主 题: Diffeomorphic Metric Matching with Applications in Medical Image
报告人: Yan CAO (PhD,Tenure-track Assistant Professor)
时 间: 2009-05-27 上午10:10 - 12:00
地 点: 理科一号楼 1568
Changes in the anatomical structures occur during the development
and aging process, as well as during many disease and injury process.
Detecting and monitoring the anatomy changes are crucial in disease
diagnosis, treatment and prevention. We would like to develop
mathematical models and computational tools to represent and quantify
the variation of different shapes and structures associated with them.
In our approach, anatomy is modeled as a deformable template and the
images are viewed as the orbit under the diffeomorphic transformations
acting on a template. A geodesic path is computed on the manifold of
diffeomorphisms connecting two images which transforms a template into
target. New algorithms for image registration and image segmentation are
developed based on this approach. We have applied this method to study
cardiac shape, fiber and laminar structure in normal and disease through
diffusion tensor magnetic resonance images. We have also applied it to
analyze brain aging.