Multi-subject connectivity-based parcellation of the human IPL using Gaussian mixture models and hidden Markov random fields

Author

Wang, Eddie ; Tungaraza, Rosalia F. ; Haynor, D.R. ; Grabowski, Thomas J.

Author_Institution

Integrated Brain Imaging Center, Univ. of Washington, Seattle, WA, USA

fYear

2013

fDate

7-11 April 2013

Firstpage

520

Lastpage

523

Abstract

Connectivity has been proposed as a criterion for functional-anatomic segregation of cortical areas. We present a new method of characterizing the DTI-based connectivity profile of cortical voxels using Gaussian mixture models (GMMs). Parcellation of the human IPL was performed on connectivity profiles using a hidden Markov random field (HMRF) model. We applied our approach to multi-subject parcellation. Using the multisubject GMM-HMRF approach, results in a smoother segmentation of IPL that is independent of the set of subjects and visually consistent with the Juelich Atlas.

Keywords

Gaussian processes; biodiffusion; biomedical MRI; brain; hidden Markov models; image segmentation; medical image processing; random processes; DTI-based connectivity profile; HMRF model; Juelich Atlas; cortical voxel; diffusion tensor imaging; functional-anatomic segregation; gaussian mixture model; hidden Markov random field model; human IPL parcellation; inferior pareital lobule; multisubject GMM-HMRF approach; multisubject connectivity-based parcellation; smooth IPL segmentation; Brain modeling; Gaussian mixture model; Hidden Markov models; Imaging; Joints; Measurement; Gaussian mixture model; connectivity-based parcellation; hidden Markov random fields; multisubject analysis; probabilistic tractography;

fLanguage

English

Publisher

ieee

Conference_Titel

Biomedical Imaging (ISBI), 2013 IEEE 10th International Symposium on

Conference_Location

San Francisco, CA

ISSN

1945-7928

Print_ISBN

978-1-4673-6456-0

Type

conf

DOI

10.1109/ISBI.2013.6556526

Filename

6556526