Raymond Hawkins, Negar Balaghi, Katheryn E Rothenberg, Michelle Ly, Rodrigo Fernandez-Gonzalez
{"title":"rescue - nets:用于三维显微数据分割的循环U-Nets。","authors":"Raymond Hawkins, Negar Balaghi, Katheryn E Rothenberg, Michelle Ly, Rodrigo Fernandez-Gonzalez","doi":"10.1083/jcb.202506102","DOIUrl":null,"url":null,"abstract":"<p><p>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.</p>","PeriodicalId":15211,"journal":{"name":"Journal of Cell Biology","volume":"224 11","pages":""},"PeriodicalIF":6.4000,"publicationDate":"2025-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"ReSCU-Nets: Recurrent U-Nets for segmentation of three-dimensional microscopy data.\",\"authors\":\"Raymond Hawkins, Negar Balaghi, Katheryn E Rothenberg, Michelle Ly, Rodrigo Fernandez-Gonzalez\",\"doi\":\"10.1083/jcb.202506102\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>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.</p>\",\"PeriodicalId\":15211,\"journal\":{\"name\":\"Journal of Cell Biology\",\"volume\":\"224 11\",\"pages\":\"\"},\"PeriodicalIF\":6.4000,\"publicationDate\":\"2025-11-03\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Cell Biology\",\"FirstCategoryId\":\"99\",\"ListUrlMain\":\"https://doi.org/10.1083/jcb.202506102\",\"RegionNum\":1,\"RegionCategory\":\"生物学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2025/8/11 0:00:00\",\"PubModel\":\"Epub\",\"JCR\":\"Q1\",\"JCRName\":\"CELL BIOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Cell Biology","FirstCategoryId":"99","ListUrlMain":"https://doi.org/10.1083/jcb.202506102","RegionNum":1,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/8/11 0:00:00","PubModel":"Epub","JCR":"Q1","JCRName":"CELL BIOLOGY","Score":null,"Total":0}
ReSCU-Nets: Recurrent U-Nets for segmentation of three-dimensional microscopy data.
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.
期刊介绍:
The Journal of Cell Biology (JCB) is a comprehensive journal dedicated to publishing original discoveries across all realms of cell biology. We invite papers presenting novel cellular or molecular advancements in various domains of basic cell biology, along with applied cell biology research in diverse systems such as immunology, neurobiology, metabolism, virology, developmental biology, and plant biology. We enthusiastically welcome submissions showcasing significant findings of interest to cell biologists, irrespective of the experimental approach.