Multi-atlas labeling with population-specific template and non-local patch-based label fusion

Vladimir Fonov, Pierrick Coupé, Simon Fristed Eskildsen, José V. Manjón, D. Louis Collins

Research output: Contribution to conferencePaperResearchpeer-review

351 Downloads (Pure)

Abstract

We propose a new method combining a population-specific nonlinear
template atlas approach with non-local patch-based structure segmentation
for whole brain segmentation into individual structures. This way, we benefit
from the efficient intensity-driven segmentation of the non-local means
framework and from the global shape constraints imposed by the nonlinear
template matching.
Original languageEnglish
Publication date5 Oct 2012
Number of pages4
Publication statusPublished - 5 Oct 2012
EventMedical Image Computing and Computer Assisted Intervention: 2012 - Nice, France
Duration: 1 Oct 20125 Oct 2012
Conference number: 15

Conference

ConferenceMedical Image Computing and Computer Assisted Intervention
Number15
Country/TerritoryFrance
CityNice
Period01/10/201205/10/2012

Fingerprint

Dive into the research topics of 'Multi-atlas labeling with population-specific template and non-local patch-based label fusion'. Together they form a unique fingerprint.

Cite this