融合t-分布随机邻域嵌入与自动谱聚类的脑功能精细分区方法

doi:10.11938/cjmr20202876

摘要/Abstract

摘要：

本文针对目前脑功能分区不够准确的问题，基于静息态功能磁共振数据，提出了一种融合t-分布随机邻域嵌入（t-SNE）与自动谱聚类（ASC）的人脑功能精细分区的算法.首先，基于静息态功能磁共振图像，对需功能划分的脑区与全脑的时间序列作相关分析，得到需划分脑区的功能连接模式；然后，利用t-SNE算法提取高维功能连接模式特征；最后，通过基于本征间隙的ASC算法自动确定聚类数目，并对降维后的脑区特征分类，得到精细划分的脑亚区.模拟种子区域上的实验结果表明，相较谱聚类算法，以及结合主成分分析的谱聚类算法，本文方法对脑功能体素划分更优.进一步将本方法应用到真实人脑的功能分区中，成功地将海马旁回分为左右半球各3个亚区.本研究表明使用t-SNE与ASC融合的算法可提高脑功能分区准确性，是脑功能精细分区、进而构建脑功能图谱的一种有效方法.

关键词: 静息态功能磁共振成像, 功能连接, 功能分区, t-分布随机邻域嵌入, 自动谱聚类

Abstract:

In this paper, a new method for fine brain functional parcellation based on resting-state functional magnetic resonance imaging (rs-fMRI) data was proposed. The method combines the t-distribution stochastic neighbor embedding (t-SNE) and automatic spectral clustering (ASC) algorithms. First, correlation analyses are conducted between the time courses of the brain region to be parcellated and the whole brain. Second, t-SNE is used to extract the high-dimensional functional connectivity patterns. Last, the number of clusters is automatically determined by the ASC algorithm, and to divide the brain region of interest to generate the fine brain subregions. The results of simulated seed regions proved that the method proposed had higher accuracy than the commonly-used spectral clustering and spectral clustering with principal component analysis. Moreover, the method was successfully applied to parcellate the parahippocampal gyrus into 3 functional subregions in the left and right hemispheres. In conclusion, the algorithm combining t-SNE and ASC is an effective method for fine brain functional parcellation and construction of functional brain atlas.

Key words: resting-state fMRI, functional connectivity, functional parcellation, t-SNE, ASC

中图分类号:

TP394.1

胡颖,王丽嘉,聂生东. 融合t-分布随机邻域嵌入与自动谱聚类的脑功能精细分区方法[J]. 波谱学杂志, 2021, 38(3): 392-402.

Ying HU,Li-jia WANG,Sheng-dong NIE. Fine Brain Functional Parcellation Based on t-Distribution Stochastic Neighbor Embedding and Automatic Spectral Clustering[J]. Chinese Journal of Magnetic Resonance, 2021, 38(3): 392-402.

图/表 4

参考文献 36

1	MARKRAM H . The blue brain project[J]. Nat Rev Neurosci, 2006, 7 (2): 153- 160. doi: 10.1038/nrn1848
2	CAI W Q , WANG Y J . Advances in construction of human brain atlases from magnetic resonance images[J]. Chinese J Magn Reson, 2020, 37 (2): 241- 253.
	蔡文琴, 王远军. 基于磁共振成像的人脑图谱构建方法研究进展[J]. 波谱学杂志, 2020, 37 (2): 241- 253.
3	AMUNTS K , ZILLES K . Architectonic mapping of the human brain beyond brodmann[J]. Neuron, 2015, 88 (6): 1086- 1107. doi: 10.1016/j.neuron.2015.12.001
4	SPORNS O . Cerebral cartography and connectomics[J]. Phil Trans R Soc B, 2015, 370 (1668): 20140173. doi: 10.1098/rstb.2014.0173
5	FAN L Z , LI H , ZHUO J J , et al. The human brainnetome atlas: a new brain atlas based on connectional architecture[J]. Cereb Cortex, 2016, 26 (8): 3508- 3526. doi: 10.1093/cercor/bhw157
6	GLASSER M F , COALSON T S , ROBINSON E C , et al. A multi-modal parcellation of human cerebral cortex[J]. Nature, 2016, 536 (7615): 171- 178. doi: 10.1038/nature18933
7	BAUMGARTNER R , SCARTH G , TEICHTMEISTER C , et al. Fuzzy clustering of gradient-echo functional MRI in the human visual cortex. Part Ⅰ: reproducibility[J]. J Magn Reson Imaging, 2010, 7 (6): 1094- 1101.
8	JUNG W H , JANG J H , PARK J W , et al. Unravelling the intrinsic functional organization of the human striatum: a parcellation and connectivity study based on resting-state FMRI[J]. Plos One, 2014, 9 (9): e106768- 106781. doi: 10.1371/journal.pone.0106768
9	THOMAS B , SAAD J , GLASSER M F , et al. Spatially constrained hierarchical parcellation of the brain with resting-state fMRI[J]. Neuroimage, 2013, 76 (1): 313- 324.
10	MORENODOMINGUEZ D , ANWANDER A , KNöSCHE T R . A hierarchical method for whole-brain connectivity-based parcellation[J]. Hum Brain Mapp, 2014, 35 (10): 5000- 5025. doi: 10.1002/hbm.22528
11	LUO Z G , ZENG L L , QIN J , et al. Functional parcellation of human brain precuneus using density-based clustering[J]. Cereb Cortex, 2020, 30 (1): 269- 282. doi: 10.1093/cercor/bhz086
12	RANDY L B , KRIENEN F M , CASTELLANOS A , et al. The organization of the human cerebellum estimated by intrinsic functional connectivity[J]. J Neurophysiol, 2011, 5 (106): 2322- 2345.
13	HAQ N F , TAN S N , MCKEOWM M J , et al. Parcellation of functional sub-regions from fMRI: A graph clustering based approach[J]. Biomed Signal Process Control, 2019, 49, 181- 191. doi: 10.1016/j.bspc.2018.11.007
14	RYALI S , CHEN T , SUPEKAR K , et al. A parcellation scheme based on von Mises-Fisher distributions and Markov random fields for segmenting brain regions using resting-state fMRI[J]. Neuroimage, 2013, 65 (1): 83- 96.
15	DONG Y C , WANG B , MA S S , et al. Dimension reduction method research of brain network status observation matrix based on t-SNE[J]. Computer Engineering and Applications, 2018, 54 (1): 42- 47.
	董迎朝, 王彬, 马洒洒, 等. 基于t-SNE的脑网络状态观测矩阵降维方法研究[J]. 计算机工程与应用, 2018, 54 (1): 42- 47.
16	PARMAR H S, MITRA S, NUTTER B, et al. Visualization and detection of changes in brain states using t-SNE[C]//2020 IEEE Southwest Symposium on Image Analysis and Interpretation (SSIAI). IEEE, 2020. 14-17.
17	VAN ESSEN D C , SMITH S M , BARCH D M , et al. The WU-Minn Human Connectome Project: an overview[J]. Neuroimage, 2013, 80 (8): 62- 79.
18	YAN C G , ZANG Y F . DPARSF: a MATLAB toolbox for "pipeline" data analysis of resting-state fMRI[J]. Front Syst Neurosci, 2010, 4 (13): 13- 19.
19	WANG J H , WANG L , ZANG Y F , et al. Parcellation-dependent small-world brain functional networks: A resting-state fMRI study[J]. Hum Brain Mapp, 2009, 30 (5): 1511- 1523. doi: 10.1002/hbm.20623
20	HINTON G, ROWEIS S T. Stochastic neighbor embedding[C]NIPS. 2002, 15: 833-840.
21	MAATEN L V D , HINTON G . Viualizing data using t-SNE[J]. J Mach Learn Res, 2008, 9 (2605): 2579- 2605.
22	NG A Y, JORDAN M I, WEISS Y. On spectral clustering: Analysis and an algorithm[C]//Proceedings of the 14th International Conference on Neural Information Processing Systems: Natural and Synthetic, 2001.
23	KONG W Z , SUN Z H , YANG C , et al. Automatic spectral clustering based on eigengap and orthogonal eigenvector[J]. Acta Electronica Sinica, 2010, 38 (8): 1980- 1985.
24	MACKAY D J, C. Information, theory, inference, and learning algorithms[M]//IEEE Transactions on Information Theory. Cambridge University Press 2003, 50(10): 1461-1468.
25	WANG Z L , FENG Z Y , ZHANG P . An iterative hungarian algorithm based coordinated spectrum sensing strategy[J]. IEEE Commun Lett, 2011, 15 (1): 49- 51. doi: 10.1109/LCOMM.2010.111910.101806
26	ROMBOUTS S A , BARKHOF F , WITTER M P , et al. Anterior medial temporal lobe activation during attempted retrieval of encoded visuospatial scenes: an event-related fMRI study[J]. Neuroimage, 2001, 14 (1 Pt 1): 67- 76.
27	LIBBY L A , HANNULA D E , RANGANATH C . Medial temporal lobe coding of item and spatial information during relational binding in working memory[J]. J Neurosci, 2014, 34 (43): 14233- 14242. doi: 10.1523/JNEUROSCI.0655-14.2014
28	STARESINA B P , DUNCAN K D , DAVACHI L . Perirhinal and parahippocampal cortices differentially contribute to later recollection of object- and scene-related event details[J]. J Neurosci, 2011, 31 (24): 8739- 8747. doi: 10.1523/JNEUROSCI.4978-10.2011
29	GUO Y E , WANG P , ZHOU B , et al. Possibility of treating grey matter in hippocampus and parahippocampus as features of Alzheimer's disease[J]. Chinese Journal of Health Care and Medicine, 2016, 18 (3): 186- 188.
	郭艳娥, 王盼, 周波, 等. 海马及海马旁回灰质作为阿尔茨海默病特征的研究[J]. 中华保健医学杂志, 2016, 18 (3): 186- 188.
30	BLATT G J , PANDYA D N , ROSENE D L . Parcellation of cortical afferents to three distinct sectors in the parahippocampal gyrus of the rhesus monkey: an anatomical and neurophysiological study[J]. J Comp Neurol, 2003, 466 (2): 161- 173. doi: 10.1002/cne.10866
31	HU Y , WANG L J , NIE S D . Review on brain functional parcellation based on resting-state functional magnetic resonance imaging data[J]. Journal of Image and Graphics, 2017, (10): 1325- 1334.
	胡颖, 王丽嘉, 聂生东. 静息态功能磁共振成像的脑功能分区综述[J]. 中国图象图形学报, 2017, (10): 1325- 1334.
32	KAYE J A , GWYTHER L , MOHS R C , et al. Practice parameter: management of dementia (an evidence-based review)[J]. Neurology, 2001, 57 (12): 2323- 2323. doi: 10.1212/WNL.57.12.2323
33	SUN J W , YAN S J , HAN Y S , et al. Classifying the course of Alzheimer's disease with brain mr images and a method based on three dimensional local pattern transformation[J]. Chinese J Magn Reson, 2019, 36 (3): 268- 277.
	孙京文, 闫士举, 韩勇森, 等. 基于脑部磁共振图像三维局部模式变换特征提取进行阿尔茨海默病病程预测分类[J]. 波谱学杂志, 2019, 36 (3): 268- 277.
34	BAXTER L C , SPARKS D L , JOHNSON S C , et al. Relationship of cognitive measures and gray and white matter in Alzheimer's disease[J]. J Alzheimers Dis, 2006, 9 (3): 253- 260. doi: 10.3233/JAD-2006-9304
35	ECHáVARRI C , AALTEN P , UYLINGS H B , et al. Atrophy in the parahippocampal gyrus as an early biomarker of Alzheimer's disease[J]. Brain Struct Funct, 2011, 215 (3, 4): 265- 271.
36	JIA J Y , KUANG L Q , XIONG F G , et al. Analysis of dynamic evolution of complex brain network based on persistent homology[J]. Chinese J Magn Reson, 2021, 38 (1): 80- 91.
	贾嘉莹, 况立群, 熊风光, 等. 基于持久同调的复杂脑网络动态演化分析[J]. 波谱学杂志, 2021, 38 (1): 80- 91.

	t-SNE+ASC	谱聚类	PCA+谱聚类
NMI	0.88	0.59	0.60
Hungarian Algorithm	90.12	69.02	71.00

[1]	贾嘉莹, 况立群, 熊风光, 韩燮. 基于持久同调的复杂脑网络动态演化分析[J]. 波谱学杂志, 2021, 38(1): 80-91.
[2]	吴瑞琪1,3，李博1,3，刘悦2，徐富强1,2*. 光激活磁共振脑功能成像的研究现状及前景[J]. 波谱学杂志, 2014, 31(2): 295-305.
[3]	杨丽琴, 林富春, 雷皓. 静息状态下脑功能连接的磁共振成像研究[J]. 波谱学杂志, 2010, 27(3): 326-340.