BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20260619T054207EDT-2561hG1lgD@132.216.98.100
DTSTAMP:20260619T094207Z
DESCRIPTION:LIVIA seminar\n\nSpeaker: Léo Milecki\, PhD candidate at Centra
 leSupelec\, Paris-Saclay University\, France\n\n\n	Abstract:\n\n	Renal trans
 plantation appears as the most effective solution for end-stage renal dise
 ase. However\, it may lead to renal allograft rejection or dysfunction wit
 hin 15%-27% of patients in the first 5 years post-transplantation. Resulti
 ng from a simple blood test\, serum creatinine is the primary clinical ind
 icator of kidney function by calculating the Glomerular Filtration Rate. T
 hese characteristics motivate the challenging task of predicting serum cre
 atinine early post-transplantation while investigating and exploring its c
 orrelation with imaging data. In this talk\, I will present our recent wor
 k regarding this task\, which exploits transformer encoders and contrastiv
 e learning schemes. Our experiments aim to highlight the relevance of cons
 idering sequential imaging data for this task and therefore in the study o
 f chronic dysfunction mechanisms in renal transplantation\, setting the pa
 th for future research in this area.\n\n\nShort bio:\n\nLéo Milecki is a P
 hD student at MICS\, CentraleSupelec\, Paris-Saclay University\, France (n
 ear Paris) under the supervision of Maria Vakalopoulou at MICS and Marc-Ol
 ivier Timsit\, Paris University. His PhD thesis focuses on applying novel 
 Machine Learning algorithms to analyze biomedical data toward graft reject
 ion diagnostic or prognosis after renal transplantation\, focusing on Deep
  Learning and un-/weakly-/self-supervised methods. He is currently visitin
 g Provost Ultrasound Lab at Polytechnique Montreal until 21st December.\n
 \n\n	 \n
DTSTART:20221207T170000Z
DTEND:20221207T180000Z
LOCATION:CA\, ZOOM
SUMMARY:Data-driven methods for renal transplantation monitoring
URL:/cim/channels/event/data-driven-methods-renal-tran
 splantation-monitoring-351790
END:VEVENT
END:VCALENDAR