Multiclass segmentation of brain intraoperative ultrasound images with limited data - Archive ouverte HAL
Accéder directement au contenu Accéder directement à la navigation
Communication dans un congrès

Multiclass segmentation of brain intraoperative ultrasound images with limited data

Abstract : During tumor resection surgery, intraoperative ultrasound images of the brain show anatomical structures like the sulci , falx cerebri and tentorium cerebelli , as well as the tumor. After resection started, the resection cavity is also visible. These elements help with the localization and tumor resection, and can be used to register the preoperative MRI to intraoperative images, to compensate for the tissue deformation occurring during surgery. In this work, we compare single-and multi-class segmentation models for the sulci , falx cerebri , tumor, resection cavity and ventricle. We present strategies to overcome the severe class imbalance in the training data, and train a model with limited data. We show that a multi-class model may leverage inter-class spatial relationships and produce more accurate results than single-class models.
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-03185247
Contributeur : Matthieu Chabanas Connectez-vous pour contacter le contributeur
Soumis le : mardi 30 mars 2021 - 11:57:43
Dernière modification le : vendredi 5 novembre 2021 - 13:25:09

Fichier

paper.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

François-Xavier Carton, Jack H Noble, Florian Le Lann, Bodil K R Munkvold, Ingerid Reinertsen, et al.. Multiclass segmentation of brain intraoperative ultrasound images with limited data. SPIE Medical Imaging, Feb 2021, Online Only, France. pp.19, ⟨10.1117/12.2581861⟩. ⟨hal-03185247⟩

Partager

Métriques

Consultations de la notice

891

Téléchargements de fichiers

98