CellPose

Node using cellpose's deeplearning-based cellular segmentation to automatically predict cellular instances without need for manual thresholds. Requires pypi package cellpose>=0.6.0 to be present in the set conda environment.

Will only predict on 2D, 3D, 2D+T images and does not perform NMS / instance linking.

Stringer, C., Wang, T., Michaelos, M. et al. Cellpose: a generalist algorithm for cellular segmentation. Nat Methods 18, 100–106 (2021). https://doi.org/10.1038/s41592-020-01018-x

Options

Perform Resampling
Run dynamics on the original image size. Setting this to true will be significantly slower but create more accurate boundaries.
Image Column
Column containing the image on which CellPose should predict. Must be of type "IMG".
Expected Diameter (px)
Approximate diameter of the objects to be detected in pixels.
Minimum Size (px)
Minimum size of a nucleus/cytoplasm in pixels.
Prediction Model Type
Which type of prediction should be made. This only applies if no custom-trained model is used.
Prediction Suffix
Suffix added after the input column's name to distinguish which column was predicted on.

Input Ports

Icon
Input table containing an image column on which cellpose will predict.

Output Ports

Icon
Table containing an additional column named "INPUT-NAME_PREDICTION-SUFFIX" containing a segmentation map of predicted cells.

Nodes

Extensions

Links

Download

To use this component in KNIME, download it from the below URL and open it in KNIME:

Download Component
On NodePit since: 2021-02-15
Last update: 2024-04-25
Created with KNIME version: v4.3.3

Deploy, schedule, execute, and monitor your KNIME workflows locally, in the cloud or on-premises – with our brand new NodePit Runner.

Try NodePit Runner!