Warning:  The EBRAINS Lab will be down today from 21:00 CEST (my timezone)  for ~10 minutes for an update


Last modified by annedevismes on 2021/06/08 11:56
From version 11.1
edited by evanhancock
on 2020/07/21 09:34
Change comment: There is no comment for this version
To version 20.1
edited by puchades
on 2020/09/24 12:17
Change comment: There is no comment for this version

Summary

Details

Page properties
Author
... ... @@ -1,1 +1,1 @@
1 -XWiki.evanhancock
1 +XWiki.puchades
Content
... ... @@ -1,17 +1,17 @@
1 1  == [[image:ilastik_logo.PNG||style="float:right"]] ==
2 2  
3 -== (% style="color:#c0392b" %)Analysis approach for series of rodent brain section image(%%) ==
3 +== [[image:Pixel_classification workflow.png||style="float:left"]](% style="color:#c0392b" %)Analysis approach for series of rodent brain section image(%%) ==
4 4  
5 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.
6 6  
7 -There are two main approaches for the analysis of rodent brain section images.
7 +**There are two main approaches for the analysis of rodent brain section image**
8 8  
9 9  1. Pixel classification only (with two or more classes)
10 -1. Pixel classification with two classes (//immunoreactivity// and //background//), followed by object classification with two classes (//objects of interest// and //artefact//).
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 12  **Which approach is best for my dataset?**
13 13  
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 based on object level features such as size and shape. The best approach is determined by trial and error.
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 based on object level features such as shape and size. The best approach is determined by trial and error.
15 15  
16 16  === (% style="color:#c0392b" %)Pixel classification workflow(%%) ===
17 17  
... ... @@ -19,7 +19,7 @@
19 19  
20 20  **Basic steps:**
21 21  
22 -* Train the classifier with two classes (labeling and background)
22 +* Train the classifier with two classes (labelling and background)
23 23  * Apply the classifier to the rest of the images (batch processing)
24 24  * Export the probability maps in HDF5 format, and simple_segmentation images in PNG format with the default settings.
25 25  * 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