<DIV>Hi Celina,</DIV>
<DIV>I'm appreciated for your detailed answer. In order to understand this method better, I should read your old paper:</DIV>
<DIV>Imielinska, C.; Downes, M; and Yuan, W., "Semi-Automated Color<BR>Segmentation of Anatomical Tissue", Journal of Computerized Medical<BR>Imaging and Graphics, 24(2000), 173-180, April, 2000</DIV>
<DIV>However, I can not get this paper. Could you please do me a favor and send a copy of this paper to me?</DIV>
<DIV>Is it possible to draw the triangle mesh of the middle result of the iteration of Voronoid diagram like the figures in your paper? Which class of ITK should I use?</DIV>
<DIV> </DIV>
<DIV> </DIV>
<DIV>Thank you very much!</DIV>
<DIV> </DIV>
<DIV> </DIV>
<DIV>Best regards,</DIV>
<DIV> </DIV>
<DIV>Jane<BR><BR><B><I>Celina Imielinska <ci42@columbia.edu></I></B> wrote:</DIV>
<BLOCKQUOTE class=replbq style="PADDING-LEFT: 5px; MARGIN-LEFT: 5px; BORDER-LEFT: #1010ff 2px solid"><BR>Jane,<BR><BR>the most detailed description of the Voronoi diagram classifier<BR>(without the fuzzy connectedness part) you can find in my old paper:<BR><BR>Imielinska, C.; Downes, M; and Yuan, W., "Semi-Automated Color<BR>Segmentation of Anatomical Tissue", Journal of Computerized Medical<BR>Imaging and Graphics, 24(2000), 173-180, April, 2000.<BR><BR>in the hybrid method that is a combination of (simple) fuzzy <BR>connectedness and voronoi classification, we use the simplest version of <BR>otherwise "stand-alone" fuzzy connectedness segmentation (look at other <BR>fuzzy connectedness filters provided by the itk), to derive statistics for <BR>a homogeneity operator for the tissue that we are segmenting. We do need <BR>a well defined homogeneity operator (in theory, it can be provided by<BR>"any" method that can do it "well") to "drive" the subdivisions in the<BR>iterative voronoi
classification part of the hybrid method. In the voronoi <BR>classification, random points are thrown at the image, and each voronoi <BR>region, in the voronoi diagram, is classified as <BR>interior/exterior/boundary depending how "close" it is to the <BR>characteristics of the homogeneity operator. We iterate the method and <BR>keep subdividing the boundary voronoi regions only, until the method <BR>converges to the boundary of the object/organ (in the process, we keep <BR>"pushing" the interior inside-out, and the exterior outside-in, and <BR>squizze the boundary in-between, until stopping ctriteria "kick-in).<BR><BR>The estimated mean and standard deviation and other parameters that are <BR>automatically computed from a sample 3D region segmented by the <BR>(simple) fuzzy, can be stored and applied to a new image (same tissue, <BR>same image modality etc.). This method hinges on the "quality" of the <BR>homegeneity operator. We can store the homogeneity operators as a database
<BR>for same tissue/organ, same image modality, etc.<BR><BR>if you need more details, please let us know (Yinpeng Jin yj76@columbia <BR>can answer all questions, too),<BR><BR>-Celina<BR><BR><BR><BR>On Thu, 26 Aug 2004, Jane Meinel wrote:<BR><BR>> Dear itk-users,<BR>> I tried the example of HybridSegmentationFuzzyVoronoi. It is quite good<BR>> image segmentation frame.<BR>> Now I have some questions about this example:<BR>><BR>> *1. In the example image case BrainT1Slice.png, the parameters are: 140 125<BR>> 140 25 0.2 2.0. Among them, (140, 125) is the seed position. It is <BR>> obviously. However, "140 and 25 are the estimated mean and standard <BR>> deviation, respectively, of the object to be segmented. Finally, 0.2 <BR>> and 2.0 are the tolerance for the mean and standard deviation, <BR>> respectively." What do those parameters mean? If I want to segment <BR>> another image, how should I set those parameters by myself?<BR>><BR>> *2. In
the BrainT1Slice.png case, the voronoi diagram classification<BR>> improves the segmentation a lot after the fuzzy connectedness <BR>> segmentation step. I want to know details about the voronoi diagram <BR>> classification. I have read the paper "Hybrid Segmentation of Anotomical <BR>> Data", which is written by Celina Imielinska, Dimitris Metaxas, Jayaram <BR>> Udupa, Yinpeng Jin, Ting Chen, and published in MICCAI 2001. But it <BR>> doesn't describe very clear about voronoi diagram classification. Which <BR>> paper should I read in order to understand this algorithm better?<BR>><BR>> *3. I'm impressed deeply by the figures of the paper mentioned about,<BR>> which show the result of the iterations of VD-based algorithm. How can I <BR>> draw such pictures by ITK classes? I want to know the procedure in <BR>> different iterate step of Voronoi Diagram algorithm.<BR>><BR>><BR>> Any help is much appreciated! Thanks a
lot!<BR>><BR>><BR>> Jane<BR>><BR>><BR>> ---------------------------------<BR>> Do you Yahoo!?<BR>> Yahoo! Mail - 50x more storage than other providers!<BR></BLOCKQUOTE><p>
<hr size=1>Do you Yahoo!?<br>
<a href="http://us.rd.yahoo.com/mail_us/taglines/10/*http://promotions.yahoo.com/new_mail/static/efficiency.html">New and Improved Yahoo! Mail</a> - Send 10MB messages!