Discrete multi atlas segmentation using agreement constraints

Stavros Alchatzidis, Aristeidis Sotiras, Nikos Paragios

Research output: Contribution to conferencePaperpeer-review

10 Scopus citations


In this paper we propose an approach for integrated volume segmentation and multiatlas registration. The aim is to recover simultaneously all atlas deformations along with a segmentation mask that imposes consistency between their deformed segmentation maps. This is modeled through a pairwise graphical model where deformation variables are coupled with segmentation ones. Optimization via dual decomposition is used to recover the optimal solution of the method. Promising results on the IBSR dataset demonstrate the potential of our method where improvement is obtained when comparing to the post-registration label fusion.

Original languageEnglish
StatePublished - 2014
Externally publishedYes
Event25th British Machine Vision Conference, BMVC 2014 - Nottingham, United Kingdom
Duration: Sep 1 2014Sep 5 2014


Conference25th British Machine Vision Conference, BMVC 2014
CountryUnited Kingdom

Fingerprint Dive into the research topics of 'Discrete multi atlas segmentation using agreement constraints'. Together they form a unique fingerprint.

Cite this