Python

EPySeg is a package for segmenting 2D epithelial tissues. EPySeg also ships with a graphical user interface that allows for building, training and running deep learning models.

Training can be done with or without data augmentation (2D-xy and 3D-xyz data augmentation are supported). EPySeg relies on the segmentation_models library. EPySeg source code is available here. Cloud version available here.

VTK is an open-source software system for image processing, 3D graphics, volume rendering and visualization. VTK includes many advanced algorithms (e.g., surface reconstruction, implicit modeling, decimation) and rendering techniques (e.g., hardware-accelerated volume rendering, LOD control).

VTK is used by academicians for teaching and research; by government research institutions such as Los Alamos National Lab in the US or CINECA in Italy; and by many commercial firms who use VTK to build or extend products.

The origin of VTK is with the textbook "The Visualization Toolkit, an Object-Oriented Approach to 3D Graphics" originally published by Prentice Hall and now published by Kitware, Inc. (Third Edition ISBN 1-930934-07-6). VTK has grown (since its initial release in 1994) to a world-wide user base in the commercial, academic, and research communities.

A collection of Image Processing and Analysis (IPA) functions used at the Facility for Advanced Imaging and Microscopy (FAIM).

DeXtrusion is a machine learning based python pipeline to detect cell extrusions in epithelial tissues movies. It can also detect cell divisions and SOPs, and can easily be trained to detect other dynamic events.

DeXtrusion takes as input a movie of an epithelium and outputs the spatio-temporal location of cell extrusion events or other event as cell divisions. The movie is discretized into small overlapping rolling windows which are individually classified for event detection by a trained neural network. Results are then put together in event probability map for the whole movie or as spatio-temporal points indicating each event.

While a quickly retrained cellpose network (only on xy slices, no need to train on xz or yz slices) is giving good results in 2D, the anisotropy of the SIM image prevents its usage in 3D. Here the workflow consists in applying 2D cellpose segmentation and then using the CellStich libraries to optimize the 3D labelling of objects from the 2D independant labels.

Here the provided notebook is fully compatible with Google Collab and can be run by uploading your own images to your gdrive. A model is provided to be replaced by your own (create by CellPose 2.0)