Last modified by puchades on 2021/12/07 10:37
From version 16.3
edited by puchades
on 2020/04/07 15:52
Change comment: There is no comment for this version
To version 16.6
edited by puchades
on 2020/04/07 15:57
Change comment: There is no comment for this version

Summary

Details

Page properties
Content
... ... @@ -6,7 +6,7 @@
6 6  
7 7  For //QuickNII,// the input requirements are described in details in Puchades et al., 2019. To summarise, images should be in 24-bit PNG or JPEG format, with a resolution up to 16 megapixels (e.g. 4000x4000 or 5000x3000 pixels). Keep in mind that QuickNII does not benefit from image resolutions exceeding the resolution of the monitor in use. For a standard FullHD or widescreen display (1920x1080 or 1920x1200 pixels) the useful image area in QuickNII is approximately 1500x1000 pixels. Using a similar resolution ensures optimal image-loading performance.
8 8  
9 -For //ilastik// (Borg et al.2019) images are downscaled in order to enable efficient processing. The pixel classification algorithm relies on input from manual user annotations of the training images, and the features ‒ intensity, edge and/or texture ‒ of the image pixels. The resizing factor is determined by trial and error, with a test run performed with //ilastik// on images of different sizes to determine the optimal resolution for segmentation. As an example, in Yates et al., 2019, the images were downscaled by a factor of 0.1 and 0.05 for cellular features and Alzheimer's plaques respectively (factor applies to the image width here).
9 +For //ilastik// (Borg et al.2019), images are downscaled in order to enable efficient processing. The pixel classification algorithm relies on input from manual user annotations of the training images, and the features ‒ intensity, edge and/or texture ‒ of the image pixels. The resizing factor is determined by trial and error, with a test run performed with //ilastik// on images of different sizes to determine the optimal resolution for segmentation. As an example, in Yates et al., 2019, the images were downscaled by a factor of 10 for cellular features, and a factor of 20 for Alzheimer's plaques with respect to image width.
10 10  
11 11  == (% style="color:#c0392b" %)Naming convention(%%) ==
12 12  
... ... @@ -19,6 +19,6 @@
19 19  
20 20  == (% style="color:#c0392b" %)Running the transformation(%%) ==
21 21  
22 -Consult the Nutil user manual for detailed procedure (lincluded in the Nutil package available for download at Nitrc.org)
22 +Consult the Nutil user manual for the detailed procedure (included in the Nutil package available for download at [[https:~~/~~/www.nitrc.org/projects/nutil/>>url:https://www.nitrc.org/projects/nutil/]]))
23 23  
24 24  [[image:Figure_2_v3.jpg]]