Database Annotation with few Examples: An Atlas-based Framework using Diffeomorphic Registration of 3D Trees - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2020

Database Annotation with few Examples: An Atlas-based Framework using Diffeomorphic Registration of 3D Trees

Résumé

Automatic annotation of anatomical structures can help simplify work-flow during interventions in numerous clinical applications but usually involves a large amount of annotated data. The complexity of the labeling task, together with the lack of representative data, slows down the development of robust solutions. In this paper, we propose a solution requiring very few annotated cases to label 3D pelvic arterial trees of patients with benign prostatic hyperplasia. We take advantage of Large Deformation Diffeomorphic Metric Mapping (LD-DMM) to perform registration based on meaningful deformations from which we build an atlas. Branch pairing is then computed from the atlas to new cases using optimal transport to ensure one-to-one correspondence during the labeling process. To tackle topological variations in the tree, which usually degrades the performance of atlas-based techniques, we propose a simple bottom-up label assignment adapted to the pelvic anatomy. The proposed method achieves 97.6% labeling precision with only 5 cases for training, while in comparison learning-based methods only reach 82.2% on such small training sets.
Fichier principal
Vignette du fichier
MICCAI_2020.pdf (752.58 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02949367 , version 1 (25-09-2020)

Identifiants

  • HAL Id : hal-02949367 , version 1

Citer

Pierre-Louis Antonsanti, Thomas Benseghir, Vincent Jugnon, Joan Glaunès. Database Annotation with few Examples: An Atlas-based Framework using Diffeomorphic Registration of 3D Trees. Medical Image Computing and Computer Assisted Intervention – MICCAI 2020, Oct 2020, Lima, Peru. pp.160-170. ⟨hal-02949367⟩
61 Consultations
65 Téléchargements

Partager

Gmail Facebook X LinkedIn More