<html xmlns:v="urn:schemas-microsoft-com:vml" xmlns:o="urn:schemas-microsoft-com:office:office" xmlns:w="urn:schemas-microsoft-com:office:word" xmlns:m="http://schemas.microsoft.com/office/2004/12/omml" xmlns="http://www.w3.org/TR/REC-html40">
<head>
<meta http-equiv="Content-Type" content="text/html; charset=us-ascii">
<meta name="Generator" content="Microsoft Word 15 (filtered medium)">
<!--[if !mso]><style>v\:* {behavior:url(#default#VML);}
o\:* {behavior:url(#default#VML);}
w\:* {behavior:url(#default#VML);}
.shape {behavior:url(#default#VML);}
</style><![endif]--><style><!--
/* Font Definitions */
@font-face
{font-family:"Cambria Math";
panose-1:2 4 5 3 5 4 6 3 2 4;}
@font-face
{font-family:Calibri;
panose-1:2 15 5 2 2 2 4 3 2 4;}
/* Style Definitions */
p.MsoNormal, li.MsoNormal, div.MsoNormal
{margin:0in;
font-size:11.0pt;
font-family:"Calibri",sans-serif;
mso-ligatures:standardcontextual;}
span.EmailStyle17
{mso-style-type:personal-compose;
font-family:"Calibri",sans-serif;
color:windowtext;}
.MsoChpDefault
{mso-style-type:export-only;
font-size:11.0pt;}
@page WordSection1
{size:8.5in 11.0in;
margin:1.0in 1.0in 1.0in 1.0in;}
div.WordSection1
{page:WordSection1;}
--></style><!--[if gte mso 9]><xml>
<o:shapedefaults v:ext="edit" spidmax="1026" />
</xml><![endif]--><!--[if gte mso 9]><xml>
<o:shapelayout v:ext="edit">
<o:idmap v:ext="edit" data="1" />
</o:shapelayout></xml><![endif]-->
</head>
<body lang="EN-US" link="#0563C1" vlink="#954F72" style="word-wrap:break-word">
<div class="WordSection1">
<div align="center">
<table class="MsoNormalTable" border="0" cellspacing="0" cellpadding="0" width="600" style="width:6.25in">
<tbody>
<tr>
<td style="padding:0in 0in 0in 0in">
<p class="MsoNormal"><span style="font-size:13.5pt;font-family:"Arial",sans-serif;color:black"><img width="599" height="171" style="width:6.2395in;height:1.7812in" id="Picture_x0020_2" src="cid:image001.png@01DBA25A.D138F990" alt="Dissertation Defense Announcement at the Cullen College of Engineering"></span><span style="font-size:13.5pt;font-family:"Arial",sans-serif;color:black;mso-ligatures:none"><o:p></o:p></span></p>
<div align="center">
<table class="MsoNormalTable" border="0" cellspacing="0" cellpadding="0" style="background:white">
<tbody>
<tr>
<td style="padding:30.0pt 15.0pt 7.5pt 15.0pt">
<p class="MsoNormal" align="center" style="margin-bottom:3.75pt;text-align:center;mso-line-height-alt:15.0pt">
<b><span style="font-size:18.0pt;font-family:"Times New Roman",serif;color:#C8102E;mso-ligatures:none">Annotation-Free Large-Scale Overlapping Nuclear Segmentation on Multiplexed Fluorescence Images Using Foundation Model and Weak to Strong Learning<o:p></o:p></span></b></p>
<p class="MsoNormal" align="center" style="margin-bottom:3.75pt;text-align:center;line-height:15.0pt">
<b><span style="font-size:13.5pt;font-family:"Times New Roman",serif;color:black;mso-ligatures:none">Lin Bai</span></b><span style="font-size:13.5pt;font-family:"Times New Roman",serif;mso-ligatures:none"><o:p></o:p></span></p>
<p class="MsoNormal" align="center" style="margin-bottom:8.0pt;text-align:center;line-height:16.5pt">
<span style="font-size:10.5pt;font-family:"Arial",sans-serif;color:black;mso-ligatures:none">April 18, 2025, 11 a.m. to 1 p.m. (CST)<br>
Location: Room N202 Bldg. 1</span><span style="font-size:10.5pt;font-family:"Arial",sans-serif;mso-ligatures:none"><o:p></o:p></span></p>
<p class="MsoNormal" align="center" style="margin-bottom:8.0pt;text-align:center;line-height:16.5pt">
<span style="font-size:10.5pt;font-family:"Arial",sans-serif;color:black;mso-ligatures:none">Zoom:
</span><span style="color:black;mso-ligatures:none"><a href="https://urldefense.com/v3/__https://uh-edu-cougarnet.zoom.us/j/84778001715?pwd=cE6pmEMQGmekjLpQViH8Nd6XxDO6DJ.1__;!!LkSTlj0I!DeWsTsNxnMEaKsSsqFQZqPmQY_OTptBdveU-8n7V2-uB7Hlzugq5u9FdRf40y-_KYxDhGW5maIRdd2FWhXem3KU5kZc$"><span style="font-size:10.5pt;font-family:"Arial",sans-serif;color:#0563C1">Join the meeting</span></a></span><span style="font-size:10.5pt;font-family:"Arial",sans-serif;color:black;mso-ligatures:none">
</span><span style="font-size:10.5pt;font-family:"Arial",sans-serif;mso-ligatures:none"><o:p></o:p></span></p>
<p class="MsoNormal" align="center" style="margin-bottom:3.75pt;text-align:center;line-height:16.5pt">
<b><span style="font-size:10.5pt;font-family:"Arial",sans-serif;color:black;mso-ligatures:none">Committee Chair:</span></b><span style="font-size:10.5pt;font-family:"Arial",sans-serif;color:black;mso-ligatures:none"><br>
Badri Roysam, Ph.D.</span><span style="font-size:10.5pt;font-family:"Arial",sans-serif;mso-ligatures:none"><o:p></o:p></span></p>
<p class="MsoNormal" align="center" style="margin-bottom:15.0pt;text-align:center;line-height:16.5pt">
<b><span style="font-size:10.5pt;font-family:"Arial",sans-serif;color:black;mso-ligatures:none">Committee Members:</span></b><span style="font-size:10.5pt;font-family:"Arial",sans-serif;color:black;mso-ligatures:none"><br>
Saurabh Prasad, Ph.D. | Hien Van Nguyen, Ph.D. | David Mayerich, Ph.D. | <br>
Dragan Maric, Ph.D.</span><span style="font-size:10.5pt;font-family:"Arial",sans-serif;mso-ligatures:none"><o:p></o:p></span></p>
</td>
</tr>
<tr>
<td style="padding:0in 15.0pt 15.0pt 15.0pt">
<p class="MsoNormal" style="mso-margin-top-alt:11.25pt;margin-right:0in;margin-bottom:11.25pt;margin-left:0in;line-height:16.5pt">
<b><span style="font-size:12.0pt;font-family:"Arial",sans-serif;color:#C8102E;mso-ligatures:none">Abstract</span></b><span style="font-size:12.0pt;font-family:"Arial",sans-serif;color:#C8102E;mso-ligatures:none"><o:p></o:p></span></p>
<p class="MsoNormal" style="margin-bottom:8.0pt;line-height:106%"><span style="color:black;mso-ligatures:none">We present a
<i>weak to strong generalization</i> methodology for fully automated training of a multi-head extension of the Mask-RCNN method with efficient channel attention for reliable segmentation of overlapping cell nuclei in multiplex cyclic immunofluorescent (IHC)
whole-slide images (WSI), and present evidence for pseudo-label correction and coverage expansion, the key phenomena underlying weak to strong generalization. This method can learn to segment
<i>de novo </i>a new class of images resulting from a new instrument and/or a new protocol without the need for human annotations. We present metrics for automated self-diagnosis of segmentation quality in production environments, where human visual proofreading
of massive WSI images is unaffordable. The proposed method was benchmarked against five current widely used methods and showed a significant improvement.
</span><span style="color:black;mso-ligatures:none;mso-fareast-language:ZH-CN">W</span><span style="color:black;mso-ligatures:none">e extend our study by adapting and applying the framework to two additional datasets</span><span style="color:black;mso-ligatures:none;mso-fareast-language:ZH-CN">
to </span><span style="color:black;mso-ligatures:none">evaluate its generalizability across different imaging domains</span><span style="color:black;mso-ligatures:none;mso-fareast-language:ZH-CN">.
</span><span style="color:black;mso-ligatures:none">The code, sample WSI images, and high-resolution segmentation results are provided in open form for community adoption and adaptation to other image analysis tasks.</span><span style="mso-ligatures:none"><o:p></o:p></span></p>
</td>
</tr>
</tbody>
</table>
</div>
</td>
</tr>
<tr>
<td style="padding:0in 0in 0in 0in">
<p class="MsoNormal"><span style="font-size:13.5pt;font-family:"Arial",sans-serif;color:black"><img border="0" width="599" height="82" style="width:6.2395in;height:.8541in" id="Picture_x0020_1" src="cid:image002.png@01DBA25A.D138F990" alt="Engineered For What's Next"></span><span style="font-size:13.5pt;font-family:"Arial",sans-serif;color:black;mso-ligatures:none"><o:p></o:p></span></p>
</td>
</tr>
</tbody>
</table>
</div>
<p class="MsoNormal" style="margin-bottom:8.0pt;line-height:106%"><span style="mso-ligatures:none"><o:p> </o:p></span></p>
<p class="MsoNormal"><o:p> </o:p></p>
</div>
</body>
</html>