<table cellspacing="0" cellpadding="0" border="0" ><tr><td valign="top" style="font: inherit;"><span class="Apple-style-span" style="font-family: monospace; font-size: 14px; line-height: 16px; "><div><span class="Apple-style-span" style="font-family: monospace; font-size: 14px; line-height: 16px; ">Hi Anja,</span></div><div><span class="Apple-style-span" style="font-family: monospace; font-size: 14px; line-height: 16px; "><br></span></div><div><span class="Apple-style-span" style="font-family: monospace; font-size: 14px; line-height: 16px; ">There is a special implementation of MI included in ITK,</span></div><div><span class="Apple-style-span" style="font-family: monospace; font-size: 14px; line-height: 16px; "><br></span></div><div><span class="Apple-style-span" style="font-family: monospace; font-size: 14px; line-height: 16px; ">MattesMutualInformation has an efficient sampling mechanism</span></div><div><span class="Apple-style-span"
style="font-family: monospace; font-size: 14px; line-height: 16px; "><br></span></div><div><span class="Apple-style-span" style="font-family: monospace; font-size: 14px; line-height: 16px; ">which could help you dealing with large datasets. More details</span></div><div><span class="Apple-style-span" style="font-family: monospace; font-size: 14px; line-height: 16px; "><br></span></div><div><span class="Apple-style-span" style="font-family: monospace; font-size: 14px; line-height: 16px; ">about this method can be found in the following article,</span></div><div><span class="Apple-style-span" style="font-family: monospace; font-size: 14px; line-height: 16px; "><br></span></div><div><span class="Apple-style-span" style="font-family: monospace; font-size: 14px; line-height: 16px; "><br></span></div><div>"PET-CT image registration in the chest using free-form</div><div><span class="Apple-style-span" style="font-family: monospace; font-size: 14px;
line-height: 16px; "><br></span></div><div><span class="Apple-style-span" style="font-family: monospace; font-size: 14px; line-height: 16px; ">deformations"</span></div><div><span class="Apple-style-span" style="font-family: monospace; font-size: 14px; line-height: 16px; "><br></span></div><div><span class="Apple-style-span" style="font-family: monospace; font-size: 14px; line-height: 16px; ">IEEE Transactions on Medical Imaging, 22(1):120–128, </span></div><div><span class="Apple-style-span" style="font-family: monospace; font-size: 14px; line-height: 16px; "><br></span></div><div><span class="Apple-style-span" style="font-family: monospace; font-size: 14px; line-height: 16px; ">January 2003</span></div><div><span class="Apple-style-span" style="font-family: monospace; font-size: 14px; line-height: 16px; "><br></span></div><div><span class="Apple-style-span" style="font-family: monospace; font-size: 14px; line-height: 16px;
"><br></span></div><div><br></div><div><span class="Apple-style-span" style="font-family: monospace; font-size: 14px; line-height: 16px; ">Best regards,</span></div><div><span class="Apple-style-span" style="font-family: monospace; font-size: 14px; line-height: 16px; "><br></span></div><div><span class="Apple-style-span" style="font-family: monospace; font-size: 14px; line-height: 16px; ">Dawood Masslawi</span></div><div><span class="Apple-style-span" style="font-family: monospace; font-size: 14px; line-height: 16px; "><br></span></div><div><span class="Apple-style-span" style="font-family: monospace; font-size: 14px; line-height: 16px; "><br></span></div><div><span class="Apple-style-span" style="font-family: monospace; font-size: 14px; line-height: 16px;
">>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<</span></div><div><span class="Apple-style-span" style="font-family: monospace; font-size: 14px; line-height: 16px; "><br></span></div><div><span class="Apple-style-span" style="font-family: monospace; font-size: 14px; line-height: 16px; ">>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<</span></div><div><br></div><div><span class="Apple-style-span" style="font-family: monospace; font-size: 14px; line-height: 16px; "><br></span></div><div><span class="Apple-style-span"
style="font-family: monospace; font-size: 14px; line-height: 16px; "><br></span></div>Hello everyone,<br style="line-height: 1.2em; outline-style: none; outline-width: initial; outline-color: initial; "><br style="line-height: 1.2em; outline-style: none; outline-width: initial; outline-color: initial; ">This is more of a general medical image registration question.</span><div><span class="Apple-style-span" style="font-family: monospace; font-size: 14px; line-height: 16px; "><br></span></div><div><span class="Apple-style-span" style="font-family: monospace; font-size: 14px; line-height: 16px; ">Does anyone know of any literature or work being done on </span></div><div><span class="Apple-style-span" style="font-family: monospace; font-size: 14px; line-height: 16px; "><br></span></div><div><span class="Apple-style-span" style="font-family: monospace; font-size: 14px; line-height: 16px; ">multi-modal similarity measures like MI or NMI but
which are a</span></div><div><span class="Apple-style-span" style="font-family: monospace; font-size: 14px; line-height: 16px; "><br></span></div><div><span class="Apple-style-span" style="font-family: monospace; font-size: 14px; line-height: 16px; ">bit more compact. One thing that I am trying to do is use</span></div><div><span class="Apple-style-span" style="font-family: monospace; font-size: 14px; line-height: 16px; "><br></span></div><div><span class="Apple-style-span" style="font-family: monospace; font-size: 14px; line-height: 16px; ">multivariate mutual information and because of many images, my</span></div><div><span class="Apple-style-span" style="font-family: monospace; font-size: 14px; line-height: 16px; "><br></span></div><div><span class="Apple-style-span" style="font-family: monospace; font-size: 14px; line-height: 16px; ">histogram size gets quite big. So, I am trying to look into other</span></div><div><span
class="Apple-style-span" style="font-family: monospace; font-size: 14px; line-height: 16px; "><br></span></div><div><span class="Apple-style-span" style="font-family: monospace; font-size: 14px; line-height: 16px; ">similarity measures which might be more friendly in this aspect.</span></div><div><span class="Apple-style-span" style="font-family: monospace; font-size: 14px; line-height: 16px; "><br></span></div><div><span class="Apple-style-span" style="font-family: monospace; font-size: 14px; line-height: 16px; "><br style="line-height: 1.2em; outline-style: none; outline-width: initial; outline-color: initial; ">Thanks,</span></div><div><span class="Apple-style-span" style="font-family: monospace; font-size: 14px; line-height: 16px; "><br style="line-height: 1.2em; outline-style: none; outline-width: initial; outline-color: initial; ">Anja</span></div></td></tr></table><br>