3. Denoising with Noise2Void

Disclaimer: Noise2Void improves the visual quality of an image. However, it is uncertain whether or not signals remain scientifically accurate for quantification (morphological quantification may be fine, intensities not)

Useful for:

Visualization
Intermediary step for mask generation
Segmentation

Credits:

1. Start Noise2Void with the icon on the desktop : N2V

2. Start by entering your credentials for the server omero-cai.hhu.de and click on "Connect"

4. You can then select the group in which the dataset you want to process is located, and indicated the dataset ID. Load the dataset by pressing "Load dataset". You can change which image ID, Z, T or C to display by updating the field and clicking on "Set"

5. To train the network to denoise your images, go to the tab "Train N2V"

Patch size: Together with "Batch size", will change how much data is passed to the GPU per batch. A patch of 256x256 with a batch size of 16 works best for our workstation (the one next to the spinning disk microscope)
Number of training epochs: Increase this if your loss is still decreasing after 100 epochs.
→ Jump to 5. if you already have a trained model
Choose a name for the model
Select the path where to save the model
"Number of training epochs" and "Batch size" can be left as default (if there is a memory error, for the training, the batch size must be reduced).
Click on "Start training" and go for a break. This should last 10-15 min.

4. Look at the result with "Preview Result" and use the navigation pane to observe the before/after

5. Apply the model to the dataset and upload results to OMERO → Start with this step if you already have a trained model for your images