Segmentation of bacteria growing in agar-pads, imaged by transmitted light stacks
Project description
TaLiSSman: TrAnsmitted LIght Stack SegMentAtioN
Segmentation of bacteria growing in agar-pads, imaged by de-focused transmitted light stacks
How it works
- Expected input images are stacks of 2D images, with Z-axis last : Image = [batch, Y, X, Z]. We advise stacks of 5 slices with a 0.2µm step, in range [-0.6µm, -1.4µm] (relatively to the focal plane)
- Segmentation is performed by regression of the Euclidean Distance Map (EDM).
- This repository does not include the downstream watershed step to obtain labeled images.
Input Transmitted-Light Stack | Predicted EDM | Segmented Bacteria |
---|---|---|
Samples provided by Daniel Thédié, El Karoui Lab, University of Edinburg
Network architecture:
- Based on U-net
- Before first layer a block is added to reduced Z-axis using 3D convolutions and 3D Z-maxpooling
More details can be found on my website
How to use it
Check the wiki!
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
TaLiSSman-0.0.3.tar.gz
(11.2 kB
view hashes)