BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:From Medical to Industrial Imaging with IMPET
DTSTART;VALUE=DATE-TIME:20260909T115000Z
DTEND;VALUE=DATE-TIME:20260909T123000Z
DTSTAMP;VALUE=DATE-TIME:20260922T173909Z
UID:indico-contribution-422-2057@events.ncbj.gov.pl
DESCRIPTION:Speakers: Wojciech Krzemien (NCBJ)\nMedical and industrial ima
 ging have long influenced one another\, from CT's migration into nondestru
 ctive testing to shared detector technologies. This talk explores that exc
 hange through IMPET\, a project developing AI-enhanced\, quantum-informed 
 multiphoton imaging for industrial applications such as opaque flow charac
 terisation and 3D porous-media analysis. We present recent progress on pos
 itronium-based image reconstruction and simulation\, alongside a brief loo
 k at our PEPT extension.\n\nhttps://events.ncbj.gov.pl/event/468/contribut
 ions/2057/
LOCATION:
URL:https://events.ncbj.gov.pl/event/468/contributions/2057/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Procedural generation of tomographic datasets for machine learning
DTSTART;VALUE=DATE-TIME:20260909T123000Z
DTEND;VALUE=DATE-TIME:20260909T130000Z
DTSTAMP;VALUE=DATE-TIME:20260922T173909Z
UID:indico-contribution-422-2038@events.ncbj.gov.pl
DESCRIPTION:Speakers: Mikołaj Mrozowski (NCBJ)\nIndustrial computed tomog
 raphy allows for non-destructive inspection of complex components\,\nmakin
 g it an interesting domain of applications for machine learning methods.\n
 In this context\, a large bottleneck for training robust models is data ac
 quisition.\nAlready time-intensive task of obtaining data using real-world
  CT scanners \nis further exacerbated by the requirement of creating accur
 ate labels.\n\nWe solve this problem by implementing a pipeline for the ge
 neration of massive \nsynthetic datasets\, and using only some examples of
  real-world data.\n\nOur data pipeline uses parametrized CAD geometry to g
 enerate thousands of \nrandomized objects from which we derive both ground
 -truth labels and \nattenuation data further fed into tomographic simulati
 ons.\n\nThe simulation code is GPU-accelerated allowing us to substantiall
 y \nreduce the time needed to generate the datasets.\n\nTo reproduce effec
 ts visible in real data\, we implement a polychromatic beam\,\nand simulat
 e artefacts such as non-uniformity of the beam and detector matrix respons
 e.\nWe also apply custom beam hardening corrections for our reconstruction
 s.\n\nWe use the synthetic data in semi-supervised training of a W-net mod
 el for the specific\ntask of segmentation of ionization chambers. We show\
 , that semi-supervised approach \nallows for effective training with only 
 partial labeling (as low as 25%-50% of the data).\nWe then validate perfor
 mance of segmentation models trained using simulations on the real-world d
 ata.\n\nhttps://events.ncbj.gov.pl/event/468/contributions/2038/
LOCATION:
URL:https://events.ncbj.gov.pl/event/468/contributions/2038/
END:VEVENT
END:VCALENDAR