DeXtrusion: automatic recognition of epithelial cell extrusion through machine learning <i>in vivo</i>

Villars, Alexis; Letort, Gaëlle; Valon, Léo; Levayer, Romain

doi:10.1242/dev.201747

Cited by 10 publications

(4 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We have overcome these various image analysis constraints by generating a Deep Learning Model to locate cell divisions in space and time from complex 2D+T imaging data (Fig. 2) (Ji et al, 2013; Nie et al, 2016; Villars et al, 2023). We use a ResNet34 model modified into a U-Net structure (He et al, 2016; Ronneberger et al, 2015).…”

Section: Resultsmentioning

confidence: 99%

Deep learning for rapid analysis of cell divisionsin vivoduring epithelial morphogenesis and repair

Turley

Chenchiah

Martin

et al. 2023

Preprint

View full text Add to dashboard Cite

Cell division is fundamental to all healthy tissue growth, as well as being rate-limiting in the tissue repair response to wounding and during cancer progression. However, the role that cell divisions play in tissue growth is a collective one, requiring the integration of many individual cell division events. It is particularly difficult to accurately detect and quantify multiple features of large numbers of cell divisions (including their spatio-temporal synchronicity and orientation), over extended periods of time. It would thus be advantageous to perform such analyses in an automated fashion, which can naturally be much enabled using Deep Learning. Hence, here we have developed a pipeline of Deep Learning Models that accurately identify dividing cells in time- lapse movies of epithelial tissues in vivo. Our pipeline also determines their axis of division orientation, as well as their shape changes before and after division. This strategy has enabled us to analyse the dynamic profile of cell divisions within the Drosophila pupal wing epithelium, both as it undergoes developmental morphogenesis, and as it repairs following laser wounding. We show that the axis of division is biased according to lines of tissue tension and that wounding triggers a synchronised (but not oriented) wave of cell divisions back from the leading edge.

show abstract

Section: Resultsmentioning

confidence: 99%

Deep learning for rapid analysis of cell divisionsin vivoduring epithelial morphogenesis and repair

Turley

Chenchiah

Martin

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…We have overcome these various image analysis constraints by generating a Deep Learning Model to locate cell divisions in space and time from complex 2D+T imaging data (Fig. 2 ) (Ji et al, 2013 ;Villars et al, 2023 ). We use a ResNet34 model modified into a U-Net structure (He et al, 2016 ;Ronneberger et al, 2015 ).…”

Section: A Deep Learning Strategy Efficiently Identifies Dividing Epi...mentioning

confidence: 99%

Deep learning for rapid analysis of cell divisions in vivo during epithelial morphogenesis and repair

Turley,

Chenchiah,

Martin

et al. 2024

Preprint

View full text Add to dashboard Cite

Cell division is fundamental to all healthy tissue growth, as well as being rate-limiting in the tissue repair response to wounding and during cancer progression. However, the role that cell divisions play in tissue growth is a collective one, requiring the integration of many individual cell division events. It is particularly difficult to accurately detect and quantify multiple features of large numbers of cell divisions (including their spatio-temporal synchronicity and orientation) over extended periods of time. It would thus be advantageous to perform such analyses in an automated fashion, which can naturally be enabled using Deep Learning. Hence, we develop a pipeline of Deep Learning Models that accurately identify dividing cells in time-lapse movies of epithelial tissues in vivo . Our pipeline also determines their axis of division orientation, as well as their shape changes before and after division. This strategy enables us to analyse the dynamic profile of cell divisions within the Drosophila pupal wing epithelium, both as it undergoes developmental morphogenesis and as it repairs following laser wounding. We show that the division axis is biased according to lines of tissue tension and that wounding triggers a synchronised (but not oriented) burst of cell divisions back from the leading edge. Accurate and efficient detection of epithelial cell divisions can be automated by deep learning of dynamic time-lapse imaging data Optimal division detection is achieved using multiple timepoints and dual channels for visualisation of nuclei and cell boundaries Epithelial cell divisions are orientated according to lines of global tissue tension after post-division shuffling Spatio-temporal cell division analyses following wounding reveal spatial synchronicity that scales with wound size Additional deep learning tools enable rapid analysis of cell division orientation

show abstract

“…We have overcome these various image analysis constraints by generating a Deep Learning Model to locate cell divisions in space and time from complex 2D+T imaging data (Fig. 2 ) (Ji et al, 2013 ;Villars et al, 2023 ). We use a ResNet34 model modified into a U-Net structure (He et al, 2016 ;Ronneberger et al, 2015 ).…”

Section: A Deep Learning Strategy Efficiently Identifies Dividing Epi...mentioning

confidence: 99%

Deep learning for rapid analysis of cell divisions in vivo during epithelial morphogenesis and repair

Turley,

Chenchiah,

Martin

et al. 2024

eLife

View full text Add to dashboard Cite

Cell division is fundamental to all healthy tissue growth, as well as being rate-limiting in the tissue repair response to wounding and during cancer progression. However, the role that cell divisions play in tissue growth is a collective one, requiring the integration of many individual cell division events. It is particularly difficult to accurately detect and quantify multiple features of large numbers of cell divisions (including their spatio-temporal synchronicity and orientation), over extended periods of time. It would thus be advantageous to perform such analyses in an automated fashion, which can naturally be much enabled using Deep Learning. Hence, here we have developed a pipeline of Deep Learning Models that accurately identify dividing cells in timelapse movies of epithelial tissues in vivo. Our pipeline also determines their axis of division orientation, as well as their shape changes before and after division. This strategy has enabled us to analyse the dynamic profile of cell divisions within the Drosophila pupal wing epithelium, both as it undergoes developmental morphogenesis, and as it repairs following laser wounding. We show that the axis of division is biased according to lines of tissue tension and that wounding triggers a synchronised (but not oriented) wave of cell divisions back from the leading edge. Accurate and efficient detection of epithelial cell divisions can be automated by deep learning of dynamic time-lapse imaging data Optimal division detection is achieved using multiple timepoints and dual channels for visualisation of nuclei and cell boundaries Epithelial cell divisions are orientated according to lines of tissue tension Spatio-temporal cell division analyses following wounding reveal spatial synchronicity that scales with wound size Additional deep learning tools enable rapid analysis of cell division orientation

show abstract

DeXtrusion: automatic recognition of epithelial cell extrusion through machine learning in vivo

Cited by 10 publications

References 55 publications

Deep learning for rapid analysis of cell divisionsin vivoduring epithelial morphogenesis and repair

Deep learning for rapid analysis of cell divisionsin vivoduring epithelial morphogenesis and repair

Deep learning for rapid analysis of cell divisions in vivo during epithelial morphogenesis and repair

Deep learning for rapid analysis of cell divisions in vivo during epithelial morphogenesis and repair

Contact Info

Product

Resources

About