Globally Optimal Label Fusion with Shape Priors

Ipek Oguz; Satyananda Kashyap; Hongzhi Wang; Paul Yushkevich; Milan Sonka

doi:10.1007/978-3-319-46723-8_62

Back

Globally Optimal Label Fusion with Shape Priors

Conference proceeding

Open access

Peer reviewed

Globally Optimal Label Fusion with Shape Priors

Ipek Oguz, Satyananda Kashyap, Hongzhi Wang, Paul Yushkevich and Milan Sonka

Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention, Vol.9901, pp.538-546

10/2016

DOI: 10.1007/978-3-319-46723-8_62

PMCID: PMC5471814

PMID: 28626843

Files and links (1)

url

https://www.ncbi.nlm.nih.gov/pmc/articles/5471814View

Open Access

Abstract

Multi-atlas label fusion methods have gained popularity in a variety of segmentation tasks given their attractive performance. Graph-based segmentation methods are widely used given their global optimality guarantee. We propose a novel approach, GOLF, that combines the strengths of these two approaches. GOLF incorporates shape priors to the label-fusion problem and provides a globally optimal solution even for the multi-label scenario, while also leveraging the highly accurate posterior maps from a multi-atlas label fusion approach. We demonstrate GOLF for the joint segmentation of the left and right pairs of caudate, putamen, globus pallidus and nucleus accumbens. Compared to the FreeSurfer and FIRST approaches, GOLF is significantly more accurate on all reported indices for all 8 structures. We also present comparisons to a multi-atlas approach, which reveals further insights on the contributions of the different components of the proposed framework.

Neuroimaging - methods

Nucleus Accumbens - diagnostic imaging

Brain - diagnostic imaging

Caudate Nucleus - anatomy & histology

Reproducibility of Results

Brain - anatomy & histology

Atlases as Topic

Humans

Middle Aged

Putamen - diagnostic imaging

Globus Pallidus - diagnostic imaging

Globus Pallidus - anatomy & histology

Nucleus Accumbens - anatomy & histology

Magnetic Resonance Imaging

Caudate Nucleus - diagnostic imaging

Putamen - anatomy & histology

Algorithms

Sensitivity and Specificity

Aged, 80 and over

Adult

Aged

Pattern Recognition, Automated

Details

Title: Subtitle: Globally Optimal Label Fusion with Shape Priors
Creators: Ipek Oguz - Iowa Institute for Biomedical Imaging, University of Iowa, Iowa City, USA
Satyananda Kashyap - Iowa Institute for Biomedical Imaging, University of Iowa, Iowa City, USA
Hongzhi Wang - IBM Research, Almaden, USA
Paul Yushkevich - Department of Radiology, University of Pennsylvania, Philadelphia, USA
Milan Sonka - Iowa Institute for Biomedical Imaging, University of Iowa, Iowa City, USA
Resource Type: Conference proceeding
Publication Details: Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention, Vol.9901, pp.538-546
DOI: 10.1007/978-3-319-46723-8_62
PMID: 28626843
PMCID: PMC5471814
eISBN: 3319467239; 9783319467238
ISSN: 0302-9743
eISSN: 1611-3349
Publisher: Germany
Grant note: R01 EB017255 / NIBIB NIH HHS R01 EB004640 / NIBIB NIH HHS R01 NS094456 / NINDS NIH HHS
Language: English
Date published: 10/2016
Academic Unit: Roy J. Carver Department of Biomedical Engineering; Electrical and Computer Engineering; Psychiatry; Radiation Oncology; Injury Prevention Research Center; Ophthalmology and Visual Sciences
Record Identifier: 9984047637802771

Metrics

12 Record Views