Synthetic Magnetic Resonance Images for Domain Adaptation: Application to Fetal Brain Tissue Segmentation

Details

Serval ID
serval:BIB_EAEBE49506C4
Type
Article: article from journal or magazin.
Collection
Publications
Institution
Title
Synthetic Magnetic Resonance Images for Domain Adaptation: Application to Fetal Brain Tissue Segmentation
Journal
2022 IEEE 19th International Symposium on Biomedical Imaging (ISBI)
Author(s)
de Dumast Priscille, Kebiri Hamza, Payette Kelly, Jakab Andras, Lajous Helene, Cuadra Meritxell Bach
Publication state
Published
Issued date
28/03/2022
Peer-reviewed
Oui
Language
english
Abstract
The quantitative assessment of the developing human brain in utero is crucial to fully understand neurodevelopment. Thus, automated multi-tissue fetal brain segmentation algorithms are being developed, which in turn require annotated data to be trained. However, the available annotated fetal brain datasets are limited in number and heterogeneity, hampering domain adaptation strategies for robust segmentation. In this context, we use FaBiAN, a Fetal Brain magnetic resonance Acquisition Numerical phantom, to simulate various realistic magnetic resonance images of the fetal brain along with its class labels. We demonstrate that these multiple synthetic annotated data, generated at no cost and further reconstructed using the target super-resolution technique, can be successfully used for domain adaptation of a deep learning method that segments seven brain tissues. Overall, the accuracy of the segmentation is significantly enhanced, especially in the cortical gray matter, the white matter, the cerebellum, the deep gray matter and the brainstem.
Research datasets
Funding(s)
Swiss National Science Foundation / Projects / 182602
Swiss National Science Foundation / Projects / 141283
Create date
31/05/2022 7:52
Last modification date
01/06/2022 5:39
Usage data