misic-napari 0.1.7

Segmentation of bacteria agnostic to imaging modality

misic-napari

---

A napari plugin for MiSiC. Segmentation of bacteria in dense colonies. The plugin provides acces to preprocessing of the image like scaling, gamma correction, sharpness and noise variance that can improve the segmentation of bacteria irrespective of the imaging modality.

Installation

You can install misic-napari via [pip] in the napari console:

pip install misic-napari

Or install through plugin manager in napari.

Tutorial

Note: The image should be in the format [n,row,col] or [row,col].

get_width

Creates a Shapes layer where the cell width can be hand drawn using line drawing tools in the shapes layer. This need not be precise and can be adjusted later.

segment

This segments the selected image or if its a image stack the first frame in a image. This can be used to quickly set the parameters that can be later used to segment the whole stack.

invert

True; for phase-contrast images.

False; for bright-field and fluorescence images.

local_noise

If checked, this adds noise to image with local variance. In this case, a sensitivity of around 0.1 works well. If unchecked, this adds noise with global variance of sensitivity/100.

gaussian_laplace

Use for Fluorescence images.

gamma

gamma correction

adjust_scale

Fine-tuning the scale near the approximate optimum scale

sharpness

Unsharp mask based sharpness with sigma = 2 and amount = sharpness

segment_stack

Segments the entire stack using the parameters that were obtained in "segment".

save and load parameters

The parameters can be saved and loaded later in a json file.

License

Distributed under the terms of the [MIT] license, "misic-napari" is free and open source software

Cite

@article {10.7554/eLife.65151,
article_type = {journal},
title = {Misic, a general deep learning-based method for the high-throughput cell segmentation of complex bacterial communities},
author = {Panigrahi, Swapnesh and Murat, Dorothée and Le Gall, Antoine and Martineau, Eugénie and Goldlust, Kelly and Fiche, Jean-Bernard and Rombouts, Sara and Nöllmann, Marcelo and Espinosa, Leon and Mignot, Tâm},
editor = {Xiao, Jie and Storz, Gisela and Hensel, Zach},
volume = 10,
year = 2021,
month = {sep},
pub_date = {2021-09-09},
pages = {e65151},
citation = {eLife 2021;10:e65151},
doi = {10.7554/eLife.65151},
url = {https://doi.org/10.7554/eLife.65151},
abstract = {Studies of bacterial communities, biofilms and microbiomes, are multiplying due to their impact on health and ecology. Live imaging of microbial communities requires new tools for the robust identification of bacterial cells in dense and often inter-species populations, sometimes over very large scales. Here, we developed MiSiC, a general deep-learning-based 2D segmentation method that automatically segments single bacteria in complex images of interacting bacterial communities with very little parameter adjustment, independent of the microscopy settings and imaging modality. Using a bacterial predator-prey interaction model, we demonstrate that MiSiC enables the analysis of interspecies interactions, resolving processes at subcellular scales and discriminating between species in millimeter size datasets. The simple implementation of MiSiC and the relatively low need in computing power make its use broadly accessible to fields interested in bacterial interactions and cell biology.},
keywords = {Deep learning, image analysis, microscopy, myxococcus xanthus, biofilms},
journal = {eLife},
issn = {2050-084X},
publisher = {eLife Sciences Publications, Ltd},
}