May 17, 2013:
New: Now allows synthesis of cell and nuclear shape instances for Hela cells using a diffeomorphic model.
The CellOrganizer project provides tools for
Model learning captures variation among cells in a collection of images. Images used for model learning and
instances synthesized from models can be two- or three-dimensional static images or movies.
- learning generative models of cell organization directly from images
- storing and retrieving those models in XML files
- synthesizing cell images (or other representations) from one or more models
learn models of
These models can be conditional upon each other. For example, for a given synthesized cell instance, organelle position is dependent upon the cell and nuclear shape of that instance.
- cell shape
- nuclear shape
- chromatin texture
- vesicular organelle size, shape and position
- microtubule distribution.
Cell types for which generative models for at least some organelles have been built include human HeLa cells, mouse NIH 3T3 cells, and Arabidopsis protoplasts. Planned projects include mouse T lymphocytes and rat PC12 cells.
Synthesized Cell Images
(click to view)