The DeepCell-tf library allows users to apply pre-existing models to imaging data as well as to develop new deep learning models for single-cell analysis. The library specializes in models for cell segmentation (whole-cell and nuclear) in 2D and 3D images as well as cell tracking in 2D time-lapse datasets. The models are applicable to data ranging from multiplexed images of tissues to dynamic live-cell imaging movies.

References:

• Noah F. Greenwald , Geneva Miller, Erick Moen, ..., Michael Angelo and David Van Valen,
  Whole-cell segmentation of tissue images with human-level performance using large-scale data annotation and deep learning,
  Nature Biotechnology, vol.40, pp. 555–565
• David A. Van Valen, Takamasa Kudo, Keara M. Lane, ..., Euan A. Ashley, Markus W. Covert,
  Deep Learning Automates the Quantitative Analysis of Individual Cells in Live-Cell Imaging Experiments,
  PLOS Computational Biology | DOI:10.1371/journal.pcbi.1005177 November 4, 2016

• DeepCell-tf Github page
• DeepCell-tf Segmentation manual
• DeepCell-tf Tracking manual

• Module Name: deepcell-tf (see the modules page for more information)
• Unusual environment variables set
  • DEEPCELLTF_HOME  installation directory
  • DEEPCELLTF_BIN    executables directory
  • DEEPCELLTF_SRC    source code directory
  • DEEPCELLTF_DATA    sample input data directory

[user@biowulf]$ sinteractive  --mem=8g  -c4 \
                                 --gres=gpu:p100,lscratch:10 \
                                 --tunnel

[user@cn0861 ~]$ cd /lscratch/$SLURM_JOB_ID
[user@cn0861 ~]$ module load deepcell-tf   
[+] Loading singularity  3.10.5  on cn0793
[+] Loading jupyter
[+] Loading deepcell-tf  0.12.6
[user@cn0861 ~]$ git clone https://github.com/vanvalenlab/deepcell-tf 
[user@cn0861 ~]$ cd deepcell-tf/notebooks/applications 

[user@cn0861 ~]$ jupyter notebook --ip localhost --port $PORT1 --no-browser

[user@cn0861 ~]$ ssh  -L $PORT1:localhost:$PORT1 user@biowulf.nih.gov 

[user@cn0861 ~]$ exit
salloc.exe: Relinquishing job allocation 46116226