BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:US/Eastern BEGIN:DAYLIGHT DTSTART:20220313T030000 TZOFFSETFROM:-0500 TZOFFSETTO:-0400 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:EDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20221106T010000 TZOFFSETFROM:-0400 TZOFFSETTO:-0500 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:EST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20220506T091253Z UID:3ECC84AE-6F3C-4A95-A5A0-4FC6592FAE46 DTSTART;TZID=US/Eastern:20220505T160000 DTEND;TZID=US/Eastern:20220505T170000 DESCRIPTION:IEEE Maine Joint Communications & Computer Societies Chapter in vites you to join us for a virtual webinar\n\nDeep Learning for Medical Im age Analysis\n\npresented by Cigdem Gunduz Demir\, PhD\, Professor of Comp uter Engineering Deputy Director of KUIS AI Center Koc University\, Turkey and moderated by Julia Upton\, PhD\, Maine Section Chair.\n\nAbstract. Au tomated imaging systems are becoming important tools for medicine and biol ogy research as they facilitate rapid analyses with better reproducibility . Segmenting regions of interest on a medical image is typically the first but one of the foremost steps of these systems\, which greatly affects th e success of the entire analysis. In this talk\, I will briefly mention th e main challenges associated with segmentation tasks in medical image anal ysis\, and then present examples of the dense prediction networks that my research group designed and implemented to address these challenges. Parti cularly\, I will talk about our proposed network architectures and loss fu nctions that were specifically designed to facilitate better training of t he segmentation networks. At the end\, I will discuss future research poss ibilities towards the direction of developing more robust segmentation net works for medical image analysis.\n\nSpeaker Biography. Cigdem Gunduz Demi r received her B.S. and M.S. degrees in computer engineering from Bogazici University in 1999 and 2001\, respectively\, and her Ph.D. degree in comp uter science from Rensselaer Polytechnic Institute in 2005. She is current ly a Professor of Computer Engineering and the Deputy Director of the Cent er of Artificial Intelligence at Koc University. Before joining Koc Univer sity\, she was working as a faculty member at the Computer Engineering Dep artment at Bilkent University. She was a visiting professor at Nanyang Tec hnological University NTU\, Singapore\, in Fall 2009\, and Stanford Univer sity in Spring 2013. Her main research interests and projects include deve lopment of new computational methods based on deep learning and computer v ision for medical image analysis.\n\nCo-sponsored by: University of Southe rn Maine \n\nVirtual: https://events.vtools.ieee.org/m/313226 LOCATION:Virtual: https://events.vtools.ieee.org/m/313226 ORGANIZER:uptonj@husson.edu SEQUENCE:4 SUMMARY:Deep Learning for Medical Image Analysis Webinar URL;VALUE=URI:https://events.vtools.ieee.org/m/313226 X-ALT-DESC:Description: <br /><p>IEEE Maine Joint Communications &amp\; Com puter Societies Chapter invites you to join us for a virtual webinar</p>\n <p><span style="font-size: 18pt\; color: #843fa1\;"><strong>Deep Learning for Medical Image Analysis </strong></span></p>\n<p>presented by <strong>C igdem Gunduz Demir</strong>\, PhD\, Professor of Computer Engineering Depu ty Director of KUIS AI Center Koc University\, Turkey and moderated by Jul ia Upton\, PhD\, Maine Section Chair.</p>\n<div class="page" title="Page 1 ">\n<div class="section">\n<div class="layoutArea">\n<div class="column">\ n<p><strong>Abstract</strong>. &nbsp\;Automated imaging systems are becomi ng important tools for medicine and biology research as they facilitate ra pid analyses with better reproducibility. Segmenting regions of interest o n a medical image is typically the first but one of the foremost steps of these systems\, which greatly affects the success of the entire analysis. In this talk\, I will briefly mention the main challenges associated with segmentation tasks in medical image analysis\, and then present examples o f the dense prediction networks that my research group designed and implem ented to address these challenges. Particularly\, I will talk about our pr oposed network architectures and loss functions that were specifically des igned to facilitate better training of the segmentation networks. At the e nd\, I will discuss future research possibilities towards the direction of developing more robust segmentation networks for medical image analysis.< /p>\n<p><strong>Speaker Biography</strong>. &nbsp\;Cigdem Gunduz Demir rec eived her B.S. and M.S. degrees in computer engineering from Bogazici Univ ersity in 1999 and 2001\, respectively\, and her Ph.D. degree in computer science from Rensselaer Polytechnic Institute in 2005. She is currently a Professor of Computer Engineering and the Deputy Director of the Center of Artificial Intelligence at Koc University. Before joining Koc University\ , she was working as a faculty member at the Computer Engineering Departme nt at Bilkent University. She was a visiting professor at Nanyang Technolo gical University NTU\, Singapore\, in Fall 2009\, and Stanford University in Spring 2013. Her main research interests and projects include developme nt of new computational methods based on deep learning and computer vision for medical image analysis.</p>\n</div>\n</div>\n</div>\n</div> END:VEVENT END:VCALENDAR