Dawood,<div> Thanks to your email, I figured out how to do it. 'am just posting my pipeline here just in case someone else stumbles on it - </div><div><br></div><div>(here's the pipeline I used for 2D liver segmentation using ITK filters)</div>
<div><br></div><div> </div><div><span class="Apple-style-span" style="border-collapse: collapse; font-family: arial, sans-serif; font-size: 13px; ">Input 2D slice ----> Curvature Flow Image Filter ----> Confidence Connected --------------> Threshold Level Set Segmentation -----> median filter </span></div>
<div><span class="Apple-style-span" style="border-collapse: collapse; font-family: arial, sans-serif; font-size: 13px; "> | |</span></div>
<div><span class="Apple-style-span" style="border-collapse: collapse; font-family: arial, sans-serif; font-size: 13px; "> | |</span></div>
<div><span class="Apple-style-span" style="border-collapse: collapse; font-family: arial, sans-serif; font-size: 13px; "> |----------------------------------------------> Rescale Intensity Image Filter ----------------------------------------</span></div>
<div><font class="Apple-style-span" face="arial, sans-serif"><span class="Apple-style-span" style="border-collapse: collapse;"> </span></font></div>
<div><font class="Apple-style-span" face="arial, sans-serif"><span class="Apple-style-span" style="border-collapse: collapse;"><br></span></font></div><div><font class="Apple-style-span" face="arial, sans-serif"><span class="Apple-style-span" style="border-collapse: collapse;">( output from rescale intensity image filter = </span></font><span class="Apple-style-span" style="border-collapse: collapse; font-family: arial, sans-serif; ">feature image for threshold level set filter</span></div>
<div><font class="Apple-style-span" face="arial, sans-serif"><span class="Apple-style-span" style="border-collapse: collapse;"> </span></font><span class="Apple-style-span" style="border-collapse: collapse; font-family: arial, sans-serif; ">output from confidence connected filter = </span><span class="Apple-style-span" style="border-collapse: collapse; font-family: arial, sans-serif; ">input image )</span></div>
<div><span class="Apple-style-span" style="border-collapse: collapse; font-family: arial, sans-serif; "><br></span></div><div><span class="Apple-style-span" style="border-collapse: collapse; font-family: arial, sans-serif; ">Thanks again,</span></div>
<div><span class="Apple-style-span" style="border-collapse: collapse; font-family: arial, sans-serif; ">Prashanth</span></div><div><br><div class="gmail_quote">On Thu, Jul 28, 2011 at 11:30 AM, Prashanth <span dir="ltr"><<a href="mailto:prashanth.dumpuri@gmail.com">prashanth.dumpuri@gmail.com</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex;">Dawood,<div> Thanks for getting back to me. So, are you suggesting that I pass my input image through a Sigmoid Image Filter to map the intensities to the same range as the binary image output by the confidence connected filter?</div>
<div>Thanks again</div><div>Prashanth</div><div><div></div><div class="h5"><div><br><br><div class="gmail_quote">On Wed, Jul 27, 2011 at 9:06 AM, Dawood AlMasslawi <span dir="ltr"><<a href="mailto:masslawi@gmail.com" target="_blank">masslawi@gmail.com</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">Hi Prashanth,<div><br></div><div>I hope I have understood your question correctly! if you are trying to </div><div><br>
</div><div>intensify a certain range of intensity values the SigmoidImageFilter </div><div><br></div><div>
is the way to go.</div><div><br></div><div>HTH,</div><div>Dawood</div><div><div></div><div><div><br></div><div><br></div><div>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<</div>
<div><br></div><div><br></div><div><span style="font-family:'Times New Roman';font-size:medium"><pre>All,
I'm working on 2D segmentation using ITK filters and right now my
pipeline looks like this:
Input 2D slice ----> Curvature Flow Image Filter ----> Confidence Connected
----> Threshold Level Set Segmentation.
I'm using the input slice as the feature image for the level set filter and
the binary image outputted from the confidence connected as the input image
for the level set filter. Ideally I would like to set the intensity range of
the threshold level set filter to be the same that was computed by the
confidence connected filter. But for the level set filter, I have a binary
image as the feature image and the input 2D slice as the input image. How do
I ensure that the intensities match?
Thanks
Prashanth</pre></span></div>
</div></div></blockquote></div><br></div>
</div></div></blockquote></div><br></div>