Versions Compared

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.
Comment: Making formatting changes following editor conversion; content updates are still needed

The Phase Cell Tracking recipe in Aivia detects cells and tracks their motility over time in time-lapse phase contrast microscopy images. The recipe applies a machine learning-based algorithm for cell segmentation. The recipe measures the motion attributes of the detected cells for comprehensive characterization of cell migrations.

Panel

On this page:

Table of Contents
maxLevel
minLevel
3
1
exclude
maxLevel
[4]
5

Parameters and Presets

Parameters

Recipe parameters for Phase Cell Tracking and their descriptions are summarized in the table below.

Preset Group

Parameter Name

Min Value

Max Value

Description

Detection

Background Flattening Factor

0

100

Adjusts the sensitivity of the background flattening operation; a lower value will preserve larger objects and more background variations

Contrast Threshold

0

255

Adjusts the detection sensitivity on the machine learning-enhanced image; a lower value will detect bigger and more objects

Fill Holes Size

0

50,000

Adjusts the maximum size threshold for filling in gaps inside a detected object; a lower value will preserve more holes in the detection

Smoothing Factor

0

100

Adjusts the amount of smoothing applied to the outline of the detected objects; a lower value will preserve more of the object's morphological features

Tracking


Object Size

0

1,000,000

Specifies the range of objects to be included in the analysis results based on the area of the detected objects

Max Search Range

0

1,000

Specifies the maximum distance for track-point matchmaking between successive time frames; a higher value will expand the search distance for fast-moving cells

Min Track Length

0

1,000

Specifies the minimum number of time frames before a detected object is considered a valid track; a lower value will generate more, and often shorter, tracks

Separation Factor

1

100

Adjusts the sensitivity of the object separation operation, a lower value will preserve larger objects with multiple intensity peaks

Presets

There are two preset groups in the recipe: Detection and Tracking; each group has three pre-configured parameter groupings to help you get started on the analysis. The default preset values are as follows:

Detection

Parameter Name

Low

Medium

High

Background Flattening Factor

50

60

63

Contrast Threshold

185

120

70

Fill Holes Size

50

500

1,000

Smoothing Factor

1

2

4


Partition

Tracking

Parameter Name

Small

Low

Medium

Large

High

Object Size

1 - 250

50 - 1,000

150 - 6,000

Max Search Range

20

20

20

Min Track Length

8

8

8

Separation Factor

50

70

85


Measurements

The Phase Cell Tracking recipe generates track measurements for each detected cell. You can add additional measurements to the analysis results by using the Measurement Tool in Aivia. The measurements generated by the recipe are as follows.

Morphological

Track

  • Area

  • Circularity

  • Total Time

  • First Frame

  • Last Frame

  • Straight Line Length (instantaneous)

  • Straight Line Velocity (instantaneous)

  • Acceleration Magnitude (instantaneous)

  • Velocity Magnitude (instantaneous)


Tutorial

Before beginning the tutorial, please download the Phase Cell Tracking 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.

  1. Unzip the demo file and load the demo image, PhCellTrackDemo.tif, into Aivia

  2. In the Recipe Console, click on the Recipe selection dropdown menu and select the Phase Cell Tracking recipe

  3. Select the Medium presets for both the Detection and Tracking preset groups

  4. Click the Start button or press the F4 key on your keyboard to begin applying the recipe to the image


The detected object outlines and tracks will be overlaid on the image.

Results

multimedia

name

PhCellTrackDemo_output.mp4

Phase Cell Tracking results


Filter by label (Content by label)
showLabelsfalse
max5
spacescom.atlassian.confluence.content.render.xhtml.model.resource.identifiers.SpaceResourceIdentifier@836
sortmodified
showSpacefalse

sortmodified

reversetrue
typepage
cqllabel in ( "2d" , "tracking" ) and type = "page" and space = "AW"
labelsrecipes image_analysis analysis EM 3d
Page Properties
hiddentrue

Related issues