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:20230831T095754Z
LOCATION:Sanada I
DTSTART;TZID=Europe/Stockholm:20230627T110000
DTEND;TZID=Europe/Stockholm:20230627T130000
UID:submissions.pasc-conference.org_PASC23_sess173@linklings.com
SUMMARY:MS3G - Biophysics-Informed Machine Learning (Part 1/2)
DESCRIPTION:Minisymposium\n\nFor designing personalized treatment strategi
 es, measurable quantities (biomarkers) that relate a patient’s clinical re
 presentation to the existence, progress, and outcome of the disease need t
 o be measured. They can often be formulated as quantities coming from biop
 hysical models involving, for example, material deformations or fluid tran
 sport. However, the computational cost of numerically solving for these qu
 antities can be prohibitive. These challenges are limiting the potential c
 linical impact of classical computational approaches, thus posing the need
  for new frameworks that reduce the time to prediction without sacrificing
  the physical consistency and fidelity of the inferred biomarkers. The suc
 cess of machine learning methods provides a viable path to amortize the co
 st of these expensive simulations by training models to replicate the inpu
 t-output behavior of the classical simulations. In purely data driven appr
 oaches, large amounts of labeled data are needed to train the model withou
 t leveraging any prior knowledge about the underlying biophysics. Unfortun
 ately, in many biological scenarios the data acquisition process can be ex
 pensive and time consuming, limiting the amount of available training data
 . To address this difficulty, biophysics-informed machine learning offers 
 a computationally efficient approach that has the potential to bridge the 
 gap between modeling and clinical decision making.\n\nDeep Learning-Based 
 Reduced Order Modeling for Microcirculation in Vascular Networks\n\nPhysic
 s-based models describing biological phenomena in mathematical terms usual
 ly rely on numerical simulations to derive physically interpretable biomar
 kers, ultimately supporting decisions in clinical treatments. Calibrating 
 model parameters in this context requires a suitable combination of unce..
 .\n\n\nNicola Rares Franco, Piermario Vitullo, Andrea Manzoni, and Paolo Z
 unino (Politecnico di Milano)\n---------------------\nReducing the Cost of
  MRI Scanning by Enhancing Data with Underlying Physics via Physics-Inform
 ed Neural Networks\n\nPhysics informed neural networks (PINNs) have grown 
 from a toy machine learning concept to very powerful and applicable in a v
 ariety of modern problems. As PINNs continue to grow, they will inevitably
  be utilized more in the fields of medicine and biology, where not only ar
 e the domains of interest ...\n\n\nMitchell Daneker and Eric Myzelev (Univ
 ersity of Pennsylvania), Arsh Kumbhat (BITS Pilani), He Li (University of 
 Georgia), and Lu Lu (University of Pennsylvania)\n---------------------\nN
 eural Operators for Detecting Aortic Aneurysm Contributors\n\nThoracic aor
 tic aneurysm is a localized dilatation of the aorta that can lead to life-
 threatening dissection or rupture. Currently, the only way to assess the p
 rogression of this condition is by measuring the size of the aneurysm and 
 its growth rate. However, there is hope that by using computationa...\n\n\
 nSomdatta Goswami (Brown University), David Li and Jay Humphrey (Yale Univ
 ersity), and George Karniadakis (Brown University)\n---------------------\
 nLeveraging Graph Neural Networks for Efficient Reduced-Order Blood Flow S
 imulations\n\nRecently, simulations of blood flow have shown great promise
  in revolutionizing cardiovascular disease research and treatment. Reduced
 -order models, specifically zero- and one-dimensional ones, can approximat
 e blood dynamics more efficiently than detailed three-dimensional simulati
 ons. These models ...\n\n\nLuca Pegolotti, Martin Pfaller, and Natalia Rub
 io (Stanford University); Ke Ding and Rita Brugarolas (Intel Corporation);
  and Eric Darve and Alison Marsden (Stanford University)\n\nDomain: Life S
 ciences\n\nSession Chair: Georgios Kissas (University of Pennsylvania)
END:VEVENT
END:VCALENDAR