver

Hawkins R, Balaghi N, Rothenberg KE, Ly M, Fernandez-Gonzalez R. ReSCU-Nets: Recurrent U-Nets for segmentation of three-dimensional microscopy data. Journal of Cell Biology. 2025. doi:10.1083/jcb.202506102

BibTeX
@article{Hawkins2025,
  author = {Hawkins, Raymond and Balaghi, Negar and Rothenberg, Katheryn E and Ly, Michelle and Fernandez-Gonzalez, Rodrigo},
  title = {ReSCU-Nets: Recurrent U-Nets for segmentation of three-dimensional microscopy data},
  journal = {Journal of Cell Biology},
  year = {2025},
  doi = {10.1083/jcb.202506102}
}
Kostenlos starten →