Automatic Multiorgan Segmentation via Multiscale Registration and Graph Cut - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue IEEE Transactions on Medical Imaging Année : 2018

Automatic Multiorgan Segmentation via Multiscale Registration and Graph Cut

Résumé

We propose an automatic multiorgan segmentation method for 3D radiological images of different anatomical content and modality. The approach is based on a simultaneous multilabel Graph Cut optimization of location, appearance and spatial configuration criteria of target structures. Organ location is defined by target-specific probabilistic atlases (PA) constructed from a training dataset using a fast (2+1)D SURF-based multiscale registration method involving a simple 4-parameter transformation. PAs are also used to derive target-specific organ appearance models represented as intensity histograms. The spatial configuration prior is derived from shortest-path constraints defined on the adjacency graph of structures. Thorough evaluations on Visceral project benchmarks and training dataset, as well as comparisons with the state of the art confirm that our approach is comparable to and often outperforms similar approaches in multiorgan segmentation, thus proving that the combination of multiple suboptimal but complementary information sources can yield very good performance.
Fichier principal
Vignette du fichier
main.pdf (5.87 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01902809 , version 1 (23-10-2018)

Identifiants

Citer

Razmig Kéchichian, Sébastien Valette, Michel Desvignes. Automatic Multiorgan Segmentation via Multiscale Registration and Graph Cut. IEEE Transactions on Medical Imaging, 2018, 37 (12), pp.2739-2749. ⟨10.1109/TMI.2018.2851780⟩. ⟨hal-01902809⟩
284 Consultations
247 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More