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:20230627T123000
DTEND;TZID=Europe/Stockholm:20230627T130000
UID:submissions.pasc-conference.org_PASC23_sess173_msa215@linklings.com
SUMMARY:Deep Learning-Based Reduced Order Modeling for Microcirculation in
Vascular Networks
DESCRIPTION:Minisymposium\n\nNicola Rares Franco, Piermario Vitullo, Andre
a Manzoni, and Paolo Zunino (Politecnico di Milano)\n\nPhysics-based model
s describing biological phenomena in mathematical terms usually rely on nu
merical simulations to derive physically interpretable biomarkers, ultimat
ely supporting decisions in clinical treatments. Calibrating model paramet
ers in this context requires a suitable combination of uncertainty quantif
ication tools and efficient numerical solvers capable of repeated simulati
ons in very rapid times. In this talk we focus on the use of recently esta
blished Deep Learning-based reduced order models (DL-ROMs) for the efficie
nt approximation of the parameter-to-solution map of parametrized partial
differential equations in the case of perfusion models, ultimately aiming
at the personalized treatment planning of radiotherapy for oncological pat
ients. In this scenario, we rely on Tumor Control Probability (TCP) models
, that exploit the relationship between oxygen partial pressure and resist
ance to radiation to estimate the probability of tumor eradication, aiming
at the approximation of maps from a set of model parameters (such as, e.g
., the permeability of the blood vessels and the topology of the vascular
network) to the oxygen partial pressure. To properly account for the impac
t of the topology of the microvascular network on the oxygen distribution
in the tissue, we rely on DL-ROMs and newly introduced mesh-informed neura
l network architectures, offering the possibility to handle geometrical in
formation efficiently.\n\nDomain: Life Sciences\n\nSession Chair: Georgios
Kissas (University of Pennsylvania)
END:VEVENT
END:VCALENDAR