BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:BSU Seminar: 'Double soft-thresholded model for multi-group scalar
  on vector-valued image regression' - Prof Arkaprava Roy\, University of F
 lorida
DTSTART:20221216T140000Z
DTEND:20221216T150000Z
UID:TALK193699@talks.cam.ac.uk
CONTACT:Alison Quenault
DESCRIPTION:In this paper\, we develop a novel spatial variable selection 
 method for scalar on vector-valued image regression in a multi-group setti
 ng. Here\, ‘vector-valued image’ refers to the imaging datasets that c
 ontain vector-valued information at each pixel/voxel location\, such as in
  RGB color images\, multimodal medical images\, DTI imaging\, etc. The foc
 us of this work is to identify the spatial locations in the image having a
 n important effect on the scalar outcome measure. Specifically\, the overa
 ll effect of each voxel is of interest. We thus develop a novel shrinkage 
 prior by soft-thresholding the ℓ2 norm of a latent multivariate Gaussian
  process. It allows us to estimate sparse and piecewise-smooth spatially v
 arying vector-valued regression coefficient function. Motivated by the rea
 l data\, we further develop a double soft-thresholding based framework whe
 n there are multiple pre-specified subgroups. For posterior inference\, an
  efficient MCMC algorithm is developed. We compute the posterior contracti
 on rate for parameter estimation and also establish consistency for variab
 le selection of the proposed Bayesian model\, assuming that the true regre
 ssion coefficients are Holder smooth. Finally\, we demonstrate the advanta
 ges of the proposed method in simulation studies and further illustrate in
  an ADNI dataset for modeling MMSE scores based on DTI-based vector-valued
  imaging markers.
LOCATION:Large Seminar Room\, East Forvie Building\, Forvie Site\, Robinso
 n Way\, Cambridge CB2 0SR
END:VEVENT
END:VCALENDAR