BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Chicago
X-LIC-LOCATION:America/Chicago
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20230124T171524Z
LOCATION:C148
DTSTART;TZID=America/Chicago:20221114T110500
DTEND;TZID=America/Chicago:20221114T111000
UID:submissions.supercomputing.org_SC22_sess442_misc163@linklings.com
SUMMARY:Lightning Talk: Image-Guided Adaptive Radiation Therapy (IGART) Ba
 sed on Massive Parallelism and Real-Time Scheduling
DESCRIPTION:Workshop\n\nLightning Talk: Image-Guided Adaptive Radiation Th
 erapy (IGART) Based on Massive Parallelism and Real-Time Scheduling\n\nKia
 ni\n\nModern high precision radiation therapy (RT) applications require a 
 rapid and accurate planning process. Since the anatomical changes during t
 reatment are mostly deformable, deformable image registration (DIR) is a c
 ore process used during treatment to account for those changes in the shap
 e and size of internal organs between the initial and adaptive planning im
 ages acquired during the treatment course. DIR methods have already obtain
 ed huge success on registration accuracy, however, they usually take a lon
 g computation time and this limits clinical applications. So, the research
  question (RQ) of this project is: performing an accurate deformable image
  registration requires a tremendous amount of computing time, how to obtai
 n significant acceleration while maintaining registration accuracy?\n\nDif
 ferent DIR algorithms will behave differently; therefore, users need to be
  aware of specifics of their software before clinical use. In our project,
  we are evaluating a multi-GPU-based DIR framework capabilities for radiot
 herapy treatments, using lung data sets. It is called CLAIRE.  CLAIRE aims
  at solving the large-scale imaging problems, while we want to provide rea
 l-time capabilities for clinically relevant problem sizes. We believe that
  CLAIRE can be benefited from a series of performance optimizations to imp
 rove strong scaling scenarios, since the scalability of CLAIRE is limited 
 due to the high communication costs for small problem sizes.\n\nSession Fo
 rmat: Recorded\n\nRegistration Category: Workshop Reg Pass
END:VEVENT
END:VCALENDAR