| Computerand Communication Technology |
|
|
|
|
| Insula functional parcellation by searching Gaussian mixture model (GMM) using immune clonal selection (ICS) algorithm |
| ZHAO Xue-wu1,2, JI Jun-zhong1, YAO Yao1 |
1. Beijing Municipal Key Laboratory of Multimedia and Intelligent Software Technology, Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China;
2. College of Software, Nanyang Normal University, Nanyang 473061, China |
|
|
|
Abstract An insula functional parcellation method based on Gaussian mixture model (GMM) searched by immune clonal selection (ICS) algorithm, called NICS-GMM, was presented to get better functional parcellation structure of insula and deepen our understanding of its functional organization. Based on functional magnetic resonance imaging (fMRI) data, the proposed method first mapped a GMM onto an antibody; then ICS algorithm was performed to search a GMM that could reflect insula functional distribution. Meanwhile, dynamic neighborhood information with the anti-noise capability was integrated into the search process to improve search quality of ICS. Finally, insula functional parcellation was obtained by using GMMs with the highest lilelihood scores. The experiments were conducted on real fMRI data of insula with parcellation numbers of 2 to 12. As a result, GMMs obtained by NICS-GMM have the heighest likelyhood scores and the silhouette index values of the corresponding parcellateion results also reach the maximum. The experimental results demonstrate that the proposed method not only has better global search capability, but also can obtain functional parcellation structures of insula with higher functional consistency and stronger regional continuity.
|
|
Received: 09 January 2017
Published: 22 November 2017
|
|
|
基于免疫克隆选择算法搜索GMM的脑岛功能划分
为了得到更好的脑岛功能划分结构，加深人们对其功能组织性的理解，提出一种基于免疫克隆选择（ICS）算法搜索高斯混合模型（GMM）的脑岛功能划分方法（NICS-GMM）.该方法基于功能磁共振成像（fMRI）数据，将GMM映射到抗体上；利用ICS算法搜索能够反映脑岛功能分布的GMM，并在搜索过程中融入具有抗噪能力的动态邻域信息，以提高其搜索质量；利用最优的GMM实现对脑岛的功能划分.在划分数为2~12的脑岛功能划分上，新方法搜得的GMM具有最高的似然分数，而且相应划分结果的轮廓系数也达到了最大值.真实脑岛fMRI数据上的实验结果表明，该方法不仅具有更强的全局搜索能力，还可以得到具有较高功能一致性与更强区域连续性的脑岛功能划分结构.
|
|
| [1] HONNORAT N, EAVANI H, SATTERTHWAITE T D, et al. GraSP:geodesic graph-based segmentation with shape priors for the functional parcellation of the cortex[J]. Neuroimage, 2015, 106(2):207-221.
[2] MEZER A, YOVEL Y, PASTERNAK O, et al. Cluster analysis of resting-state fMRI time series[J]. Neuroimage, 2009, 45(4):1117-1125.
[3] 赵学武, 冀俊忠, 梁佩鹏. 面向fMRI数据的人脑功能划分[J]. 科学通报, 2016, 61(18):2035-2052. ZHAO Xue-wu, JI Jun-zhong, LIANG Pei-peng. The human brain functional parcellation based on fMRI data[J]. Chinese Science Bulletin, 2016, 61(18):2035-2052.
[4] VERCELLI U, DIANO M, COSTA T, et al. Node detection using high-dimension-al fuzzy parcellation applied to the insula cortex[J]. Neural Plasticity, 2016, 2016(5-6):1-8.
[5] KURTH F, ZILLES K, FOX P T, et al. A linkbetween the systems:functional differentiation andintegration within the human insula revealed by meta-analysis[J]. Brain Structure and Function, 2010,214(5-6):519-534.
[6] CHANG L J, YARKONI T, KHAW M W, et al. Decoding the role of the insula in human cogntion:functional parcellation and large-scale reverse inference[J]. Cerebral Cortex, 2013, 23(3):739-749.
[7] BEN D, PITSKEL N B, PELPHREY K A. Three systems of insula functional connectivity identified with cluster analysis[J]. Cerebral Cortex, 2011, 21(7):1498-1506.
[8] CAUDA F, COSTA T, TORTA D M, et al. Meta-analytic clustering of the insula cortex:characterizing the meta-analytic connectivity of the insula when involved in active tasks[J]. Neuroimage, 2012, 62(1):343-355.
[9] NORMI J S, FARRANT K, DAMARAJU E, et al. Dynamic functional network connectivity reveals unique and overlapping profiles of insula subdivisions[J]. Human Brain Mapping, 2016, 37(5):1770-1787.
[10] SHEN X, PAPADEMETRIS X, CONSTABLE R T. Graph-theory based parcellation of functional subunits in the brain from resting-state fMRI data[J]. Neuroimage, 2010, 50(3):1027-1035.
[11] JANSSEN R J, JYLÄNKI P, KESSELS R P C, et al. Probabilistic model-based functional parcellation reveals a robust, fine-grained subdivision of the striatum[J]. Neuroimage, 2015, 119(10):398-405.
[12] GOLLAND P, GOLLAND Y, MALACH R. Detection of spatial activation patterns as unsupervised segmentation of fMRI data[C]//International Confer ence on Medical Image Computing and Computer-as-sisted Intervention. MICCAI. Brisbane:Springer, 2006:110-118.
[13] 林琳, 王树勋. 基于自适应小生境混合遗传算法的说话人识别[J]. 电子学报, 2007, 35(1):8-12. LIN Lin, WANG Shu-xun. Speaker recognition based on adaptive niche hybrid genetic algorithms[J]. Chinese Journal of Electronics, 2007, 35(1):8-12.
[14] BEHESHTI Z, SHAMSUDDIN S M. A review of population-based metaheuristic algorithm[J]. International Journal of Advances in Soft Computing and Its Applications, 2013, 5(1):1-35.
[15] HAKTANIRTAR ULUTAS B, KULTUREL-KONAK S. A review of clonal selection algorithm and its applications[J]. Artificial Intelligence Review, 2011, 36(2):117-138.
[16] KOTANODA K, MATSUDA Y, SUGISHITA M. A spatio-temporal regression model for the analysis of functional MRI data[J]. Neuroimage, 2002, 17(3):1415-1428.
[17] OIKONOMOU V P, BLEKAS K. An adaptive regression mixture model for fMRI cluster analysis[J]. IEEE Transactions on Medical Imaging, 2013, 32(4):649-659.
[18] ARI Ç, AKSOY S, ARIKAN O. Maximum likelihood estimation of Gaussian mixture models using stochastic search[J]. Pattern Recognition, 2012, 45(7):2804-2816.
[19] BURNET F M. The clonal selection theory of acquired immunity[M]. London:Cambridge University Press, 1959.
[20] DE CASTRO L N, VON ZUBEN F J. An immun-ological approach to initialize centers of radial basis function neural networks[C]//In Proceeding of Brazilian Conference on Neural Networks. CBRN, Rio de Janeiro:[s.n.], 2001:79-84.
[21] PENG Y, LU B L. Hybrid learning clonal selectionalgorithm[J]. Information Sciences, 2015, 296(1):128-146.
[22] MEJIA A F, NEBEL M B, SHOU H, et al. Improving reliability of subject-level resting-state fMRI parcellation with shrinkage estimators[J]. Neuroimage, 2015, 112(5):14-29.
[23] 朱峰, 罗立民, 宋余庆,等. 基于自适应空间邻域信息GMM的图像分割[J]. 计算机研究与发展, 2011,48(11):2000-2007. ZHU Feng, LUO Li-min, SONG Yu-qing, et al.Adaptive spatially neighborhood information gaussian mixture model image segmentation[J]. Journal of computer Research and Development, 2011, 48(11):2000-2007.
[24] ZHANG Y, CASPERS S, FAN L, et al. Robust brain parcellation using sparse representation on resting-state fMRI[J]. Brain Structure and Function, 2014,220(6):1-15.
[25] HE Y. The HE LAB[EB/OL]. http://www.yonghelab.org/downloads/data.
[26] YAN C G. Data processing assistant for resting-state fMRI[EB/OL]. http://rfmri.org/DPARSF.
[27] FAN Y, NICKERSON L, LI H, et al. Functional connectivity-based parcellation of the thalamus:an unsupervised clustering method and its validity investigation[J]. Brain Connectivity, 2015, 5(10):620-630.
[28] KAHNT T, CHANG L J, PARK S Q, et al. Connectivity-based parcellation of the human orbitofrontal cortex[J]. Journal of the Society for Neuroscience, 2012, 32(18):6240-6250.
[29] MEIL M. Comparing clusterings:an information based distance[J]. Journal of Multivariate Analysis, 2007, 98(5):873-895. |
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
| |
Shared |
|
|
|
|
| |
Discussed |
|
|
|
|
