mhlabCodingTeam / SegEM

Semi automated image analysis toolkit for Connectomics
http://segem.io
MIT License
11 stars 3 forks source link

SegEM: Semi automated image analysis toolkit for Connectomics

This toolkit provides all code described in the paper “SegEM: An efficient semi-automated image analysis toolset for high-resolution connectomics”. (Berning, Boergens & Helmstaedter)

There are two main use cases:

  1. De-novo training of CNNs for the analysis of a novel EM dataset.
  2. Connectomic analysis of a volume-segmented data set based on skeleton reconstructions.

Prerequisites:

Usage

This code was tested on Matlab R2014b.

Set the Matlab working directory to the root folder of the SegEM repository.

Execute initalSettings.m and provide the requested information in the GUI (alternatively, these variables can be set via command line):

Press “OK”. Then, the relevant scripts will be opened in the Matlab editor.


The scripts are conveniently executed using the cell mode in Matlab (pressing Ctrl+Enter executes the current script section; see “cell mode” help in Matlab).

For use case 1: start with cnnStart.m, then proceed to cnnParameterSelection.m, mainSeg.m, wholeDatsetFwdPass.m and skeletonsToContacts.m; these scripts will be opened in the matlab editor automatically

For use case 2: start with skeletonsToContacts.m. When working with the retina dataset ek563, use legacy version skeletonsToContacts_legacy.m, instead.


Brief description of the most relevant SegEM code files:


To further analyze the retina dataset ek563, the following SegEM legacy code is provided: