Multiplexed Cell Detection Recipe

The Multiplexed Cell Detection recipe in Aivia is based on Cellpose, a generalist deep-learning based algorithm for cellular segmentation. This recipe is designed for 2D data.

The recipe detects cell membrane and nuclear membrane using multiple membrane marker channels and a single nucleus marker channel.

On this page:

1 Inputs and Outputs
2 Parameters and Presets
- 2.1 Parameters
- 2.2 Presets
3 Tutorial (written steps)
4 Tutorial (videos)
5 Related Articles

Inputs and Outputs

Recipe inputs and outputs for Multiplexed Cell Detection and their descriptions are summarized in the table below.

	Name	Description

	Name	Description
Inputs	Deep Learning Model	(Optional) Select a deep learning model to apply before this recipe is applied
	Input Nucleus Image	Select the channel which contains the nuclei of cells in the image
	Input Cell Membrane Images	Select the membrane marker channels to be used while detecting cells in this recipe
Outputs	Cells	Select the object set to which the results of the detection are outputted. Defaults to creating a new object set

Parameters and Presets

Parameters

Recipe parameters for Multiplexed Cell Detection and their descriptions are summarized in the table below.

Preset Group	Parameter Name	Min Value	Max Value	Description

Preset Group	Parameter Name	Max Value	Description
Nucleus Detection	Nucleus Probability Threshold	100	Adjusts the sensitivity of nucleus detection. Higher values mean lesser number of detected cells
	Nucleus Diameter	65535 px	Indicates the estimated diameter of typical cells
	Min Nucleus Size	65535 px² or µm²	Filters out and ignores nuclei of size smaller than this parameter
	Nucleus Expansion Distance	65535	If no cell membrane is detected corresponding to a nucleus, the cell membrane is generated by expanding the nuclear membrane by a distance specified by this parameter
Cell Membrane Detection	Cell Membrane Probability Threshold	100	Adjusts the sensitivity of cell membrane detection. Higher values mean lesser number of detected cells membranes

Presets

There are two preset groups in the recipe: Nucleus Detection and Cell Membrane Detection. Each group has three pre-configured parameter groupings to help you get started on the analysis. The default preset values are in the sections to follow.

Nucleus Detection

Parameter Name	Small	Medium	Large
Nucleus Probability Threshold	10	10	10
Nucleus Diameter	10 px or µm	20 px or µm	30 px or µm
Min Nucleus Size	20 px² or µm²	50 px² or µm²	100 px² or µm²
Nucleus Expansion Distance	2 px or µm	4 px or µm	6 px or µm

Cell Membrane Detection

Parameter Name	Low	Medium	High
Cell Membrane Probability Threshold	10	50	90

Tutorial (written steps)

Before beginning the tutorial, please download the Multiplexed Cell Detection Demo image. For information on how to select presets or modify parameter values, please refer to the tutorial on how to use the Recipe Console.

Unzip the demo file and load the demo image, “MultiplexedCellDetectionDemo.aivia.tif,” into Aivia.
Set the calibration to 0.325 µm
In the Recipe Console, click on the Recipe selection dropdown menu and select the Multiplexed Cell Detection recipe.
Select the DAPI channel in the dropdown menu for Input Nucleus Image
Select following membrane marker channels in the dropdown menu for Input Cell Membrane Images:
- CD3
- CD45
- CD4
- CD8
- GLUT1
- HLA1
- NAK
- PCAD
Select the Small preset for the Nucleus Detection group and the Medium preset for the Cell Membrane Detection group.
Click on the Show Advanced Interface icon to expand the Recipe Console and show parameter options for the recipe.
Modify the parameter values in the recipe as follows while leaving the other values intact:
- Nucleus Probability Threshold: 30
- Nucleus Diameter: 5.5 µm
- Min Nucleus Size: 15 µm²
- Cell Membrane Probability Threshold: 40
Click the Start button or press the F4 key on your keyboard to begin applying the recipe to the image.

The detected nuclear and cell membrane outlines will be overlaid on the image.

Multiplexed Cell Detection tutorial results

Results at 100% scaling