BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Europe/Stockholm
X-LIC-LOCATION:Europe/Stockholm
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20230831T095746Z
LOCATION:Sanada I
DTSTART;TZID=Europe/Stockholm:20230627T173000
DTEND;TZID=Europe/Stockholm:20230627T180000
UID:submissions.pasc-conference.org_PASC23_sess174_msa102@linklings.com
SUMMARY:A Novel Deep Learning Model for Patient-Specific Computational Mod
 eling of Cardiac Electrophysiology
DESCRIPTION:Minisymposium\n\nMinglang Yin (Johns Hopkins Whiting School of
  Engineering), Lu Lu (University of Pennsylvania), and Mauro Maggioni and 
 Natalia Trayanova (Johns Hopkins Whiting School of Engineering)\n\nPatient
 -specific computational modeling of cardiac electrophysiology (EP) has bee
 n shown to have a potential utility in a wide range of arrhythmia prognost
 ics and treatment applications. Yet, it requires extensive computational r
 esources, posing a critical challenge for expanding its application in the
  clinic. Hence, there is a pressing need to develop accurate and trustable
  personalized EP heart models with affordable computational costs. We deve
 lop a novel approach to modeling patient-specific cardiac electrophysiolog
 y, which utilizes, at a much-reduced cost, deep learning in lieu of solvin
 g the equations for electrical wave propagation. The new approach is devel
 oped based on an operator-learning neural network (DeepONet) to predict th
 e propagation of electric signals in different patient-specific heart cham
 bers. We train our model to predict electric signal propagation given the 
 encoded geometric information with the pacing location. After training, th
 e accuracy of the deep learning approach is demonstrated by comparing its 
 predictions with simulation results on unseen geometries. We propose a nov
 el deep-learning approach for modeling patient-specific cardiac electrophy
 siology with high accuracy and reduced computational cost. This developmen
 t paves the way for utilization of personalized cardiac EP modeling in cli
 nical applications, as part of the clinical workflow, in ablation target p
 redictions and arrhythmia morphology assessment.\n\nDomain: Life Sciences\
 n\nSession Chair: Georgios Kissas (University of Pennsylvania)
END:VEVENT
END:VCALENDAR