BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:Europe/Warsaw
BEGIN:DAYLIGHT
DTSTART:20260329T030000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20251026T020000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20251203T122806Z
UID:7E5CFFB3-623F-404F-B488-C54D094C3AC5
DTSTART;TZID=Europe/Warsaw:20251203T121500
DTEND;TZID=Europe/Warsaw:20251203T130000
DESCRIPTION:The source of the image in positron emission tomography (PET) i
 s the detection of pairs of gamma photons produced by the annihilation of 
 a positron with an electron. However\, the recorded coincidence events inc
 lude not only true signals\, but also noise: Compton-scattered events (in 
 the patient's body and in the detector crystals) and random events. Their 
 effective identification can significantly improve image reconstruction qu
 ality and measurement accuracy. The presentation will discuss the applicat
 ion of deep learning to the classification of coincidence events. The mode
 l\, based on a 3D CNN architecture\, processes a spatial map extended with
  physical characteristics of coincidences\, such as photon energies\, dete
 ction time differences\, and event geometry. The current results and prosp
 ects for the development of the method will be discussed.\n\nSpeaker(s): M
 ichał \, \n\nRoom: 229\, Bldg: Faculty of Electronics and Information Tec
 hnology\, Nowowiejska 15/19\, Warsaw\, Mazowieckie\, Poland\, 00-665
LOCATION:Room: 229\, Bldg: Faculty of Electronics and Information Technolog
 y\, Nowowiejska 15/19\, Warsaw\, Mazowieckie\, Poland\, 00-665
ORGANIZER:konrad.jedrzejewski@pw.edu.pl
SEQUENCE:11
SUMMARY: Coincidence events classification in PET tomography using machine 
 learning methods
URL;VALUE=URI:https://events.vtools.ieee.org/m/518356
X-ALT-DESC:Description: <br /><p>The source of the image in positron emissi
 on tomography (PET) is the detection of pairs of gamma photons produced by
  the annihilation of a positron with an electron. However\, the recorded c
 oincidence events include not only true signals\, but also noise: Compton-
 scattered events (in the patient's body and in the detector crystals) and 
 random events. Their effective identification can significantly improve im
 age reconstruction quality and measurement accuracy. The presentation will
  discuss the application of deep learning to the classification of coincid
 ence events. The model\, based on a 3D CNN architecture\, processes a spat
 ial map extended with physical characteristics of coincidences\, such as p
 hoton energies\, detection time differences\, and event geometry. The curr
 ent results and prospects for the development of the method will be discus
 sed.</p>
END:VEVENT
END:VCALENDAR