PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Bayesian Experimental Design of Magnetic Resonance Imaging Sequences
M.W. Seeger, H. Nickisch, R. Pohmann and B. Schölkopf
In: The Twenty-Second Annual Conference on Neural Information Processing Systems (NIPS 2008), 8-11 Dec 2008, Vancouver, Canada.


We show how improved sequences for magnetic resonance imaging can be found through automated optimization of Bayesian design scores. Combining recent advances in approximate Bayesian inference and natural image statistics with high-performance numerical computation, we propose the first scalable Bayesian experimental design framework for this problem of high relevance to clinical and brain research. Our solution requires approximate inference for dense, non-Gaussian models on a scale seldom addressed before. We propose a novel scalable variational inference algorithm, and show how powerful methods of numerical mathematics can be modified to compute primitives in our framework. Our approach is evaluated on a realistic setup with raw data from a 3T MR scanner.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Poster)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Computational, Information-Theoretic Learning with Statistics
Learning/Statistics & Optimisation
Brain Computer Interfaces
Theory & Algorithms
ID Code:4351
Deposited By:Bernhard Schölkopf
Deposited On:13 March 2009