<div>Dear Daniel</div>
<div>Thank you for your answer. This looks very interresting I think.</div>
<div>Could this filter also be used for a coupled shape model i wonder?</div>
<div> </div>
<div>A coupled shape model is where i have several regions represented in my same shape model. This means that i simulataneously can segment many regions, and use the prior knowledge of the spatial position of the different regions, which i have also captured in my shape model.
</div>
<div>For more information of the strongly coupled model, this article gives a good insight:</div>
<div>
<div><a href="http://ssg.mit.edu/group/alumni/atsai/Papers/IPMI03.pdf">http://ssg.mit.edu/group/alumni/atsai/Papers/IPMI03.pdf</a></div>
<div> </div>
<div>I hope to hear from you or anybody else soon.</div>
<div>Yours Sincerely</div>
<div>Arne Hansen<br><br> </div></div>
<div><span class="gmail_quote">2007/1/26, Daniel Mace <<a href="mailto:dlm19@duke.edu">dlm19@duke.edu</a>>:</span>
<blockquote class="gmail_quote" style="PADDING-LEFT: 1ex; MARGIN: 0px 0px 0px 0.8ex; BORDER-LEFT: #ccc 1px solid">Arne,<br><br>Is your question: what methods are out there that you can use (but would<br>need to implement), or what methods are in ITK/VTK that you could use?
<br>The standard shape model in ITK is the the work done by Leventon et al.<br>(<br><a href="http://spl.bwh.harvard.edu:8000/pages/papers/leventon/cvpr00/cvpr00.pdf">http://spl.bwh.harvard.edu:8000/pages/papers/leventon/cvpr00/cvpr00.pdf
</a><br>). His method basically relies on the observation that the gradient of<br>an image is inversely related to a signed distance map and created a MAP<br>estimate from it. If you already have your mean + modes of variation
<br>then using his method should be easy to implement (easy to implement,<br>getting the parameters to converge might take a bit). It's described in<br>9.3.7 in the ITK software guide.<br><br>Cheers,<br>Dan<br><br>Arne Hansen wrote:
<br>> Hello. I have a question regarding the use of shape models built using<br>> Signed Distance Maps(Level Set Function).<br>> I have applied a principal component analysis on my Level Set<br>> Functions, and found a meanshape + modes of variation.
<br>> I now need to use these as prior information in a segmentation model<br>> where certain regions(those which my shape model represent) needs to<br>> be segmeneted.<br>> I am however unsure of how i can do this. So my question is if an
<br>> Active Appearance Model technique can be used when i have built my<br>> shape model on Level Set Functions, or if i actually need to do it on<br>> landmarks.<br>><br>> Is there other methods to use?<br>
> Maybe you can recommend a method to use.<br>> Thank you very much, and best of regards.<br>> Arne Hansen<br>> ------------------------------------------------------------------------<br>><br>> _______________________________________________
<br>> This is the private VTK discussion list.<br>> Please keep messages on-topic. Check the FAQ at: <a href="http://www.vtk.org/Wiki/VTK_FAQ">http://www.vtk.org/Wiki/VTK_FAQ</a><br>> Follow this link to subscribe/unsubscribe:
<br>> <a href="http://www.vtk.org/mailman/listinfo/vtkusers">http://www.vtk.org/mailman/listinfo/vtkusers</a><br>><br><br></blockquote></div><br>