MRF's for MRI's: Bayesian Reconstruction of MR Images via Graph Cuts
Associate Professor of Computer Science and Radiology,
April 6, 2006
JEC 3117 - 4:00 p.m. to 5:00 p.m.
Refreshments at 3:30 p.m.
Markov Random Fields (MRF's) are a very effective way to impose spatial
smoothness in computer vision. I will describe an application of MRF's to a
non-traditional but important problem in medical imaging: the reconstruction
of MR images from raw fourier data. This can be formulated as a linear
inverse problem, where the goal is to find a spatially smooth solution while
permitting discontinuities. Although it is easy to apply MRF's for MR
reconstruction, the resulting energy minimization problem poses some
interesting challenges. It lies outside of the class of energy functions that
can be straightforwardly minimized with graph cuts. I will show how graph
cuts can nonetheless be adapted to solve this problem, and demonstrate some
preliminary results that are extremely promising.
Joint work with Ashish Raj and Gurmeet Singh.
Ramin Zabih is an associate professor of Computer Science at Cornell
University. His research interests focus on discrete optimization methods and
their applications, especially in early vision and medical imaging. Since
2000 he has also held a joint appointment in the Radiology Department of
Cornell's Weill Medical College. He is best known for his work on energy
minimization via graph cuts, which is the basis for most of the
top-performing stereo algorithms. Two of his papers on this topic received
Best Paper awards at the European Conference on Computer Vision in 2002. He
currently serves as an Associate Editor of the IEEE Transactions on Pattern
Analysis and Machine Intelligence, and is Program Co-chair of the 2007 IEEE
International Conference on Computer Vision and Pattern Recognition.
Hosted by: Daniel Freedman (x4785)
Last updated: February 27, 2006