Meeting Banner
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.

This abstract and the presentation materials are available to members only; a login is required.

Join Here