Re: Nuclei segmentation

Posted by Michael Schmid on Mar 18, 2014; 9:46am
URL: http://imagej.273.s1.nabble.com/Nuclei-segmentation-tp5006953p5006967.html

Hi Chin,

watershed (more exactly, watershed of the Euclidian Distance map) does not help because it is essentially meant for circular or near-circular particles.
The only chance for better segmentation I see is trying to enhance the weak dark lines where the nuclei touch, and make them dividing lines in the binary image. Then watershed might do the job.

Michael
________________________________________________________________
On Mar 18, 2014, at 08:14, chin wrote:

> Thank you all your answer.
>
> Yeah, it seems no better ways to use watershed method to split connections
> between such irregular
> objects right now. I could only do is draw the lines to split them manully.
> But it takes much time and
> quite laborious job. Hopefully, there will be some labor-saving method for
> imagej developed by some
> experts.
>
> best,
> chin
>
>
>
> --
> View this message in context: http://imagej.1557.x6.nabble.com/Nuclei-segmentation-tp5006953p5006964.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