Step-by-Step Protocol for Using Convpaint
Convpaint Usage in Napari:
Open your data:
Launch Napari from the terminal:
conda activate napari_env
napari
Open your image via File > Open.
Open Convpaint:
Go to Plugins > Convpaint.
The Convpaint panel will appear in the interface.
Create annotations:
Add an annotation layer to create a labels layer.
Draw your annotations:
Use the brush tool to paint regions.
If you want to detect one type of object, use:
Label 1: background
Label 2: foreground
Image type and normalization:
Select the correct image type:
Single channel image
Multichannel image
RGB image
Choose a normalization method:
No normalization
Normalize over stack
Normalize by plane
Train and segment:
Click Train to train the pixel classifier
Click Segment Image to apply the model.
If Auto segment is enabled, segmentation runs automatically after training.
If segmentation is not accurate:
Add more annotations.
Click Train again.
Re-run segmentation.
Convert binary segmentation into instances:
To convert the binary segmentation into individual object instances, install the plugin inside Napari:
napari-segment-blobs-and-things-with-membranes
Open the plugin from:
Tools > Segment blobs and things with membranes
Select:
Connected Component labeling.
Choose your binary segmentation image and run.
A new labels will be created where each connected object has an independent label ID.
Save the model:
Click Save model.
You have two options:
.yml file: saves only the model settings.
.pkl file: saves the full trained model.
Reload a model:
Click Load Model.
Select a previously saved .yml or .pkl file.