An end-to-end pipeline based on open source deep learning tools for reliable analysis of complex 3D images of ovaries
Development · 01.04.2023 · 150 (7)
DOI: 10.1242/dev.201185 ↗Kurz gefasst
Fachartikel in der Zeitschrift Development, online erschienen am 03.04.2023. Verfasst von Manon Lesage und 9 weiteren Autor:innen. Beteiligte Einrichtung: INRAE, Fish Physiology and Genomics Institute, 16 Allee Henri Fabre, Rennes 35000, France. Hauptthemen laut MEDLINE: Deep Learning. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 34 Literaturangaben. Gefördert von: Medical Research Council, Wellcome Trust, Cancer Research UK.
Abstract (Originalsprache)
Computational analysis of bio-images by deep learning (DL) algorithms has made exceptional progress in recent years and has become much more accessible to non-specialists with the development of ready-to-use tools. The study of oogenesis mechanisms and female reproductive success has also recently benefited from the development of efficient protocols for three-dimensional (3D) imaging of ovaries. Such datasets have a great potential for generating new quantitative data but are, however, complex to analyze due to the lack of efficient workflows for 3D image analysis. Here, we have integrated two existing open-source DL tools, Noise2Void and Cellpose, into an analysis pipeline dedicated to 3D follicular content analysis, which is available on Fiji. Our pipeline was developed on larvae and adult medaka ovaries but was also successfully applied to different types of ovaries (trout, zebrafish and mouse). Image enhancement, Cellpose segmentation and post-processing of labels enabled automatic and accurate quantification of these 3D images, which exhibited irregular fluorescent staining, low autofluorescence signal or heterogeneous follicles sizes. In the future, this pipeline will be useful for extensive cellular phenotyping in fish or mammals for developmental or toxicology studies.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- INRAE, Fish Physiology and Genomics Institute, 16 Allee Henri Fabre, Rennes 35000, France.
- BIOSIT, UAR 3480 US 018, Université de Rennes, 2 rue Prof. Leon Bernard, Rennes 35042, France.
- INERIS, UMR-I 02 SEBIO, Verneuil en Halatte 65550, France.
- The Francis Crick Institute, 1 Midland Rd, London NW1 1AT, UK.
ORCID-Profile: Manon Lesage, Thierry Pécot, Violette Thermes
Förderung
- Medical Research Council
- Wellcome Trust
- Cancer Research UK
- Agence Nationale de la Recherche
- Institut National de Recherche pour l'Agriculture, l'Alimentation et l'Environnement
- Agence nationale de sécurité sanitaire de l'alimentation, de l'environnement et du travail
- Chan Zuckerberg Initiative
Zitieren
APA
Lesage, M., Thomas, M., Pécot, T., Ly, T. K., Hinfray, N., Beaudouin, R., Neumann, M., Lovell-Badge, R., Bugeon, J., & Thermes, V. (2023). An end-to-end pipeline based on open source deep learning tools for reliable analysis of complex 3D images of ovaries. Development, 150(7). https://doi.org/10.1242/dev.201185
Vancouver
Lesage M, Thomas M, Pécot T, Ly TK, Hinfray N, Beaudouin R, et al. An end-to-end pipeline based on open source deep learning tools for reliable analysis of complex 3D images of ovaries. Development. 2023;150(7). doi:10.1242/dev.201185
BibTeX
@article{Lesage2023,
author = {Lesage, Manon and Thomas, Manon and Pécot, Thierry and Ly, Tu-Ky and Hinfray, Nathalie and Beaudouin, Remy and Neumann, Michelle and Lovell-Badge, Robin and Bugeon, Jérôme and Thermes, Violette},
title = {An end-to-end pipeline based on open source deep learning tools for reliable analysis of complex 3D images of ovaries},
journal = {Development},
year = {2023},
volume = {150},
number = {7},
doi = {10.1242/dev.201185}
}
EUVIMED