Practical Fluorescence Reconstruction Microscopy for Large Samples and Low-Magnification Imaging

LaChance, Julienne; Cohen, Daniel

doi:10.1101/2020.03.05.979419

Cited by 6 publications

(6 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Cell density measurements. We first reproduced nuclei positions from 4× phasecontrast images using our in-house Fluorescence Reconstruction Microscopy tool 71 . The output of this neural network was then segmented in ImageJ to determine nuclei footprints and centroids.…”

Section: Methodsmentioning

confidence: 99%

Self-assembly of tessellated tissue sheets by expansion and collision

et al. 2022

Self Cite

View full text Add to dashboard Cite

Tissues do not exist in isolation—they interact with other tissues within and across organs. While cell-cell interactions have been intensely investigated, less is known about tissue-tissue interactions. Here, we studied collisions between monolayer tissues with different geometries, cell densities, and cell types. First, we determine rules for tissue shape changes during binary collisions and describe complex cell migration at tri-tissue boundaries. Next, we propose that genetically identical tissues displace each other based on pressure gradients, which are directly linked to gradients in cell density. We present a physical model of tissue interactions that allows us to estimate the bulk modulus of the tissues from collision dynamics. Finally, we introduce TissEllate, a design tool for self-assembling complex tessellations from arrays of many tissues, and we use cell sheet engineering techniques to transfer these composite tissues like cellular films. Overall, our work provides insight into the mechanics of tissue collisions, harnessing them to engineer tissue composites as designable living materials.

show abstract

Section: Methodsmentioning

confidence: 99%

Self-assembly of tessellated tissue sheets by expansion and collision

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…The FUCCI system contains a period after M-phase where cells go dark, making FUCCI unreliable for cell counting. Instead, we developed and trained a convolutional neural network to reproduce nuclei from 4X phase contrast images using our in-house Fluorescence Reconstruction Microscopy tool ( LaChance and Cohen, 2020 ) . The output of this neural network was then segmented in ImageJ to determine nuclei footprints and centroids.…”

Section: Methodsmentioning

confidence: 99%

Size-dependent patterns of cell proliferation and migration in freely-expanding epithelia

Heinrich

Alert

LaChance

et al. 2020

eLife

Self Cite

View full text Add to dashboard Cite

The coordination of cell proliferation and migration in growing tissues is crucial in development and regeneration but remains poorly understood. Here, we find that, while expanding with an edge speed independent of initial conditions, millimeter-scale epithelial monolayers exhibit internal patterns of proliferation and migration that depend not on the current but on the initial tissue size, indicating memory effects. Specifically, the core of large tissues becomes very dense, almost quiescent, and ceases cell-cycle progression. In contrast, initially-smaller tissues develop a local minimum of cell density and a tissue-spanning vortex. To explain vortex formation, we propose an active polar fluid model with a feedback between cell polarization and tissue flow. Taken together, our findings suggest that expanding epithelia decouple their internal and edge regions, which enables robust expansion dynamics despite the presence of size and history-dependent patterns in the tissue interior.

show abstract

“…However, the often cited weakness of these techniques is the lack of an intuitive explanation of which parts of the data are particularly meaningful in defining the extracted pattern. While in some applications, such as image segmentation, image restoration or mapping between imaging modalities, a well-validated outcome of a network has been satisfactory (Christiansen et al, 2018;Fang et al, 2019b;Guo et al, 2019;Hershko et al, 2019;Hollandi et al, 2019;LaChance and Cohen, 2020;Moen et al, 2019;Nehme et al, 2018;Ounkomol et al, 2018;Ouyang et al, 2018;Rivenson et al, 2019;Wang et al, 2019;Weigert et al, 2018;Wu et al, 2019), there is increasing mistrust in results produced by 'black-box' neural networks. Aside from increasing the confidence, the analysis of the properties -also referred to as 'mechanisms'of the pattern recognition process can potentially generate insight of a biological/physical phenomenon that escapes the analysis driven by human intuition.…”

Section: Interpretation Of Latent Features Discriminating High and Lomentioning

confidence: 99%

Interpretable deep learning of label-free live cell images uncovers functional hallmarks of highly-metastatic melanoma

Zaritsky

Jamieson

Welf

et al. 2020

Preprint

View full text Add to dashboard Cite

Deep convolutional neural networks have emerged as a powerful technique to identify hidden patterns in complex cell imaging data. However, these machine learning techniques are often criticized as uninterpretable "black-boxes" -lacking the ability to provide meaningful explanations for the cell properties that drive the machine's prediction. Here, we demonstrate that the latent features extracted from label-free live cell images by an adversarial auto-encoding deep convolutional neural network capture subtle details of cell appearance that allow classification of melanoma cell states, including the metastatic efficiency of seven patientderived xenograft models that reflect clinical outcome. Although trained exclusively on patientderived xenograft models, the same classifier also predicted the metastatic efficiency of immortalized melanoma cell lines suggesting that the latent features capture properties that are specifically associated with the metastatic potential of a melanoma cell regardless of its origin.We used the autoencoder to generate "in-silico" cell images that amplified the cellular features driving the classifier of metastatic efficiency. These images unveiled pseudopodial extensions and increased light scattering as functional hallmarks of metastatic cells. We validated this interpretation by analyzing experimental image time-lapse sequences in which melanoma cells spontaneously transitioned between states indicative of low and high metastatic efficiency.Together, this data is an example of how the application of Artificial Intelligence supports the identification of processes that are essential for the execution of complex integrated cell functions but are too subtle to be identified by a human expert. -Gurion University of the Negev, Israel (to AZ). We thank Sean Morrison for PDX-derived cell models. We thank Andrew R. Cohen for LEVER. Author ContributionAZ, ESW and GD conceived the study. ESW designed the experimental assay, optimized culture conditions for PDX cells, and trained AN and JC to perform the experiments. AN performed all live imaging and mouse experiments. JC performed additional experiments. UE generated the PDX samples. AZ and ARJ developed analytic tools, analyzed, and interpreted the data. AZ drafted the manuscript. All authors wrote and edited the manuscript and approved its content.GD mentored all authors.

show abstract

Practical Fluorescence Reconstruction Microscopy for Large Samples and Low-Magnification Imaging

Cited by 6 publications

References 41 publications

Self-assembly of tessellated tissue sheets by expansion and collision

Self-assembly of tessellated tissue sheets by expansion and collision

Size-dependent patterns of cell proliferation and migration in freely-expanding epithelia

Interpretable deep learning of label-free live cell images uncovers functional hallmarks of highly-metastatic melanoma

Contact Info

Product

Resources

About