<div dir="ltr"><br clear="all"><div><div dir="ltr" class="gmail_signature" data-smartmail="gmail_signature"><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr"><div><br></div></div></div></div></div></div></div></div><div class="gmail_quote"><div><div><p><img alt="SDSU_CSRC Logo.jpg" width="534px" height="107px" src="cid:78dd458c-190c-4831-aa20-3bdd9eed73c3"><br><br></p><p>DATE:  <br><b>Friday, October 8, 2021</b></p><p><br></p><div dir="ltr"><p></p><p></p><p>TITLE:<br><b>Interpretation of Radiological Imaging Features using Generative Adversarial Networks  </b> <b> </b>    <b>    </b> <b>  </b>  <b>   </b>   </p><div><br></div><p>TIME:  <br><b>3:30-4:30PM</b></p><p> <br></p><p>LOCATION:<br><b>In Person - GMCS 314</b><br><span style="font-weight:bold">or<br>Join Zoom Meeting -  </span> <a href="https://sdsu.zoom.us/j/86808277973" target="_blank">https://SDSU.zoom.us/j/86808277973</a></p><p><br></p><p>SPEAKER/BIO: <br><b>Kyle Hasenstab, Mathematics and Statistics, San Diego State University </b> <b> </b>   <b>  </b></p><p><br></p><p>ABSTRACT:</p></div><div dir="ltr"><p>Convolutional neural networks (CNNs) have become valuable instruments for computer vision in medical imaging, able to learn features of disease without explicit programming. However, algorithm transparency is necessary for these to be applied in clinical practice. To address this, we propose a feature interpretation generative adversarial network (FIGAN) to generate synthetic images that facilitate CNN feature interpretation. Feasibility of the proposed approach was assessed on a previously-developed CNN designed to assess contrast enhancement adequacy of liver MR images for lesion detection. Review of FIGAN images revealed that this CNN utilizes features related to tissue-vessel contrast, nodular liver texture, and tissue brightness to determine adequacy of contrast enhancement.<br></p><p><br></p><p>Host:<br><b>Jose Castillo</b></p></div><div><br></div><div><p><span style="font-weight:bold">Note:</span><span style="font-weight:bold"> </span>Videos of previous colloquium talks can be seen on the CSRC website in the colloquium archive section or on the <a href="https://www.youtube.com/channel/UCN0ZEztlmyDqG2pm-Rle_Eg/feed" target="_blank">CSRC YouTube page here</a>.</p><br></div><div><br></div></div><div><div></div><div></div><br></div></div><div><br></div>
<p></p>
-- <br>
You received this message because you are subscribed to the Google Groups "CSRC Colloquium" group.<br>
To unsubscribe from this group and stop receiving emails from it, send an email to <a href="mailto:csrc.colloquium+unsubscribe@sdsu.edu" target="_blank">csrc.colloquium+unsubscribe@sdsu.edu</a>.<br>
To view this discussion on the web visit <a href="https://groups.google.com/a/sdsu.edu/d/msgid/csrc.colloquium/719d7126-1407-4a88-b7c1-c8b6b680a4b6n%40sdsu.edu?utm_medium=email&utm_source=footer" target="_blank">https://groups.google.com/a/sdsu.edu/d/msgid/csrc.colloquium/719d7126-1407-4a88-b7c1-c8b6b680a4b6n%40sdsu.edu</a>.<br>
</div></div>