Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
New Methods for the Segmentation of Medical Image Data with Applications to Deep Brain Structures,
 

Summary: New Methods for the Segmentation of Medical Image
Data with Applications to Deep Brain Structures,
Vessel Detection and White Matter Brain Tractography
Allen R. Tannenbaum
Julian Hightower Professor
School of Electrical and Computer Engineering and Biomedical Engineering Department
Georgia Institute of Technology
Departmental Hosts: Mustafa Khammash and B.S. Manjunath
Wednesday, October 4th, 2006, 12.30 -1.30 p.m., ESB 2001
ABSTRACT
In this talk, we describe some new techniques for the segmentation of medical imaging data. The first method is
based on a directional modification of the conformal (geodesic) active contour framework. Here one modifies the
ordinary Euclidean metric by an image dependent conformal (weighting) factor, and computes the corresponding
curve shortening flow. The conformal factor which is chosen only depends on position and is in this sense isotropic.
In our new work, we propose a framework in which directionality is added to the factor. This has a number of appli-
cations including the detection of curves in images, and in white matter brain tractography.
Further, we present a novel multiscale shape representation and segmentation algorithm based on the spherical
wavelet transform. Our work is motivated by the need to compactly and accurately encode variations at multiple
scales in the shape representation in order to drive the segmentation and shape analysis of deep brain structures,
such as the caudate nucleus or the hippocampus. Our proposed shape representation can be optimized to com-

  

Source: Akhmedov, Azer - Department of Mathematics, University of California at Santa Barbara

 

Collections: Mathematics