Revision as of 16:12, 22 December 2022 by Israel.herrera (talk | contribs)
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to navigation Jump to search


PyHIST website  

PyHIST is a Histological Image Segmentation Tool: a lightweight semi-automatic command-line tool to extract tiles from histopathology whole image slides. It is intended to be an easy-to-use tool to preprocess histological image data for usage in machine learning tasks.

Environment Modules

Run module spider PyHIST to find out what environment modules are available for this application.

System Variables

  • HPC_PYHIST_DIR - installation directory

Additional Information

Example PyHIST run command: \
   --patch-size 64 \
   --output-downsample 16 \
   --save-patches \
   --save-tilecrossed-image \
   --info "verbose" \
   --output /data/apps/tests/pyhist/output \

Things to note:

  • The HiPerGator module for PyHIST has been set up in a manner that does not require you to invoke Python to run the script. If you are following the examples in the authors' tutorial, drop the "python" or "python3" from the command. In the example above, you can see that the command is just " ...".
  • The full path must be specified for the input file and the output directory. In the above example this is "/data/apps/tests/pyhist/GTEX-1117F-0126.svs" and "/data/apps/tests/pyhist/output" respectively. Your paths will likely look something like "/blue/yourgroup/yourusename/yourdir/...". If you do not specify the full path, the script will try to write to unexpected directories and will fail.
  • You must always include the "--output" option to specify the full path to the output directory. As above, the default action (if you leave this option off) will attempt to save the output to a directory that will likely fail. Including this option will ensure that your output goes to your intended directory.


If you publish research that uses PyHIST you have to cite it as follows:

Expand this section to view citation instructions.

Muñoz-Aguirre, M., Ntasis, V. F., Rojas, S. & Guigó, R. PyHIST: A Histological Image Segmentation Tool. PLoS Computational Biology 16, e1008349 (2020).

  doi = {10.1371/journal.pcbi.1008349},
  url = {},
  year = {2020},
  month = oct,
  publisher = {Public Library of Science ({PLoS})},
  volume = {16},
  number = {10},
  pages = {e1008349},
  author = {Manuel Mu{\~{n}}oz-Aguirre and Vasilis F. Ntasis and Santiago Rojas and Roderic Guig{\'{o}}},
  title = {{PyHIST}: A Histological Image Segmentation Tool},
  journal = {{PLOS} Computational Biology}