 |
 |
Dear All, I have a question on the segmentation algorithm. As far as I understand it, segmentation works by making an initial probability estimate as to which tissue type a voxel most likely belongs to (based on the a priori-data) and then proceeds to do a cluster analysis (based on pixel intensity). My question is, what is the "usual" contribution of these two steps to the end-result ? Is the first or the second step more decisive ? I am aware of the 1997 paper on this, but was looking for a more informal assessment... Thanks! Marko -- =============================================== Marko Wilke, MD Research Fellow, Imaging Research Center Children's Hospital Research Foundation 3333 Burnet Avenue - ML 5031 Cincinnati, OH 45229 Phone +1 (513) 636-0142 FAX +1 (513) 636-3754 [log in to unmask] http://www.irc.chmcc.org