Updated: Nov 17, 2020
This model deconvolves resonant confocal 3D images to remove noise and enhance image signal. The model takes single-line average resonant scanning image as input and restores the signal to that of a deconvolved 48-line average image. This allows samples to be imaged at significantly higher rates of acquisition without major loss in fidelity. This model is trained using the 3D-RCAN architecture, developed in-house (read about it on BioRxiv ).
The model is trained on 3D volumetric images of EGFP-labeled mouse neurons captured on a Leica SP8 confocal system with resonant scanner at 20x. The resonant scanning mode for the input and ground truth data are set to single-line and 48-line average respectively.
Make sure you have Python versions 3.5 to 3.7 installed with TensorFlow-GPU version 1.13.0 and above.
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.
J Chen, et. al. Three-dimensional residual channel attention networks denoise and sharpen fluorescence microscopy image volumes. BioRxiv.