Just to build a little on what Luis wrote, many of the algorithms require seed-points, but that doesn't necessarily imply "interactively" specified seed-points. ITK implements the algorithms, but leaves the specification of the seed-points up to the user of the algorithm. If you have some innovative way of automatically providing seed-points for one or more anatomical structures those points can be used in place of interactive selection.
<br><br>- Wes<br><br><div><span class="gmail_quote">On 7/5/07, <b class="gmail_sendername">Luis Ibanez</b> <<a href="mailto:luis.ibanez@kitware.com">luis.ibanez@kitware.com</a>> wrote:</span><blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">
<br>Hi Kambiz,<br><br><br>It all depends on how large is your classification of "Region Growing".<br><br>What we formally call "Region Growing" methods in ITK: all require<br>seed points or initial regions as input data.
<br><br><br>If you consider Watersheds to be a Region Growing method, then that will<br>qualify for your question. Most Level Set methods could arguably be<br>called "Region Growing" methods too.<br><br><br>That being said, what you described is a pretty "Magical" method, since
<br>it is not clear to me *what* are you segmenting from the image. That is,<br>a typical medical image will contain mutliple organs, and at some point<br>you have to specify which one of all of those organs you are interested
<br>in segmenting, unless the segmentation method produces a total partition<br>of the image... and stil we will have to ask if the blood vessels inside<br>an organ should be classified as part of the organ or as part of the
<br>circulatory system...<br><br><br>The description of this "magical" method sounds very appealing for a<br>standard paper to be submitted to one of the many decadent journals<br>and conferences in our field, where the main interest is to qualify for
<br>the "originality cookie" by claiming that the content of the paper is<br>some "never seen before" method.<br><br><br>It doesn't sound like the serious method that you may want to use<br>for an actual medical application.
<br><br><br><br> Regards,<br><br><br> Luis<br><br><br><br>------------------------<br>kambiz rakhshan wrote:<br>> Hi all users,<br>> /I Would like to know if there is an algorithm in ITK that /is proposed<br>
> for the automated segmentation of three-dimensional images. No initial<br>> parameters such as the homogeneity threshold or the seeds location have<br>> to be adjusted. The principle of this method is to build a region
<br>> growing sequence by increasing the maximal homogeneity threshold from a<br>> very small value to a large one. On each segmented region, a 3D<br>> parameter that has been validated on a test image assesses the
<br>> segmentation quality.<br>><br>> All the region growing algorith which nis developed by ITK need seed<br>> points interactively.Is that right?<br>> any comments will be appreciated.<br>> Kambiz<br>>
<br>><br>> ------------------------------------------------------------------------<br>> Moody friends. Drama queens. Your life? Nope! - their life, your story.<br>> Play Sims Stories at Yahoo! Games.<br>> <
<a href="http://us.rd.yahoo.com/evt=48224/*http://sims.yahoo.com/">http://us.rd.yahoo.com/evt=48224/*http://sims.yahoo.com/</a>><br>><br>><br>> ------------------------------------------------------------------------
<br>><br>> _______________________________________________<br>> Insight-users mailing list<br>> <a href="mailto:Insight-users@itk.org">Insight-users@itk.org</a><br>> <a href="http://www.itk.org/mailman/listinfo/insight-users">
http://www.itk.org/mailman/listinfo/insight-users</a><br>_______________________________________________<br>Insight-users mailing list<br><a href="mailto:Insight-users@itk.org">Insight-users@itk.org</a><br><a href="http://www.itk.org/mailman/listinfo/insight-users">
http://www.itk.org/mailman/listinfo/insight-users</a><br></blockquote></div><br><br clear="all"><br>-- <br>Wesley D. Turner, Ph.D.<br>Kitware, Inc.<br>R&D Engineer<br>28 Corporate Drive<br>Clifton Park, NY 12065-8662<br>
Phone: 518-371-3971 x120