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:20230627T163000
DTEND;TZID=Europe/Stockholm:20230627T170000
UID:submissions.pasc-conference.org_PASC23_sess174_msa243@linklings.com
SUMMARY:WarpPINN: Cine-MR Image Registration with Physics-Informed Neural 
 Networks
DESCRIPTION:Minisymposium\n\nFrancisco Sahli Costabal (Pontificia Universi
 dad Católica de Chile, iHEALTH); Pablo Arratia López (University of Bath);
  Hernán Mella (Pontificia Universidad Católica de Valparaíso); and Sergio 
 Uribe and Daniel Hurtado (Pontificia Universidad Católica de Chile)\n\nHea
 rt failure is typically diagnosed with a global function assessment, such 
 as ejection fraction. However, these metrics have low discriminate power, 
 failing to distinguish different types of this disease. Quantifying local 
 deformations in the form of cardiac strain can provide helpful information
 , but it remains a challenge. In this work, we introduce WarpPINN, a physi
 cs-informed neural network to perform image registration to obtain local m
 etrics of the heart deformation. We apply this method to cine magnetic res
 onance images to estimate the motion during the cardiac cycle. We inform o
 ur neural network of near-incompressibility of cardiac tissue by penalizin
 g the jacobian of the deformation field. The loss function has two compone
 nts: an intensity-based similarity term between the reference and the warp
 ed template images, and a regularizer that represents the hyperelastic beh
 avior of the tissue. The architecture of the neural network allows us to e
 asily compute the strain via automatic differentiation to assess cardiac a
 ctivity. We test our algorithm on a synthetic example and on a cine-MRI be
 nchmark of 15 healthy volunteers. We outperform current methodologies both
  landmark tracking and strain estimation. We expect that WarpPINN will ena
 ble more precise diagnostics of heart failure based on local deformation i
 nformation.\n\nDomain: Life Sciences\n\nSession Chair: Georgios Kissas (Un
 iversity of Pennsylvania)
END:VEVENT
END:VCALENDAR