Talk
"Image-driven Population Analysis through Mixture Modeling"
Mert R. Sabuncu, MIT CSAIL
Tuesday, October 7, 2008 at 12:00 Noon
Room 368 (CIT 3rd floor)
In this talk, I will present *iCluster*, a fast and efficient algorithm that clusters a set of images while co-registering them using a parameterized, nonlinear transformation model. The output of the algorithm is a small number of template images that represent different modes in a population. This is in contrast with traditional, hypothesis-driven computational anatomy approaches that assume a single template to construct an atlas. We derive the algorithm based on a generative model of an image population as a mixture of deformable template images. I will present some interesting results from several experiments. In one experiment, I will demonstrate the utility of having multiple atlases for the application of localizing medial temporal brain structures in a pool of subjects that consists of healthy controls and schizophrenia patients. Next, I will show how we employed iCluster to partition a data set of 416 whole brain MR volumes of subjects aged 18 through 96 years into three sub-groups, which mainly correspond to age groups. The templates reveal significant structural differences across these age groups that confirm previous findings in aging research. In another experiment, we ran iCluster on a group of 15 patients with dementia and 15 age-matched healthy controls. The algorithm produced three modes that mainly correspond to a sub-population of healthy controls, a sub-population of patients with dementia and a mixture group that contains both types. These results suggest that the algorithm can be used to discover sub-populations that correspond to interesting structural or functional "modes."
Mert R. Sabuncu is a post-doctoral researcher in Polina Golland's "medical vision" group at MIT's CSAIL. He received his PhD degree from the Department of Electrical Engineering at Princeton University in 2006. His research interests lie in signal/image processing, pattern recognition and artificial intelligence. His dissertation work was on information-theoretic multi-modal image registration. He used a minimum spanning tree based entropy estimation technique to design an efficient and fast rigid-body multi-modal image registration algorithm. Currently, he is working on a data-driven population analysis approach, named iCluster, and exploring the theoretical and practical link between "learning" and "image registration."
Host: David Laidlaw
| Page Owner: Webmaster | Last Modified: Fri Sep 26 15:24:40 2008 |