Abstract #4174
Parcellating Brain Cortical Regions at Multiple Levels of Granularity using the Weighted K-means Algorithm
Shih-Yen Lin 1,2 , Hengtai Jan 1 , Tsang-Chu Yu 3 , Yi-Ping Chao 3 , Kuan-Hung Cho 4 , and Li-Wei Kuo 1
1
Institute of Biomedical Engineering and
Nanomedicine, National Health Research Institutes,
Miaoli, Taiwan,
2
Department
of Computer Science, National Chiao Tung University,
Hsinchu, Taiwan,
3
Department
of Computer Science and Information Engineering, Chang
Gung University, Taoyuan, Taiwan,
4
Institute
of Brain Science, National Yang-Ming University, Taipei,
Taiwan
To investigate the brain networks at multiple scales,
recent studies have attempted to divide the cortical
regions into smaller parcels at multiple levels of
granularity. In this study, we proposed a parcellation
method based on the weighted k-means algorithm with the
following desirable features, including similar
subdivision volume size over the whole brain, not
fragmented, fully deterministic and highly reproducible.
A quantitative evaluation with calculating the
coefficient of variance among all parcels was performed.
Our results show the variances significantly drop
between intermediate to finest levels, suggesting that
the clustering sizes become more uniformly. Future works
include developing more quantitative evaluation
parameters, demonstration on other brain atlases and
application on brain network analysis at multiple
scales.
How to access this content:
For one year after publication, abstracts and videos are only open to registrants of this annual meeting. Registrants should use their existing login information. Non-registrant access can be purchased via the ISMRM E-Library.
After one year, current ISMRM & ISMRT members get free access to both the abstracts and videos. Non-members and non-registrants must purchase access via the ISMRM E-Library.
After two years, the meeting proceedings (abstracts) are opened to the public and require no login information. Videos remain behind password for access by members, registrants and E-Library customers.
Click here for more information on becoming a member.
