<html><head><meta http-equiv="Content-Type" content="text/html charset=utf-8"></head><body style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space;" class=""><div class="">Hi Andriy,</div><div class=""><br class=""></div><div class="">How are you comparing ITKv3 with ITKv4? I assume you’re running</div><div class="">ITKv3 through BRAINSFit but how are you running ITKv4?</div><div class=""><br class=""></div><div class="">There are a couple of alternative B-spline methods if you’re interested.</div><div class="">There’s B-spline SyN which is described here</div><div class=""><br class=""></div><div class=""><a href="http://www.ncbi.nlm.nih.gov/pubmed/24409140" class="">http://www.ncbi.nlm.nih.gov/pubmed/24409140</a></div><div class=""><br class=""></div><div class="">and </div><div class=""><br class=""></div><div class="">a Demon’s like B-spline algorithm described here</div><div class=""><br class=""></div><div class=""><a href="http://www.ncbi.nlm.nih.gov/pubmed/19171516" class="">http://www.ncbi.nlm.nih.gov/pubmed/19171516</a></div><div class=""><br class=""></div><div class="">which both offer different regularization options that are available in</div><div class="">ITKv4. However, alternative explicit regularization models, such as</div><div class="">thin plate splines, are not available in ITKv4.</div><div class=""><br class=""></div><div class="">Nick</div><div class=""><br class=""></div><div class=""><br class=""></div><div class=""><br class=""></div><div class=""><br class=""></div><br class=""><div><blockquote type="cite" class=""><div class="">On May 19, 2015, at 5:38 PM, Andriy Fedorov <<a href="mailto:fedorov@bwh.harvard.edu" class="">fedorov@bwh.harvard.edu</a>> wrote:</div><br class="Apple-interchange-newline"><div class="">Hi,<br class=""><br class="">we are in the process of evaluating the possibility of migrating<br class="">workflows from ITKv3 to ITKv4 b-spline based registration (see details<br class="">here [1]).<br class=""><br class="">One issue that is becoming apparent is that sometime the deformations<br class="">we are getting with ITKv4 lack are a lot more irregular and<br class="">unrealistic than what we used to get in ITKv3 (see case 9 on the page<br class="">referenced).<br class=""><br class="">At the ITK community hangout last week it was suggested that there are<br class="">some ways in ITKv4 to add regularization to b-spline transformation.<br class=""><br class="">Is there an example of b-spline regularization we could follow to see<br class="">how this should be done? Is there a significant performance hit if<br class="">this regularization is used?<br class=""><br class="">Thanks<br class=""><br class="">AF<br class=""><br class="">[1] <a href="http://www.na-mic.org/Wiki/index.php/BRAINSFit_prostate_registration" class="">http://www.na-mic.org/Wiki/index.php/BRAINSFit_prostate_registration</a><br class=""><br class=""><br class="">The information in this e-mail is intended only for the person to whom it is<br class="">addressed. If you believe this e-mail was sent to you in error and the e-mail<br class="">contains patient information, please contact the Partners Compliance HelpLine at<br class=""><a href="http://www.partners.org/complianceline" class="">http://www.partners.org/complianceline</a> . If the e-mail was sent to you in error<br class="">but does not contain patient information, please contact the sender and properly<br class="">dispose of the e-mail.<br class=""></div></blockquote></div><br class=""></body></html>