<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
</head>
<body style="word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;" class="">
<div class="">
<div dir="auto" style="text-align: start; text-indent: 0px; word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;" class="">
<div>
<div class="ContentPasted0" style="caret-color: rgb(0, 0, 0); color: rgb(0, 0, 0); letter-spacing: normal; text-transform: none; white-space: normal; word-spacing: 0px; text-decoration: none; -webkit-text-stroke-width: 0px; border: 0px; font-stretch: inherit; line-height: inherit; margin: 0px; padding: 0px; vertical-align: baseline; background-color: rgb(255, 255, 255);">
This is an announcement of Renyu Zhang’s Candidacy Exam.</div>
<div style="caret-color: rgb(0, 0, 0); color: rgb(0, 0, 0); letter-spacing: normal; text-transform: none; white-space: normal; word-spacing: 0px; text-decoration: none; -webkit-text-stroke-width: 0px;" class="">
<div class="">===============================================</div>
<div class="">Candidate: Renyu Zhang</div>
</div>
<div class="" style="caret-color: rgb(0, 0, 0); color: rgb(0, 0, 0); letter-spacing: normal; text-transform: none; white-space: normal; word-spacing: 0px; text-decoration: none; -webkit-text-stroke-width: 0px;">
<br class="">
</div>
<div class="" style="caret-color: rgb(0, 0, 0); color: rgb(0, 0, 0); letter-spacing: normal; text-transform: none; white-space: normal; word-spacing: 0px; text-decoration: none; -webkit-text-stroke-width: 0px;">
Date: Monday, June 26, 2023</div>
<div class="" style="caret-color: rgb(0, 0, 0); color: rgb(0, 0, 0); letter-spacing: normal; text-transform: none; white-space: normal; word-spacing: 0px; text-decoration: none; -webkit-text-stroke-width: 0px;">
<br class="">
</div>
<div class="" style="caret-color: rgb(0, 0, 0); color: rgb(0, 0, 0); letter-spacing: normal; text-transform: none; white-space: normal; word-spacing: 0px; text-decoration: none; -webkit-text-stroke-width: 0px;">
Time: 1:30 pm CST</div>
<div class="" style="caret-color: rgb(0, 0, 0); color: rgb(0, 0, 0); letter-spacing: normal; text-transform: none; white-space: normal; word-spacing: 0px; text-decoration: none; -webkit-text-stroke-width: 0px;">
<br class="">
</div>
<div class="" style="caret-color: rgb(0, 0, 0); color: rgb(0, 0, 0); letter-spacing: normal; text-transform: none; white-space: normal; word-spacing: 0px; text-decoration: none; -webkit-text-stroke-width: 0px;">
Location: JCL 298</div>
<div class="" style="caret-color: rgb(0, 0, 0); color: rgb(0, 0, 0); letter-spacing: normal; text-transform: none; white-space: normal; word-spacing: 0px; text-decoration: none; -webkit-text-stroke-width: 0px;">
<br class="">
</div>
<div class="" style="caret-color: rgb(0, 0, 0); color: rgb(0, 0, 0); letter-spacing: normal; text-transform: none; white-space: normal; word-spacing: 0px; text-decoration: none; -webkit-text-stroke-width: 0px;">
Title: Machine Learning for Biomedical Images in Low-Data Regime</div>
<div class="" style="caret-color: rgb(0, 0, 0); color: rgb(0, 0, 0); letter-spacing: normal; text-transform: none; white-space: normal; word-spacing: 0px; text-decoration: none; -webkit-text-stroke-width: 0px;">
<br class="">
</div>
<div class="">Abstract: Diagnostic pathology and histopathology images play a critical role in the diagnosis and treatment of carcinomas. In order to get satisfying performance, we usually need a large amount of labeled data. Annotating a large number of histopathology
images for training machine learning models can be expensive and time-consuming. We explored several approaches of machine learning in a low-data regime for histopathology images, including caption generation from histology images [Zhang et al., 2020b], a
deep Bayesian active learning method [Zhang et al., 2023] to enable efficient selection of training examples that can undergo more expensive annotation, and representation learning approach that utilize existing coarse-grained labels for H&E slides to improve
model performance on fine-grained data. Our experiments demonstrate that these approaches can improve the accuracy of models in the low-data regime while maintaining high levels of interpretability. The results of this study provide valuable insights for future
research in the area of machine learning in low-data regimes for histopathology images.</div>
<div class=""><br class="">
</div>
<div class="">Advisors: Robert L. Grossman</div>
<div class=""><br class="">
</div>
<div class="">Committee Members: Robert L. Grossman, Aly A. Khan, and Yuxin Chen</div>
<div class=""><br class="">
</div>
<div class=""><a href="https://urldefense.com/v3/__https://drive.google.com/file/d/15ftMGuxg6-fRYVNfObLnpOzCc-C9jdRw/view?usp=drive_web__;!!BpyFHLRN4TMTrA!51WmbVugZWrpvj2edkSQUTTk7ZmvNv-zbL9hQFdLXTFoGZXsU9ESBq9lX2vICpc_XqNPwh9Asc94w4RwQjseBRpr6Gc$" class=""> CandidacyProposal.pdf</a></div>
<div class=""><br class="">
</div>
<div class=""><br class="">
</div>
</div>
</div>
<br class="Apple-interchange-newline">
</div>
<br class="">
</body>
</html>