Published March 31, 2022 | Version v1
Dataset Open

DeepBacs – Escherichia coli release from stationary phase - Bright field segmentation dataset and StarDist model

  • 1. Institute of Physical and Theoretical Chemistry, Max-von-Laue Str. 7, Goethe-University Frankfurt, 60439 Frankfurt, Germany

Description

Training and test images of live E. coli cells imaged under bright field for the task of segmentation.

Additional information can be found on this github wiki.

The example shows a bright field image of live E. coli cells of an overnight culture and the manually annotated segmentation mask.

 

Data type: Paired bright field and segmented mask images 

Microscopy data type: 2D bright field images recorded at 2 min interval

Microscope: Nikon Eclipse Ti-E equipped with an Apo TIRF 1.49NA 100x oil immersion objective

Cell type: E. coli MG1655 wild type strain (CGSC #6300).

File format: .tif (8-bit)

Image size: 512 x 512 px² (106 nm / pixel), 19/15 individual frames (training/test dataset)

512 x 512 px² (106 nm / pixel), 7 regions of interest with 20 frames @ 2 min time interval (live-cell time series)

Data annotation: Images were annotated using the Fiji freehand selection tool.

Image preprocessing: Time series were stabilized using the Fiji plugin StackReg and the 480 x 480 px center region was cropped

StarDist model

The StarDist 2D model was trained from scratch for 200 epochs on 33 paired image patches (image dimensions: (512, 512 px²), patch size: (512 x 512 px²)) with a batch size of 2, 80 rays, grid size 1, 4-fold data augmentation and a mae loss function, using the StarDist 2D ZeroCostDL4Mic notebook (v 1.13) (von Chamier & Laine et al., 2020). Key python packages used include tensorflow (v 0.1.12), Keras (v2.3.1), csbdeep (v 0.6.3), numpy (v 1.21.5), cuda (v 11.1.105). The training was accelerated using a Tesla K80 GPU.

Model weights can be used with the ZeroCostDL4Mic StarDist 2D notebook or the Fiji StarDist plugin.


Author(s): Christoph Spahn1,2, Mike Heilemann1,3

Contact email: christoph.spahn@mpi-marburg.mpg.de

Affiliation(s)

1) Institute of Physical and Theoretical Chemistry, Max-von-Laue Str. 7, Goethe-University Frankfurt, 60439 Frankfurt, Germany

2) ORCID: 0000-0001-9886-2263 

3) ORCID: 0000-0002-9821-3578 

Files

A_Ecoli_ON_segmentation.tif

Files (456.8 MB)

Name Size Download all
md5:c186cb138584ab5a4b3444029be723dd
821.5 kB Preview Download
md5:42ff7a8a3fac87ab98a2558fcce16d02
68.7 MB Preview Download
md5:ec8194112b514a205643d645b04ba374
386.1 MB Preview Download
md5:8a3c4fa6dc90dfa49b1955673cf9de26
1.2 MB Preview Download