Titre
Improving Cross-Domain Brain Tissue Segmentation in Fetal MRI with Synthetic Data
Type
chapitre
Institution
UNIL/CHUV/Unisanté + institutions partenaires
Auteur(s)
Zalevskyi, Vladyslav
Auteure/Auteur
Sanchez, Thomas
Auteure/Auteur
Roulet, Margaux
Auteure/Auteur
Aviles Verdera, Jordina
Auteure/Auteur
Hutter, Jana
Auteure/Auteur
Kebiri, Hamza
Auteure/Auteur
Bach Cuadra, Meritxell
Auteure/Auteur
Liens vers les personnes
Liens vers les unités
Maison d’édition
Springer Nature Switzerland
Titre du livre ou conférence/colloque
Lecture Notes in Computer Science
ISBN du livre
9783031723773
Statut éditorial
Publié
Date de publication
2024
Première page
437
Dernière page/numéro d’article
447
Peer-reviewed
Oui
Langue
anglais
Résumé
Segmentation of fetal brain tissue from magnetic resonance imaging (MRI) plays a crucial role in the study of in utero neurodevelopment. However, automated tools face substantial domain shift challenges as they must be robust to highly heterogeneous clinical data, often limited in number and lacking annotations. Indeed, high variability of the fetal brain morphology, MRI acquisition parameters, and superresolution reconstruction (SR) algorithms adversely affect the model’s performance when evaluated out-of-domain. In this work, we introduce FetalSynthSeg, a domain randomization method to segment fetal brain MRI, inspired by SynthSeg. Our results show that models trained solely on synthetic data outperform models trained on real data in out-ofdomain settings, validated on a 120-subject cross-domain dataset. Furthermore, we extend our evaluation to 40 subjects acquired using lowfield (0.55T) MRI and reconstructed with novel SR models, showcasing robustness across different magnetic field strengths and SR algorithms. Leveraging a generative synthetic approach, we tackle the domain shift problem in fetal brain MRI and offer compelling prospects for applications in fields with limited and highly heterogeneous data.
PID Serval
serval:BIB_973F8E4A8F68
Date de création
2024-10-23T14:14:03.851Z
Date de création dans IRIS
2025-05-20T23:42:01Z
Fichier(s)![Vignette d'image]()
En cours de chargement...
Nom
2403.15103v1.pdf
Version du manuscrit
preprint
Taille
7.3 MB
Format
Adobe PDF
PID Serval
serval:BIB_973F8E4A8F68.P001
URN
urn:nbn:ch:serval-BIB_973F8E4A8F688
Somme de contrôle
(MD5):6bd9f0d6f7ecfd7142eb6c34f218fefe