Communication Dans Un Congrès Année : 2025

FLAIRBrainSeg: Fine-grained brain segmentation using FLAIR MRI only

Résumé

This paper introduces FLAIRBrainSeg, a novel method for fine-grained segmentation of brain structures using only FLAIR MRIs, specifically targeting cases where access to other imaging modalities is limited. By leveraging existing automatic segmentation methods, we train a network to approximate segmentations, typically obtained from T1-weighted MRIs. Our method produces segmentations of 132 structures and is robust to multiple sclerosis lesions. Experiments on both in-domain and out-of-domain datasets demonstrate that our method outperforms modality-agnostic approaches based on image synthesis, the only currently available alternative for performing brain parcellation using FLAIR MRI alone. This technique holds promise for scenarios where T1-weighted MRIs are unavailable or to reduce acquisition time, and offers a valuable alternative for clinicians and researchers in need of reliable anatomical segmentation.

Fichier principal
Vignette du fichier
138_FLAIRBrainSeg_Fine_Grained.pdf (2.58 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-05213598 , version 1 (18-08-2025)

Licence

Identifiants

  • HAL Id : hal-05213598 , version 1

Citer

Edern Le Bot, Rémi Giraud, Boris Mansencal, Thomas Tourdias, Josè V Manjon, et al.. FLAIRBrainSeg: Fine-grained brain segmentation using FLAIR MRI only. Medical Imaging with Deep Learning (MIDL 2025), Jul 2025, Salt Lake City, UT, United States. ⟨hal-05213598⟩
249 Consultations
186 Téléchargements

Partager

  • More