Skip to content

models for pixelwise classification of zebrafish cryosection cell membranes

Notifications You must be signed in to change notification settings

mpicbg-csbd/unet-smfish-seg

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

About

Example membrane classification and cell segmentation. This method performs automatic pixelwise membrane labeling and cell instance segmentation in 2D cross-sections of Zebrafish embryos labeled with smFISH.

For information about the sample preparation and imaging involved in creating the data please see Stapel et al.

Methods

Membrane pixelwise classification is performed with a 5-layer U-Net modified from retinal blood vessel segmentation.

Dependencies

You need Python3 with the standard scientific python libraries: numpy, scipy, scikit-learn and scikit-image the deep learning framework Keras which uses as backend: Tensorflow or Theano

Footnotes

[Stapel et al]:
Stapel, L. Carine, et al. "Automated detection and quantification of single RNAs at cellular resolution in zebrafish embryos."Development 143.3 (2016): 540-546.

About

models for pixelwise classification of zebrafish cryosection cell membranes

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages