Journal article
ReSCU-Nets: Recurrent U-Nets for segmentation of three-dimensional microscopy data
The Journal of cell biology, Vol.224(11), e202506102
11/03/2025
DOI: 10.1083/jcb.202506102
PMID: 40788207
Abstract
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.
Details
- Title: Subtitle
- ReSCU-Nets: Recurrent U-Nets for segmentation of three-dimensional microscopy data
- Creators
- Raymond Hawkins - University of TorontoNegar Balaghi - University of TorontoKatheryn E Rothenberg - University of TorontoMichelle Ly - University of TorontoRodrigo Fernandez-Gonzalez - University of Toronto
- Resource Type
- Journal article
- Publication Details
- The Journal of cell biology, Vol.224(11), e202506102
- DOI
- 10.1083/jcb.202506102
- PMID
- 40788207
- NLM abbreviation
- J Cell Biol
- ISSN
- 0021-9525
- eISSN
- 1540-8140
- Publisher
- ROCKEFELLER UNIV PRESS
- Grant note
- Ontario Graduate Scholarship NVIDIA Canada Research Chair in Quantitative Cell Biology and Morphogenesis Ted Rogers Centre for Heart Research 186188 / CIHR 418438-13 / Natural Sciences and Engineering Research Council of Canada 156279 / CIHR 30279 / Canada Foundation for Innovation
- Language
- English
- Date published
- 11/03/2025
- Academic Unit
- Biology
- Record Identifier
- 9984946836802771
Metrics
23 Record Views