In academic collaboration with: ETH Zürich; University of Zürich; Max Planck Institute for Informatics; Argonne National Laboratory; Northwestern University
Scientific Director: Prof. Dr. Bjoern Menze
Contact Person(s): Markus Rempfler
|
Keywords: IBBM: image computing
Abstract
Segmentation of the vasculature from image data is relevant for many biomedical applications and has been subject to research for many years. The reconstruction of the vascular networks, however, remains a difficult task when it comes to low-resolution data. In this project, we address such a reconstruction of cerebrovascular networks from low-resolution microMRA images of mice. We employ methods ranging from state-of-the-art segmentation algorithms for local detection of vessels to discrete optimization techniques to estimate the best network with respect to a probabilistic model.
Pictures
|
Figure 1: Overview of the reconstruction scheme.
|
|
|
Figure 2: Illustration of the effect of incorporating physiological knowledge on geometrical relations of bifurcations.
|
|
|
Figure 3: Cerebrovascular network reconstructed from a high-resolution microCT of a corrosion casted mouse brain.
|
|
Team
Contact Person(s)
Working Group
Location
Visit our lab at Garching.
internal project page
Please contact
Markus Rempfler for available student projects within this research project.