Automatic 3D Multiorgan Segmentation via Clustering and Graph Cut Using Spatial Relations and Hierarchically-Registered Atlases

Autor:	Sébastien Valette, Razmig Kéchichian, Michaël Sdika, Michel Desvignes
Rok vydání:	2014
Předmět:	Computer science business.industry Probabilistic logic Pattern recognition Topology Spatial relation Computer Science::Computer Vision and Pattern Recognition Cut Graph (abstract data type) Adjacency list Segmentation Artificial intelligence Cluster analysis Voronoi diagram business
Zdroj:	Medical Computer Vision: Algorithms for Big Data ISBN: 9783319139715 MCV
DOI:	10.1007/978-3-319-13972-2_19
Popis:	We propose a generic method for automatic multiple-organ segmentation based on a multilabel Graph Cut optimization approach which uses location likelihood of organs and prior information of spatial relationships between them. The latter is derived from shortest-path constraints defined on the adjacency graph of structures and the former is defined by probabilistic atlases learned from a training dataset. Organ atlases are mapped to the image by a fast (2+1)D hierarchical registration method based on SURF keypoints. Registered atlases are furthermore used to derive organ intensity likelihoods. Prior and likelihood models are then introduced in a joint centroidal Voronoi image clustering and Graph Cut multiobject segmentation framework. Qualitative and quantitative evaluation has been performed on contrast-enhanced CT images from the Visceral Benchmark dataset.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::7fbba0e6a2685f0b0ef57cdc2c5d2591 https://doi.org/10.1007/978-3-319-13972-2_19 Zobrazit plný text záznamu