All,<div> I'm using ThresholdSegmentationLevelSetImageFilter for a 2D application. It works really well for me and is automated for the most part. I would really appreciate it if someone can help me understand the filter better by answering the following questions:</div>
<div><br></div><div>(i) I'm using the output from ConfidenceConnectedImageFilter as the initial level set for the threshold level set filter. I used a replacement value of 255 for the connected confidence filter. In other words, the input image to the threshold level set filter is a binary image with 255 representing the region of interest (and 0 outside of it). I therefore expect the iso-surface value for the threshold level set filter to be set to 255. However any value other than 0 did not work. What 'am I missing here?</div>
<div><br></div><div>(ii) I did not set the upper and lower threshold values for the threshold level set filter and it still works. How?</div><div><br></div><div>(iii) Since I'm using a threshold level set filter with confidence connected image as the input should I still use a zero crossing image filter to get the output?</div>
<div><br></div><div>(iv) I see from the documentation that I can get a speed image for the threshold level set filter. What's a speed image?</div><div><br></div><div>(v) Can someone please point me to a paper/article that describes in detail the effect of the different constants in Equation 9.3 from the ITK Software Guide? (I want to learn more about the effect of the advection, propagation and spatial modifier terms).</div>
<div><br></div><div>Thanks</div><div>Prashanth</div><div> </div>