Attention: The Keycloak upgrade has been completed. As this was a major upgrade, there may be some unexpected issues occurring. Please report any issues you find to support by using the contact form found at https://www.ebrains.eu/contact/. Thank you for your patience and understanding. 


Last modified by annedevismes on 2021/06/08 11:56
From version 1.5
edited by puchades
on 2020/03/25 14:46
Change comment: There is no comment for this version
To version 20.2
edited by annedevismes
on 2021/06/08 10:57
Change comment: There is no comment for this version

Summary

Details

Page properties
Author
... ... @@ -1,1 +1,1 @@
1 -XWiki.puchades
1 +XWiki.annedevismes
Content
... ... @@ -1,33 +1,35 @@
1 -== Analysis approach for series of rodent brain section image ==
1 +== [[image:ilastik_logo.PNG||style="float:right"]] ==
2 2  
3 -There are two main approaches for the analysis of rodent brain section images.
3 +== [[image:Pixel_classification workflow.png||style="float:left"]](% style="color:#c0392b" %)Analysis approach for series of rodent-brain section image(%%) ==
4 4  
5 -1. Pixel classification only (with two or more classes)
6 -1. Pixel classification with two classes (//immunoreactivity// and //background//), followed by object classification with two classes (//objects-of-interest// and //artefact//).
5 +//Ilastik //is a versatile image analysis tool specifically designed for the classification, segmentation, and analysis of biological images based on supervised machine-learning algorithms.
7 7  
8 -**Which approach is best for my dataset?**
7 +**There are two main approaches for the analysis of rodent-brain section image~:**
9 9  
10 -As a general rule, pixel classification is suitable for images in which there are clear differences in the colour, intensity and/ or texture of the feature-of-interest versus the background and other structures.  If there is non-specific labelling in the image that is very similar in appearance to the labelling-of-interest, object classification may allow the non-specific labelling to be filtered out based on object level features such as size and shape. The best approach is determined by trial and error.
9 +1. pixel classification only (with two or more classes) and
10 +1. pixel classification with two classes (//immunoreactivity// and //background//), followed by Object classification with two classes (//objects of interest// and //artefact//).
11 11  
12 +**Which approach is best for my dataset?**
12 12  
13 -=== H3 Headings Will Appear In The Table of Content ===
14 +As a general rule, pixel classification is suitable for images in which there are clear differences in the colour, intensity, and / or texture of the feature of interest (labelling) versus the background and other structures.  If there is non-specific labelling in the image that is very similar in appearance to the labelling of interest, object classification may allow the non-specific labelling to be filtered out on the basis of the object-level features such as shape and size. The best approach is determined by trial and error.
14 14  
15 -==== You can also add images ====
16 +=== (% style="color:#c0392b" %)Pixel classification workflow(%%) ===
16 16  
17 -[[image:Collaboratory.Apps.Article.Code.ArticleSheet@placeholder.jpg]]
18 +For a quick introduction, [[watch this video>>https://www.youtube.com/watch?v=5N0XYW9gRZY&feature=youtu.be]].
18 18  
19 -Photo by David Clode
20 +**Basic steps**
20 20  
21 -==== Or code ====
22 +* Train the classifier with two classes (labelling and background).
23 +* Apply the classifier to the rest of the images (batch processing).
24 +* Export the probability maps in HDF5 format and simple_segmentation images in PNG format with the default settings.
25 +* Review the results.
22 22  
23 -Code blocks can be added by using the code macro:
27 +=== (% style="color:#c0392b" %)Object-classification workflow(%%) ===
24 24  
25 -{{code language="python"}}
26 -x = 1
27 -if x == 1:
28 - # indented four spaces
29 - print("x is 1.")
30 -{{/code}}
29 +There are three options on the //ilastik //start-up page for running Object Classification. Choose the //Object Classification with Raw Data and Pixel Prediction Maps //as input.
31 31  
32 -(% class="wikigeneratedid" id="HH4Won27tAppearinToC" %)
33 -
31 +* Save the object-classification file in the same folder as the raw images for analysis. If the images are moved after the //ilastik// file is created, the link between the //ilastik //file and the images may be lost, resulting in a corrupted file.
32 +* In the "Input Data" applet, upload the original images and their respective probability maps in HDF5 format (output from the Pixel Classification).
33 +* Train the classifier with two classes (labelling and artefacts).
34 +* In the "Object Information Export" applet, export “Object Predictions” in PNG format.  Do not change the default export location.
35 +* Review the results.
Pixel_classification workflow.png
Author
... ... @@ -1,0 +1,1 @@
1 +XWiki.puchades
Size
... ... @@ -1,0 +1,1 @@
1 +1.0 MB
Content
ilastik_logo.PNG
Author
... ... @@ -1,0 +1,1 @@
1 +XWiki.puchades
Size
... ... @@ -1,0 +1,1 @@
1 +6.0 KB
Content