Cellcutter is a simple library for cell segmentation from microscopy images. It is designed to work on crowded cell populations.
Note: Even though cellcutter uses a neural network, it is not a deep-learning model in the traditional sense. It is intended to be used directly on the image you want to segment, as if it is a classical unsupervised segmentation algorithm (e.g. watershed). If you are more interested in building a generalizable deep-learning model, you should check out our project LACSS.
Easiest way to see how cellcutter works it to check the notebook under the notebooks folder. The demo notebook can be run in google colab.
