Author
Wei Ouyang, Hao Xu
Description
DP-UNet trained to segment fluorescent microscopy images of cell borders.
Input channels: 2D images with first channel input (Red), usually actin or microtubules; second channel input (Green), any type of cytosolic marker; third channel input (Blue) nuclei.
Scale: approximately 60x.
Bit depth: 8 bit.
Output channels: first output channel probabilities of 1 minus the mask and minus the border; second, probability of cell borders; third mask probabilities.
More info in https://github.com/CellProfiling/HPA-Cell-Segmentation and https://www.kaggle.com/c/data-science-bowl-2018/discussion/54741. This model was downloaded and converted from BioImage.io, respecting the associated license (see the License section below for more information).
Download
By downloading, installing, copying, accessing, or using the software, you agree to the terms of this end user license agreement.
Requirements
Make sure you have installed Aivia and the required DeepLearning module (which includes Python 3.9.7 and CUDA 11).
Installation and apply instructions
Aivia is required for applying the model file. You can request a demo copy of Aivia here.
Drag-and-drop the model file into the Recipe Console area; or use the 'Load recipe' option in the Recipe Console to load the model file.
Load the test image (or any image of your own) into Aivia.
If your image contains more than one channel, click on the 'Input & Output' section and specify the image channel you wish to apply the model on.
Click 'Start' to apply the model.
License
Copyright 2021 Wei Ouyang. Full license information can be found here.
View license available online: CC 4.0
Acknowledgement
Bioimage.io is supported by AI4Life. AI4Life has received funding from the European Union's Horizon Europe research and innovation programme under grand agreement number 101057970.
About AI4Life: https://ai4life.eurobioimaging.eu/.
References
J Kaimal and P Thul. HPA cell segmentation dataset (version v2) [Data set]. Zenodo.
Comments