Aarhus University Seal

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

Research output: Contribution to conferencePaperResearchpeer-review

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 year5 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


ConferenceMedical Image Computing and Computer Assisted Intervention

Bibliographical note

ISBN-10: 1479126187
ISBN-13: 978-1479126187

See relations at Aarhus University Citationformats

Download statistics

No data available

ID: 50684504