دورية أكاديمية
DeXtrusion: automatic recognition of epithelial cell extrusion through machine learning in vivo
| العنوان: | DeXtrusion: automatic recognition of epithelial cell extrusion through machine learning in vivo |
|---|---|
| المؤلفون: | Villars, Alexis, Letort, Gaëlle, Valon, Léo, Levayer, Romain |
| المساهمون: | Biologie du Développement et Cellules souches (CNRS UMR3738), Institut Pasteur Paris (IP)-Centre National de la Recherche Scientifique (CNRS)-Université Paris Cité (UPCité), Ecole Doctorale Complexité du Vivant (ED515), Sorbonne Université (SU), A.V. was supported by a PhD grant from the doctoral school ‘Complexité du Vivant’ Sorbonne Université and from an extension grant of the Ligue Contre le Cancer. Work in the R.L. lab is supported by the Institut Pasteur (G5 starting package), a European Research Council starting grant (CoSpaDD, Competition for Space in Development and Disease, grant number 758457), the Agence Nationale de la Recherche (CoECECa, Coordination of Epithelial Cell Extrusion by Caspases) and the Centre National de la Recherche Scientifique (UMR 3738). We also thank Danielle Casteran and her family for their generous donation, which helped to finalise this project. Open Access funding provided by the European Research Council. Deposited in PMC for immediate release., We acknowledge the Image Analysis Hub of the Institut Pasteur for discussions and advice for this work. We thank Jean-Yves Tinevez, Kevin Yamauchi and Raphaël Etournay for critical reading of the manuscript. We also thank Raphaël Etournay for sharing the pupal wing movie and Nic Tapon for providing the original and segmentation of the pupal abdomen movies. We acknowledge the help of the HPC Core Facility of the Institut Pasteur for this work., ANR-22-CE13-0002,CoECECa,Vers une caractérisation exhaustive de la coordination de l'extrusion epithéliales par les caspases(2022), European Project: 758457,H2020-EU.1.1. - EXCELLENT SCIENCE - European Research Council (ERC),ERC-2017-STG,CoSpaDD(2018) |
| المصدر: | ISSN: 0950-1991. |
| بيانات النشر: | HAL CCSD Company of Biologists |
| سنة النشر: | 2023 |
| مصطلحات موضوعية: | Deep-learning, convolutional neural network, epithelia, live imaging, extrusion, cell division, SOPs, Drosophila, [SDV.BC.IC]Life Sciences [q-bio]/Cellular Biology/Cell Behavior [q-bio.CB] |
| الوصف: | International audience ; Accurately counting and localising cellular events from movies is an important bottleneck of high-content tissue/embryo live imaging. Here, we propose a new methodology based on deep learning that allows automatic detection of cellular events and their precise xyt localisation on live fluorescent imaging movies without segmentation. We focused on the detection of cell extrusion, the expulsion of dying cells from the epithelial layer, and devised DeXtrusion: a pipeline based on recurrent neural networks for automatic detection of cell extrusion/cell death events in large movies of epithelia marked with cell contour. The pipeline, initially trained on movies of the Drosophila pupal notum marked with fluorescent E-cadherin, is easily trainable, provides fast and accurate extrusion predictions in a large range of imaging conditions, and can also detect other cellular events, such as cell division or cell differentiation. It also performs well on other epithelial tissues with reasonable re-training. Our methodology could easily be applied for other cellular events detected by live fluorescent microscopy and could help to democratise the use of deep learning for automatic event detections in developing tissues. |
| نوع الوثيقة: | article in journal/newspaper |
| اللغة: | English |
| العلاقة: | info:eu-repo/semantics/altIdentifier/pmid/37283069; info:eu-repo/grantAgreement//758457/EU/Competition for Space in Development and Diseases/CoSpaDD; pasteur-04244427; https://pasteur.hal.science/pasteur-04244427Test; https://pasteur.hal.science/pasteur-04244427/documentTest; https://pasteur.hal.science/pasteur-04244427/file/Villars%26LetortFused.pdfTest; PUBMED: 37283069; PUBMEDCENTRAL: PMC10323232 |
| DOI: | 10.1242/dev.201747 |
| الإتاحة: | https://doi.org/10.1242/dev.201747Test https://pasteur.hal.science/pasteur-04244427Test https://pasteur.hal.science/pasteur-04244427/documentTest https://pasteur.hal.science/pasteur-04244427/file/Villars%26LetortFused.pdfTest |
| حقوق: | http://creativecommons.org/licenses/by-ncTest/ |
| رقم الانضمام: | edsbas.E15C9E01 |
| قاعدة البيانات: | BASE |
| DOI: | 10.1242/dev.201747 |
|---|