BEGIN:VCALENDAR
CALSCALE:GREGORIAN
VERSION:2.0
METHOD:PUBLISH
PRODID:-//Drupal iCal API//EN
X-WR-TIMEZONE:America/New_York
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
DTSTART:20070311T020000
TZNAME:EDT
TZOFFSETTO:-0400
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
DTSTART:20071104T020000
TZNAME:EST
TZOFFSETTO:-0500
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
SEQUENCE:1
X-APPLE-TRAVEL-ADVISORY-BEHAVIOR:AUTOMATIC
234936
20260417T141800Z
DTSTART;TZID=America/New_York:20260428T100000
DTEND;TZID=America/New_York:2
 0260428T110000
URL;TYPE=URI:https://www.wpi.edu/news/calendar/events/compu
 ter-science-department-ms-thesis-presentation-jessica-elmhurst-automated-s
 can-viability-mapping
Computer Science Department, MS Thesis Presentation, Jessica Elmhurst " Automated Scan-Viability Mapping Using Image Segmentation for Optical Coherence Tomography on Deceased Donor Kidneys"
Jessica Elmhurst\nMS Student\nWPI – Computer Science Department\nTuesday, April 28th, 2026\nTime:
  10:00am-11:00am\nLocation: Unity Hall 446 Tech Suite\n\nAdvisor: Prof. Ha
 ichong K. Zhang\nReader: Prof. Bahman Moraffah\nAbstract:\nCurrent decease
 d donor kidney assessment often leads to the disqualification of viable or
 gans. Optical Coherence Tomography (OCT) is a powerful and non-invasive im
 aging modality that produces high-resolution images of tissue microstructu
 res associated with post-transplant renal function. Integrated with a robo
 tic system, the process of imaging renal microstructures with OCT has beco
 me faster and capable of capturing spatially dense information with large-
 area scans. However, the presence of fat tissue on the surface of the kidn
 ey can attenuate the OCT scan signal and delay scan acquisition. To resolv
 e this, we present a deep learning pipeline to identify scan-viable region
 s for precise robotic tissue targeting.\nUsing a two-tiered U-Net architec
 ture trained on a dataset of deceased donor kidneys, the pipeline first is
 olates the kidney contour and then segments adipose tissue. The resulting 
 inference masks are used to create a scan viability map and virtual trajec
 tories to assist robotic probe movement and optimize scan acquisition. Val
 idated against state-of-the-art models using Dice Coefficient and IoU metr
 ics, the pipeline will augment pre-transplant organ evaluation and enhance
  organ assessment workflows.\n\nThank you so much for your guidance with t
 his process. Please let me know if you have any questions or something I s
 hould change.\n
END:VEVENT
END:VCALENDAR