Re: SKM Cross sectional area measurement

Posted by Adam Hughes on Jan 30, 2014; 6:08pm
URL: http://imagej.273.s1.nabble.com/SKM-Cross-sectional-area-measurement-tp5006330p5006344.html

Hi Steve,

While I have not tried it myself, I think the trainable segmentation (weka)
might be able to help:

http://fiji.sc/Trainable_Weka_Segmentation

I've had success with a similar, but non ImageJ product for trainable
segementation as well called ilastik:

http://ilastik.org/


On Thu, Jan 30, 2014 at 6:21 AM, stevefaulkner <[hidden email]>wrote:

> Yes they are all saved as tif files! The aim is to generate a CSA for each
> cell within the image, but ignoring those that come ito contact with the
> edges. So far I have been doing this by creating and ROI and then manually
> measuring a selections of cells, which is less than ideal! As you suggest,
> I
> have been doing this using the green channel alone, I just wanted to show a
> complete image as I'll also be analysing the density and activation of a
> number of other cell within the image.
>
> When I have tried to threshold the image, the problem that I get is that
> the
> fluoro isn't uniform throughout, so each cell often becomes grainy and is
> no
> longer recogonised as a single entity as defined by the cell membrane.
>
> I will have a number of images to analyse but so far they are just stored
> as
> each composite image (each filter) of the total overlay in a single file
> from a single field of view, all within a subject specific folder.
>
> Steve
>
>
>
> --
> View this message in context:
> http://imagej.1557.x6.nabble.com/SKM-Cross-sectional-area-measurement-tp5006330p5006338.html
> Sent from the ImageJ mailing list archive at Nabble.com.
>
> --
> ImageJ mailing list: http://imagej.nih.gov/ij/list.html
>

--
ImageJ mailing list: http://imagej.nih.gov/ij/list.html