ITK Experts,<div><br></div><div>I need to segment nuclei (specially mitosis nuclei) in H&E stained histopathological images (see in attachment). I have seed points. I tried ConfidenceConnectedImageFilter and FastMarchingImageFilter but it give poor results. Most of the time, nuclei are under segment. Mitosis nuclei are homogeneous and having variations in shape and size. Please suggest any better segmentation filter. </div>
<div><br></div>-- <br><font face="arial, helvetica, sans-serif">-- <br>Best Regards, <br><br></font><div><b><font face="arial, helvetica, sans-serif">HUMAYUN IRSHAD</font></b></div><div><span style="border-collapse:collapse"><b><span style="border-collapse:separate;font-weight:normal"><div>
<span style="border-collapse:collapse"><b><span style="border-collapse:separate;font-weight:normal"><div style="display:inline!important"><span style="border-collapse:collapse"><b><span style="border-collapse:separate;font-weight:normal"><font face="arial, helvetica, sans-serif">PhD student, University of Joseph Fourier, Grenoble, France</font></span></b></span></div>
</span></b></span></div></span></b></span><span style="border-collapse:collapse"><b><span style="border-collapse:separate;font-weight:normal"><div style="display:inline!important"><span style="border-collapse:collapse"><b><span style="border-collapse:separate;font-weight:normal"><div style="display:inline!important">
<span style="border-collapse:collapse"><b><span style="border-collapse:separate;font-weight:normal"><font face="arial, helvetica, sans-serif">Research Engineer, </font></span></b></span></div></span></b></span></div></span></b></span><span style="border-collapse:collapse"><b><span style="border-collapse:separate;font-weight:normal"><div style="display:inline!important">
<span style="border-collapse:collapse"><b><span style="border-collapse:separate;font-weight:normal"><font face="arial, helvetica, sans-serif">IPAL – Image & Pervasive Access Lab, Singapore</font></span></b></span></div>
</span></b></span><span style="border-collapse:collapse"><b><span style="border-collapse:separate;font-weight:normal"><div><span style="border-collapse:collapse"><b><span style="border-collapse:separate;font-weight:normal"><font face="arial, helvetica, sans-serif">UMI CNRS (I2R/A*STAR, NUS, UJF, UPMC, IT)</font></span></b></span></div>
<div><div><div><span style="border-collapse:collapse"><font face="arial, helvetica, sans-serif"><div><span style="border-collapse:collapse"><br></span></div>Institute for Infocomm Research (I2R)<br>1 Fusionopolis Way<br>#10-19 Connexis South Tower<br>
Singapore 138632<br>Tel:+65-65162864</font></span></div></div></div><div><span style="border-collapse:collapse"><font face="arial, helvetica, sans-serif">Cell: +65-83851671</font></span></div><div><span style="font-family:arial,sans-serif;font-size:13px;border-collapse:collapse"><br>
</span></div></span></b></span></div><br>