Semi-automatic muscle segmentation in MR images using deep registration-based label propagation - LATIM - IMT Atlantique Accéder directement au contenu
Article Dans Une Revue Pattern Recognition Année : 2023

Semi-automatic muscle segmentation in MR images using deep registration-based label propagation

Résumé

Fully automated approaches based on convolutional neural networks have shown promising performances on muscle segmentation from magnetic resonance (MR) images, but still rely on an extensive amount of training data to achieve valuable results. Muscle segmentation for pediatric and rare diseases cohorts is therefore still often done manually. Producing dense delineations over 3D volumes remains a timeconsuming and tedious task, with significant redundancy between successive slices. In this work, we propose a segmentation method relying on registration-based label propagation, which provides 3D muscle delineations from a limited number of annotated 2D slices. Based on an unsupervised deep registration scheme, our approach ensures the preservation of anatomical structures by penalizing deformation compositions that do not produce consistent segmentation from one annotated slice to another. Evaluation is performed on MR data from lower leg and shoulder joints. Results demonstrate that the proposed few-shot multi-label segmentation model outperforms state-of-the-art techniques.
Fichier principal
Vignette du fichier
PR___Few_shot_muscle_segmentation_in_MR_images_using_deep_registration_based_label_propagation (9).pdf (5.69 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
licence : Domaine public

Dates et versions

hal-03945559 , version 1 (18-01-2023)
hal-03945559 , version 2 (28-02-2023)

Identifiants

Citer

Nathan Decaux, Pierre-Henri Conze, Juliette Ropars, Xinyan He, Frances T Sheehan, et al.. Semi-automatic muscle segmentation in MR images using deep registration-based label propagation. Pattern Recognition, 2023, 140 (August 2023), pp.109529. ⟨10.1016/j.patcog.2023.109529⟩. ⟨hal-03945559v2⟩
73 Consultations
136 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More