{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T18:13:05Z","timestamp":1760465585138,"version":"build-2065373602"},"reference-count":42,"publisher":"Public Library of Science (PLoS)","issue":"10","license":[{"start":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T00:00:00Z","timestamp":1760400000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100007391","name":"Association pour la Recherche sur le Cancer","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007391","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Fondation Recherche M\u00c3\u00a9dicale"},{"DOI":"10.13039\/501100001665","name":"Agence Nationale de la Recherche","doi-asserted-by":"publisher","award":["ANR-21-CE13- 0010-01"],"award-info":[{"award-number":["ANR-21-CE13- 0010-01"]}],"id":[{"id":"10.13039\/501100001665","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001665","name":"Agence Nationale de la Recherche","doi-asserted-by":"publisher","award":["ANR-20-ASTR-0005"],"award-info":[{"award-number":["ANR-20-ASTR-0005"]}],"id":[{"id":"10.13039\/501100001665","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001665","name":"Agence Nationale de la Recherche","doi-asserted-by":"publisher","award":["ANR-10-INBS-04-07"],"award-info":[{"award-number":["ANR-10-INBS-04-07"]}],"id":[{"id":"10.13039\/501100001665","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"abstract":"<jats:p>Segmentation and detection of biological objects in fluorescence microscopy is of paramount importance in cell imaging. Deep learning approaches have recently shown promise to advance, automatize and accelerate analysis. However, most of the interest has been given to the segmentation of static objects of 2D\/3D images whereas the segmentation of dynamic processes obtained from time-lapse acquisitions has been less explored. Here we adapted DeepFinder, a U-Net originally designed for 3D noisy cryo-electron tomography (cryo-ET) data, for the detection of rare dynamic exocytosis events (termed ExoDeepFinder) observed in temporal series of 2D Total Internal Reflection Fluorescence Microscopy (TIRFM) images. ExoDeepFinder achieved good absolute performances with a relatively small training dataset of 12000 events in 60 cells. We rigorously compared deep learning performances with unsupervised conventional methods from the literature. ExoDeepFinder outcompeted the tested methods, but also exhibited a greater plasticity to the experimental conditions when tested under drug treatments and after changes in cell line or imaged reporter. This robustness to unseen experimental conditions did not require re-training demonstrating generalization capability of our deep learning model. ExoDeepFinder, as well as the annotated training datasets, were made transparent and available through an open-source software as well as a Napari plugin and can directly be applied to custom user data. The apparent plasticity and performances of ExoDeepFinder to detect dynamic events open new opportunities for future deep learning guided analysis of dynamic processes in live-cell imaging.<\/jats:p>","DOI":"10.1371\/journal.pcbi.1013556","type":"journal-article","created":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T17:32:12Z","timestamp":1760463132000},"page":"e1013556","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Deep learning detection of dynamic exocytosis events in fluorescence TIRF microscopy"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9090-7893","authenticated-orcid":true,"given":"Hugo","family":"Lachuer","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6264-3245","authenticated-orcid":true,"given":"Emmanuel","family":"Moebel","sequence":"additional","affiliation":[]},{"given":"Anne-Sophie","family":"Mac\u00e9","sequence":"additional","affiliation":[]},{"given":"Arthur","family":"Masson","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6102-8790","authenticated-orcid":true,"given":"Kristine","family":"Schauer","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6263-0452","authenticated-orcid":true,"given":"Charles","family":"Kervrann","sequence":"additional","affiliation":[]}],"member":"340","published-online":{"date-parts":[[2025,10,14]]},"reference":[{"issue":"7","key":"pcbi.1013556.ref001","first-page":"3523","article-title":"Image segmentation using deep learning: a survey","volume":"44","author":"S Minaee","year":"2022","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"pcbi.1013556.ref002","article-title":"U-Net: convolutional networks for biomedical image segmentation","author":"O Ronneberger","year":"2015","journal-title":"Preprint at arXiv"},{"key":"pcbi.1013556.ref003","doi-asserted-by":"crossref","first-page":"66","DOI":"10.1186\/s13007-018-0333-4","article-title":"Deep phenotyping: deep learning for temporal phenotype\/genotype classification","volume":"14","author":"S Taghavi Namin","year":"2018","journal-title":"Plant Methods"},{"issue":"1","key":"pcbi.1013556.ref004","article-title":"Quantitative digital microscopy with deep learning","volume":"8","author":"B Midtvedt","year":"2021","journal-title":"Appl Phy Rev"},{"key":"pcbi.1013556.ref005","doi-asserted-by":"crossref","first-page":"102128","DOI":"10.1016\/j.media.2021.102128","article-title":"Deep probabilistic tracking of particles in fluorescence microscopy images","volume":"72","author":"R Spilger","year":"2021","journal-title":"Med Image Anal"},{"key":"pcbi.1013556.ref006","doi-asserted-by":"crossref","DOI":"10.7554\/eLife.79519","article-title":"DetecDiv, a generalist deep-learning platform for automated cell division tracking and survival analysis","volume":"11","author":"T Aspert","year":"2022","journal-title":"Elife"},{"key":"pcbi.1013556.ref007","doi-asserted-by":"crossref","first-page":"537","DOI":"10.1007\/978-3-031-43993-3_52","article-title":"Self-supervised dense representation learning for live-cell microscopy with time arrow prediction.","author":"B Gallusser","year":"2023","journal-title":"Medical image computing and computer assisted intervention \u2013 MICCAI 2023 Switzerland: Springer Nature Switzerland"},{"issue":"13","key":"pcbi.1013556.ref008","doi-asserted-by":"crossref","DOI":"10.1242\/dev.201747","article-title":"DeXtrusion: automatic recognition of epithelial cell extrusion through machine learning in vivo","volume":"150","author":"A Villars","year":"2023","journal-title":"Development"},{"issue":"11","key":"pcbi.1013556.ref009","doi-asserted-by":"crossref","first-page":"955","DOI":"10.1016\/j.tcb.2023.10.010","article-title":"Opportunities and challenges for deep learning in cell dynamics research","volume":"34","author":"B Chai","year":"2024","journal-title":"Trends Cell Biol"},{"issue":"2","key":"pcbi.1013556.ref010","doi-asserted-by":"crossref","first-page":"667","DOI":"10.1109\/TIP.2014.2380178","article-title":"Background fluorescence estimation and vesicle segmentation in live cell imaging with conditional random fields","volume":"24","author":"T P\u00e9cot","year":"2015","journal-title":"IEEE Trans Image Process"},{"issue":"11","key":"pcbi.1013556.ref011","doi-asserted-by":"crossref","first-page":"5395","DOI":"10.1109\/TIP.2017.2707803","article-title":"Piecewise-stationary motion modeling and iterative smoothing to track heterogeneous particle motions in dense environments","volume":"26","author":"P Roudot","year":"2017","journal-title":"IEEE Trans Image Process"},{"key":"pcbi.1013556.ref012","doi-asserted-by":"crossref","DOI":"10.7554\/eLife.32311","article-title":"A quantitative approach for analyzing the spatio-temporal distribution of 3D intracellular events in fluorescence microscopy","volume":"7","author":"T P\u00e9cot","year":"2018","journal-title":"Elife"},{"issue":"36","key":"pcbi.1013556.ref013","doi-asserted-by":"crossref","first-page":"9026","DOI":"10.1073\/pnas.1804420115","article-title":"Convolutional neural networks automate detection for tracking of submicron-scale particles in 2D and 3D","volume":"115","author":"JM Newby","year":"2018","journal-title":"Proc Natl Acad Sci U S A"},{"issue":"1","key":"pcbi.1013556.ref014","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1109\/TCBB.2006.11","article-title":"Spatio-temporal analysis of constitutive exocytosis in epithelial cells","volume":"3","author":"R Sebastian","year":"2006","journal-title":"IEEE\/ACM Trans Comput Biol Bioinform"},{"issue":"1","key":"pcbi.1013556.ref015","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1016\/j.cmet.2006.11.013","article-title":"Dissecting multiple steps of GLUT4 trafficking and identifying the sites of insulin action","volume":"5","author":"L Bai","year":"2007","journal-title":"Cell Metab"},{"key":"pcbi.1013556.ref016","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1063\/1.2816641","article-title":"Towards fully automated identification of vesicle-membrane fusion events in TIRF microscopy.","author":"P Vallotton","year":"2007","journal-title":"AIP conference proceedings"},{"issue":"9","key":"pcbi.1013556.ref017","doi-asserted-by":"crossref","first-page":"3456","DOI":"10.1128\/MCB.01719-06","article-title":"Insulin stimulates membrane fusion and GLUT4 accumulation in clathrin coats on adipocyte plasma membranes","volume":"27","author":"S Huang","year":"2007","journal-title":"Mol Cell Biol"},{"key":"pcbi.1013556.ref018","first-page":"578","article-title":"Automatic identification of fusion events in TIRF microscopy image sequences.","author":"K Mele","year":"2009","journal-title":"2009 IEEE 12th International conference on computer vision workshops, ICCV workshops"},{"issue":"10","key":"pcbi.1013556.ref019","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0013190","article-title":"A patch-based method for repetitive and transient event detection in fluorescence imaging","volume":"5","author":"J Boulanger","year":"2010","journal-title":"PLoS One"},{"issue":"7","key":"pcbi.1013556.ref020","doi-asserted-by":"crossref","first-page":"1794","DOI":"10.1016\/j.bpj.2011.09.007","article-title":"Interactive, computer-assisted tracking of speckle trajectories in fluorescence microscopy: application to actin polymerization and membrane fusion","volume":"101","author":"MB Smith","year":"2011","journal-title":"Biophys J"},{"issue":"2","key":"pcbi.1013556.ref021","doi-asserted-by":"crossref","first-page":"251","DOI":"10.1016\/j.bpj.2014.11.3462","article-title":"Spatiotemporal detection and analysis of exocytosis reveal fusion \u201chotspots\u201d organized by the cytoskeleton in endocrine cells","volume":"108","author":"T Yuan","year":"2015","journal-title":"Biophys J"},{"key":"pcbi.1013556.ref022","first-page":"610482","article-title":"Automatically identifying fusion events between GLUT4 storage vesicles and the plasma membrane in TIRF microscopy image sequences","volume":"2015","author":"J Wu","year":"2015","journal-title":"Comput Math Methods Med"},{"key":"pcbi.1013556.ref023","doi-asserted-by":"crossref","first-page":"695","DOI":"10.1109\/ISBI.2015.7163968","article-title":"Detection and estimation of membrane diffusion during exocytosis in TIRFM image sequences.","author":"A Basset","year":"2015","journal-title":"2015 IEEE 12th International symposium on biomedical imaging (ISBI)"},{"issue":"11","key":"pcbi.1013556.ref024","doi-asserted-by":"crossref","first-page":"4512","DOI":"10.1109\/TIP.2015.2450996","article-title":"Adaptive spot detection with optimal scale selection in fluorescence microscopy images","volume":"24","author":"A Basset","year":"2015","journal-title":"IEEE Trans Image Process"},{"issue":"1","key":"pcbi.1013556.ref025","doi-asserted-by":"crossref","first-page":"352","DOI":"10.1186\/s12859-017-1765-y","article-title":"An extended model of vesicle fusion at the plasma membrane to estimate protein lateral diffusion from TIRF microscopy images","volume":"18","author":"A Basset","year":"2017","journal-title":"BMC Bioinform"},{"issue":"3","key":"pcbi.1013556.ref026","doi-asserted-by":"crossref","first-page":"1113","DOI":"10.1083\/jcb.201709064","article-title":"Spatiotemporal organization of exocytosis emerges during neuronal shape change","volume":"217","author":"FL Urbina","year":"2018","journal-title":"J Cell Biol"},{"issue":"175","key":"pcbi.1013556.ref027","doi-asserted-by":"crossref","DOI":"10.3791\/62400-v","article-title":"Automated detection and analysis of exocytosis","author":"F Urbina","year":"2021","journal-title":"J Vis Exp"},{"issue":"20","key":"pcbi.1013556.ref028","article-title":"ExoJ - a Fiji\/ImageJ2 plugin for automated spatiotemporal detection and analysis of exocytosis","volume":"137","author":"J Liu","year":"2024","journal-title":"J Cell Sci"},{"issue":"20","key":"pcbi.1013556.ref029","article-title":"pHusion - a robust and versatile toolset for automated detection and analysis of exocytosis","volume":"137","author":"EC O\u2019Shaughnessy","year":"2024","journal-title":"J Cell Sci"},{"key":"pcbi.1013556.ref030","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1016\/j.compmedimag.2017.04.003","article-title":"A hierarchical convolutional neural network for vesicle fusion event classification","volume":"60","author":"H Li","year":"2017","journal-title":"Comput Med Imaging Graph"},{"issue":"1","key":"pcbi.1013556.ref031","doi-asserted-by":"crossref","first-page":"1412","DOI":"10.1038\/s41467-017-01752-5","article-title":"Semisynthetic fluorescent pH sensors for imaging exocytosis and endocytosis","volume":"8","author":"M Martineau","year":"2017","journal-title":"Nat Commun"},{"issue":"11","key":"pcbi.1013556.ref032","doi-asserted-by":"crossref","first-page":"1386","DOI":"10.1038\/s41592-021-01275-4","article-title":"Deep learning improves macromolecule identification in 3D cellular cryo-electron tomograms","volume":"18","author":"E Moebel","year":"2021","journal-title":"Nat Methods"},{"key":"pcbi.1013556.ref033","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1016\/j.cag.2020.07.010","article-title":"SHREC 2020: classification in cryo-electron tomograms","volume":"91","author":"I Gubins","year":"2020","journal-title":"Comp Graph"},{"issue":"8","key":"pcbi.1013556.ref034","doi-asserted-by":"crossref","DOI":"10.1073\/pnas.2207425120","article-title":"Spatial organization of lysosomal exocytosis relies on membrane tension gradients","volume":"120","author":"H Lachuer","year":"2023","journal-title":"Proc Natl Acad Sci U S A"},{"issue":"4","key":"pcbi.1013556.ref035","doi-asserted-by":"crossref","first-page":"625","DOI":"10.1083\/jcb.200208154","article-title":"Membrane proximal lysosomes are the major vesicles responsible for calcium-dependent exocytosis in nonsecretory cells","volume":"159","author":"JK Jaiswal","year":"2002","journal-title":"J Cell Biol"},{"issue":"3","key":"pcbi.1013556.ref036","doi-asserted-by":"crossref","first-page":"1129","DOI":"10.1083\/jcb.201703206","article-title":"Quantifying exosome secretion from single cells reveals a modulatory role for GPCR signaling","volume":"217","author":"FJ Verweij","year":"2018","journal-title":"J Cell Biol"},{"key":"pcbi.1013556.ref037","article-title":"A Survey on Curriculum Learning","author":"X Wang","year":"2021","journal-title":"Preprint at arXiv"},{"issue":"49","key":"pcbi.1013556.ref038","doi-asserted-by":"crossref","first-page":"34365","DOI":"10.1074\/jbc.M804587200","article-title":"Role of HRB in clathrin-dependent endocytosis","volume":"283","author":"M Chaineau","year":"2008","journal-title":"J Biol Chem"},{"issue":"7","key":"pcbi.1013556.ref039","doi-asserted-by":"crossref","first-page":"2215","DOI":"10.1083\/jcb.201805002","article-title":"RAB6 and microtubules restrict protein secretion to focal adhesions","volume":"218","author":"L Fourriere","year":"2019","journal-title":"J Cell Biol"},{"key":"pcbi.1013556.ref040","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1016\/S0091-679X(10)97008-8","article-title":"Protein micropatterns: a direct printing protocol using deep UVs","volume":"97","author":"A Azioune","year":"2010","journal-title":"Methods Cell Biol"},{"issue":"163","key":"pcbi.1013556.ref041","doi-asserted-by":"crossref","DOI":"10.3791\/60801","article-title":"Quantifying spatiotemporal parameters of cellular exocytosis in micropatterned cells","author":"H Lachuer","year":"2020","journal-title":"J Vis Exp"},{"key":"pcbi.1013556.ref042","first-page":"379","article-title":"Tversky loss function for image segmentation using 3D fully convolutional deep networks.","author":"SSM Salehi","year":"2017","journal-title":"Machine learning in medical imaging. Springer International Publishing"}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1013556","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T17:32:21Z","timestamp":1760463141000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1013556"}},"subtitle":[],"editor":[{"given":"Virginie","family":"Uhlmann","sequence":"first","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2025,10,14]]},"references-count":42,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2025,10,14]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1013556","relation":{},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,14]]}}}