[Back]


Talks and Poster Presentations (without Proceedings-Entry):

R. Licandro, E. Schwartz, G. Langs, R. Sablatnig:
"Longitudinal Diffeomorphic Fetal Brain Atlas Learning For Tissue Labeling Using Geodesic Regression And Graph Cuts";
Poster: Medical Imaging Summer School 2014, Favignana, Sizilien, Italien; 2014-07-28 - 2014-08-01.



English abstract:
The human brain undergoes fundamental structural changes between the second and the third
trimester of pregnancy [1]. The most accurate non-invasive method for observing these events to
date is the (ultra) fast magnetic resonance (MR) imaging technique. It allows to image a fetus at
a satisfying resolution, despite its small size or varying position [2]. A problem of MR imaging is the
lack of comparability and constancy of gray-values, which are mapped according to the proton
(hydrogen) concentration. It differs among patients and results in varying gray-values for varying
proton density [3]. This motivates to build a fetal brain atlas to use it as a standard space. Brain
structures can be mapped according to marked anatomical locations, to make fetal brains
comparable for studying brain development, fetal pathology locations, fetal abnormalities or
anatomy. !
!
The aim of the work is to provide an atlas of the developing fetal brain, consisting of a
continuous, quantifiable model of brain development derived by geodesic shooting regression
[4,5] and an automated labeling procedure using a graph cut based segmentation approach [7].

Created from the Publication Database of the Vienna University of Technology.