BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Date iCal//NONSGML kigkonsult.se iCalcreator 2.20.2//
METHOD:PUBLISH
X-WR-CALNAME;VALUE=TEXT:Eventi DIAG
BEGIN:VTIMEZONE
TZID:Europe/Paris
BEGIN:STANDARD
DTSTART:20251026T030000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
RDATE:20261025T030000
TZNAME:CET
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20260329T020000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:calendar.30655.field_data.0@www.diag.uniroma1.it
DTSTAMP:20260412T092514Z
CREATED:20260313T105133Z
DESCRIPTION:AbstractContinuous intracranial pressure (ICP) monitoring is es
 sential for managing severe neurological conditions\; however\, traditiona
 l methods require invasive surgical skull drilling\, which carries signifi
 cant risks of infection and hemorrhage. This presentation introduces the S
 afeICP platform\, a non-invasive alternative that measures microvascular c
 erebral blood flow at the bedside using speckle contrast optical spectrosc
 opy and near-infrared biophotonics. A major focus will be the project's de
 ep learning framework\, demonstrating how advanced architectures – specifi
 cally InceptionTime and Multi-Wavelet Decomposition Network – can capture 
 subtle temporal dynamics in raw blood flow index time-series and translate
  them directly into absolute ICP values without manual feature extraction.
  We will also present a complementary feature-based machine learning appro
 ach that leverages pulse morphology descriptors and patient demographics t
 hrough gradient boosting and random forest models.
DTSTART;TZID=Europe/Paris:20260513T150000
DTEND;TZID=Europe/Paris:20260513T150000
LAST-MODIFIED:20260313T110604Z
LOCATION:Aula B203
SUMMARY:Illuminating the black box: Non-invasive intracranial pressure esti
 mation via near-infrared photonics and deep learning - Viacheslav Danilov
URL;TYPE=URI:https://www.diag.uniroma1.it/node/30655
END:VEVENT
END:VCALENDAR