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:20230627T120000
DTEND;TZID=Europe/Stockholm:20230627T123000
UID:submissions.pasc-conference.org_PASC23_sess173_msa191@linklings.com
SUMMARY:Reducing the Cost of MRI Scanning by Enhancing Data with Underlyin
 g Physics via Physics-Informed Neural Networks
DESCRIPTION:Minisymposium\n\nMitchell Daneker and Eric Myzelev (University
  of Pennsylvania), Arsh Kumbhat (BITS Pilani), He Li (University of Georgi
 a), and Lu Lu (University of Pennsylvania)\n\nPhysics informed neural netw
 orks (PINNs) have grown from a toy machine learning concept to very powerf
 ul and applicable in a variety of modern problems. As PINNs continue to gr
 ow, they will inevitably be utilized more in the fields of medicine and bi
 ology, where not only are the domains of interest incredibly complex but i
 nformation on them incomplete. We study PINN performance in said area via 
 the lens of aortic dissections (AD) informed by MRI scanning. Specifically
 , we consider the prediction accuracy of PINNs as a function of 4D flow MR
 I in both spatial and temporal resolutions, and consider PINN prediction o
 f gradient based parameters, wall shear stress and shear rate. Three AD an
 eurysms are analyzed, ones with large, medium, and small sized mouths. The
 se mouths lack any boundary conditions making this an unsolvable problem w
 ith standard computational techniques. We utilize PINN aided by 2D MRI dat
 a to learn the hemodynamics of the domain. We conclude that full MRI resol
 ution may not be required, saving on scanning cost, and in the case of AD 
 aneurysms, larger mouths lead to more accurate results due to the larger o
 rder of magnitude in the velocities which are easier for PINNs to learn.\n
 \nDomain: Life Sciences\n\nSession Chair: Georgios Kissas (University of P
 ennsylvania)
END:VEVENT
END:VCALENDAR