Segmentation Informed by Manifold Learning

In many biomedical imaging applications, video sequences are captured with low resolution and low contrast challenging conditions in which to detect, segment, or track features. When image deformations have just a few underlying causes, such as continuously captured cardiac MRI without breath-holds or gating, the captured images lie on a lowdimensional, non-linear manifold. The manifold structure of such image sets can be extracted by automated methods for manifold learning. Furthermore, the manifold structure of these images offers new constraints for tracking and segmentation of relevant image regions. We illustrate how to incorporate these new constraints within a snake-based energy minimization approach, and demonstrate improvements in using snakes to segment a set of cardiac MRI images in challenging conditions.