MC 5136
Speaker
Mehran Ebrahimi, University of Toronto, Sunnybrook Health Sciences Centre
Title
Inverse Problems in Imaging and Applications in Medicine
Abstract
In many practical problems in the field of applied sciences, the features of most interest are commonly inferred from other observable quantities. The problem of solving an unknown object from the observed quantities is called an inverse problem. Many classical imaging problems, including image denoising, deblurring, zooming, and registration, can be modelled as inverse problems.
In this talk, we will review general theoretical and computational aspects of inverse theory. We will revisit a number of inverse problems including single-frame image zooming, multi-frame resolution enhancement also known a super-resolution, and image registration.
More specifically, we will present numerical methodologies for automated simultaneous registration and intensity correction of dynamic contrast enhanced magnetic resonance imaging (DCE-MRI) series. Furthermore, we propose an image registration scheme aimed at computer assisted surgery of the breast and validate our results on patient datasets.