BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20261027T044337EDT-7125vLBoXE@132.216.98.100
DTSTAMP:20261027T084337Z
DESCRIPTION:Shariq Mohammed\, PhD\n\nAssistant Professor\n	Department of Bio
 statistics\n	Boston University\, School of Public Health\n\nWHEN: Wednesday
 \, March 20\, 2024\, from 3:30 to 4:30 p.m.\n	WHERE: Hybrid | 2001 McGill C
 ollege Avenue\, Room 1201\; Zoom\n	NOTE: Shariq Mohammed will be presenting
  from Boston\n\nAbstract\n\nQuantification of heterogeneity in the tumor m
 icroenvironment is extremely important as differentiating disease types vi
 sually is challenging. In this talk\, we will present a statistical framew
 ork that quantifies spatial interactions in biomedical images to build pre
 diction models for clinical phenotypes. We first build a spatial regressio
 n model to assess spatial interactions in regions of interest in the image
 . The heterogeneity in the spatial interactions in each image is then repr
 esented as a probability density function (serving as a signature quantify
 ing spatial interactions). These density functions are analyzed using a Ri
 emannian-geometric framework to include them as covariates in models that 
 predict clinical outcomes of interest. We present our methodology with app
 lications to radiology imaging in brain cancer to predict isocitrate dehyd
 rogenase mutation\, and to pathology imaging in pancreatic cancer to disti
 nguish between different pancreatic disease subtypes.\n\nSpeaker bio\n\nPl
 ease visit: https://shariq-mohammed.github.io/\n\n \n
DTSTART:20240320T193000Z
DTEND:20240320T203000Z
SUMMARY:Quantifying Imaging Heterogeneity Via Density Functions with Applic
 ations in Brain and Pancreatic Cancer Imaging
URL:https://www.mcgill.ca/epi-biostat-occh/channels/event/quantifying-imagi
 ng-heterogeneity-density-functions-applications-brain-and-pancreatic-cance
 r-imaging-355666
END:VEVENT
END:VCALENDAR