Abstract #4618
Segmentation of fetal pericerebral spaces based on reconstructed high-resolution MRI
Maud CAGNEAUX 1,2 , Meritxell BACH CUADRA 3,4 , Sbastien TOURBIER 3,4 , Marie SCHAER 5 , Salem HANNOUN 2 , Laurent GUIBAUD 1 , and Dominique SAPPEY-MARINIER 2
1
Radiology, Hpital Femme Mre Enfant, Lyon,
France,
2
CREATIS
(UMR 5220 CNRS & U1044 INSERM), University of Lyon and
CERMEP-Imagerie du Vivant, Lyon, France,
3
University
Hospital Center (CHUV) and University of Lausanne
(UNIL), Lausanne, Switzerland,
4
Center
for Biomedical Imaging (CIBM), Lausanne, Switzerland,
5
University
of Geneva, Switzerland
The aim of our study is to determine the feasibility of
the fetal brain segmentation applied to pericerebral
spaces (PCS), which relies only on subjective pattern
recognition expertise. 10 patients who underwent a fetal
MRI were included. High-resolution reconstruction using
motion compensation BTK was applied to obtain volumetric
images of the fetal brain from 2D MR stacks. PCS were
extracted using semi-automatic segmentation, requiring
manual expert slice to slice corrections. Our study
demonstrates the feasibility of PCS segmentation, albeit
time consuming and expert-dependent. It could help
diagnosing fetal cerebral pathologies and become a daily
tool in the fetal brain exploration.
This abstract and the presentation materials are available to members only;
a login is required.
Join Here