Published June 29, 2023 | Version 1.0.0

Structure preserving adversarial generation of labeled training samples for single cell segmentation

  • 1. Biological Research Centre, Szeged

Description

Supplementary package (dataset, generated data and code) for the article: "Structure preserving adversarial generation of labeled training samples for single cell segmentation". (Cell Reports Methods, 2023 - under submission)

Content of the package:

  • datasets.zip: the images and annotations for the fallopian tube and salivary gland dataset.
  • mask_quality_experiment.zip: the generated masks using SIMCEP and the generated microscopy images using pix2pix using the SIMCEP masks.
  • pix2pix_models.zip: the models for fold 0 for both datasets. It can be used to synthesize new images.
  • StyleGAN2-ada_models.zip: the models for synthesizing new masks.
  • code.zip: a github repository (named .git) for executing the pipeline.

Files

code.zip

Files (8.8 GB)

Name Size
md5:a71999728842bf08aa9cbaf1644d62e5
71.9 kB Preview Download
md5:f8591dc7fbca755e12009c82ae97b527
13.5 MB Preview Download
md5:ed3ef0068a6751fb5246cbd9d4c2d508
41.6 MB Preview Download
md5:f31bfc7f65828acc089a85e276ff8054
6.2 GB Preview Download
md5:0964cf40290c8471154ec36120e8bebc
30.9 kB Preview Download
md5:f6fa5c0432d3d480f692ffb03ddd265f
1.6 GB Preview Download
md5:d14137bb5da0619b9e0b082ea3d1841b
987.9 MB Preview Download
md5:78dee999abe8677a2c31908ebdf63e03
88.3 kB Download