Automatic Brain Extraction in Fetal MRI using Multi-Atlas-based Segmentation

Details

Serval ID
serval:BIB_40F526281083
Type
Inproceedings: an article in a conference proceedings.
Collection
Publications
Institution
Title
Automatic Brain Extraction in Fetal MRI using Multi-Atlas-based Segmentation
Title of the conference
Medical Imaging 2015: Image Processing
Author(s)
Tourbier Sebastien, Hagmann Patric, Cagneaux Maud, Guibaud Laurent, Gorthi Subrahmanyam, Schaer Marie, Thiran Jean-Philippe, Meuli Reto, Cuadra Bach Meritxell
Publisher
Spie-Int Soc Optical Engineering
Address
Bellingham, March 20, 2015
ISBN
978-1-62841-503-2
ISSN-L
0277-786X
Publication state
Published
Issued date
2015
Editor
Ourselin S, Styner M.A.
Volume
9413
Series
SPIE Proceedings
Pages
94130Y
Language
english
Notes
EPFL-CONF-212414
Abstract
In fetal brain MRI, most of the high-resolution reconstruction algorithms rely on brain segmentation as a preprocessing step. Manual brain segmentation is however highly time-consuming and therefore not a realistic solution. In this work, we assess on a large dataset the performance of Multiple Atlas Fusion (MAF) strategies to automatically address this problem. Firstly, we show that MAF significantly increase the accuracy of brain segmentation as regards single-atlas strategy. Secondly, we show that MAF compares favorably with the most recent approach (Dice above 0.90). Finally, we show that MAF could in turn provide an enhancement in terms of reconstruction quality.
Keywords
Fetal MRI, Brain Extraction, Template-based, Segmentation, Multi-Atlas Fusion
Create date
27/11/2015 14:22
Last modification date
20/08/2019 13:40
Usage data