Abstract：Brain atlas is an important tool in brain science research, including brain function exploration, neuroscience and cognitive science, and clinical diagnosis and treatment, which can be constructed using machine learning based on neuroimaging data. The parcellation patterns generated by brain atlas provide the foundation for understanding brain structure and function, and are frequently used for defining nodes in brain networks to reduce the impact of imaging noise on analysis results. Compared to structural atlases, functional atlases have a later development but demonstrate higher functional consistency, gradually gaining widespread attention and application in various brain function-related studies. In order to reveal the development path of functional atlases, based on the investigation of different types and methods of brain functional atlases constructed using neuroimaging data and machine learning, this article first classified and summarized the atlases according to multiple attribute features such as cortical surface and voxel, individual and population, and imaging modalities, providing detailed information for each atlas. After that, according to machine learning methods, we reviewed the construction methods of brain atlases based on graph clustering and time series clustering separately. Finally, we outlined the challenges faced in the field of brain atlas research and prospects for future research directions.
杨梦婷, 张道强, 温旭云. 基于神经影像和机器学习的大脑功能图谱构建方法综述[J]. 中国生物医学工程学报, 2024, 43(1): 80-97.
Yang Mengting, Zhang Daoqiang, Wen Xuyun. A Review of Methods for Constructing Brain Functional Atlas Based on Neuroimaging Data and Machine Learning. Chinese Journal of Biomedical Engineering, 2024, 43(1): 80-97.
[1] Kim JH, Lee JM, Jo HJ.Defining functional SMA and pre-SMA subregions in human MFC using resting state fMRI: functional connectivity-based parcellation method[J]. NeuroImage, 2010, 49(3): 2375-2386.
[2] Evans AC, Janke AL, Collins DL, et al.Brain templates and atlases[J]. NeuroImage, 2012, 62(2): 911-922.
[3] Bellec P, Benhajali Y, Carbonell F, et al.Impact of the resolution of brain parcels on connectome-wide association studies in fMRI[J]. NeuroImage, 2015, 123: 212-228.
[4] Thirion B, Varoquaux G, Dohmatob E, et al.Which fMRI clustering gives good brain parcellations?[J]. Frontiers in Neuroscience, 2014, 8(8): 167-180.
[5] Eickhoff SB, Yeo BT, Genon S.Imaging-based parcellations of the human brain[J]. Nature Reviews Neuroscience, 2018, 19(11): 672-686.
[6] Brodmann K.Vergleichende Lokalisationslehre der Grosshirnrinde in Ihren Prinzipien Dargestellt Auf Grund Des Zellenbaues[M]. Leipzig: Johann Ambrosius Barth, 1909.
[7] Klatzo I.Cecile and Oskar vogt: the visionaries of modern neuroscience[M]. Vienna: Springer Science & Business Media, 2002: 29-32.
[8] Amunts K, Zilles K.Architectonic mapping of the human brain beyond brodmann[J]. Neuron, 2015, 88(6):1086-1107.
[9] Fischl B, Rajendran N, Busa E, et al.Cortical folding patterns and predicting cytoarchitecture[J]. Cerebral Cortex, 2008, 18(8): 1973-1980.
[10] Tzourio-Mazoyer N, Landeau B, Papathanassiou D, et al.Automated anatomical labeling of activations in SPM using a macroscopic anatomical parcellation of the MNI MRI single-subject brain[J]. NeuroImage, 2002, 15(1): 273-289.
[11] Desikan RS, Ségonne F, Fischl B, et al.An automated labeling system for subdividing the human cerebral cortex on MRI scans into gyral based regions of interest[J]. NeuroImage, 2006, 31(3): 968-980.
[12] Yeo BT, Krienen FM, Sepulcre J, et al.The organization of the human cerebral cortex estimated by intrinsic functional connectivity[J]. Journal of Neurophysiology, 2011, 106(3): 1125-1165.
[13] Wang D, Buckner RL, Fox MD, et al.Parcellating cortical functional networks in individuals[J]. Nature Neuroscience, 2015, 18(12): 1853-1860.
[14] Luxburg UV.A tutorial on spectral clustering[J]. Statistics and Computing, 2007, 17(4): 395-416.
[15] Chang LJ, Yarkoni T, Khaw MW, et al.Decoding the role of the insula in human cognition: functional parcellation and large-scale reverse inference[J]. Cerebral Cortex, 2013, 23(3): 739-749.
[16] Finn ES, Shen X, Holahan JM, et al.Disruption of functional networks in dyslexia: a whole-brain data-driven analysis of connectivity[J]. Biological Psychiatry, 2014, 76(5): 397-404.
[17] Honnorat N, Eavani H, Satterthwaite TD, et al.GraSP: geodesic graph-based segmentation with shape priors for the functional parcellation of the cortex[J]. NeuroImage, 2015, 106: 207-221.
[18] Bullmore ET, Bassett DS.Brain graphs: graphical models of the human brain connectome[J]. Annual Review of Clinical Psychology, 2011, 7: 113-140.
[19] Mandal PK, Rashima M, Dinov ID, et al.Structural brain atlases: design, rationale and applications in normal and pathological cohorts[J]. Journal of Alzheimer's Disease, 2012, 31(S3): S169-S188.
[20] Arslan S, Ktena SI, Makropoulos A, et al.Human brain mapping: a systematic comparison of parcellation methods for the human cerebral cortex[J]. NeuroImage, 2018, 170: 5-30.
[21] Moghimi P, Dang AT, Netoff TI, et al. A review on MR based human brain parcellation methods [EB/OL]. https://arxiv.org/abs/2107.03475, 2021-07-07/2022-09-02.
[22] 王康程, 吴国榕, 侯鑫, 等. 从群体到个体脑功能网络的分割及应用[J]. 科学通报, 2016, 61(27): 3022-3035.
[23] Schaefer A, Kong R, Gordon EM, et al.Local-global parcellation of the human cerebral cortex from intrinsic functional connectivity MRI[J]. Cerebral Cortex, 2018, 28(9): 3095-3114.
[24] Craddock RC, James GA, Holtzheimer III PE, et al.A whole brain fMRI atlas generated via spatially constrained spectral clustering[J]. Human Brain Mapping, 2012, 33(8): 1914-1928.
[25] Shen X, Tokoglu F, Papademetris X, et al.Groupwise whole-brain parcellation from resting-state fMRI data for network node identification[J]. NeuroImage, 2013, 82: 403-415.
[26] Gordon EM, Laumann TO, Adeyemo B, et al.Generation and evaluation of a cortical area parcellation from resting-state correlations[J]. Cerebral Cortex, 2016, 26(1): 288-303.
[27] Yan X, Kong R, Xue A, et al.Homotopic local-global parcellation of the human cerebral cortex from resting-state functional connectivity[J]. NeuroImage, 2023, 273: 120010-120031.
[28] Holmes AJ, Hollinshead MO, O’keefe TM, et al.Brain Genomics Superstruct Project initial data release with structural, functional, and behavioral measures[J]. Scientific Data, 2015, 2(1): 1-16.
[29] Kong R, Li J, Orban C, et al.Spatial topography of individual-specific cortical networks predicts human cognition, personality, and emotion[J]. Cerebral Cortex, 2019, 29(6): 2533-2551.
[30] Zuo XN, Anderson JS, Bellec P, et al.An open science resource for establishing reliability and reproducibility in functional connectomics[J]. Scientific Data, 2014, 1(1): 1-13.
[31] Chen B, Xu T, Zhou C, et al.Individual variability and test-retest reliability revealed by ten repeated resting-state brain scans over one month[J]. PLoS ONE, 2015, 10(12): e0144963-e0144984.
[32] Van Essen DC, Ugurbil K, Auerbach E, et al.The Human Connectome Project: a data acquisition perspective[J]. NeuroImage, 2012, 62(4): 2222-2231.
[33] Smith SM, Beckmann CF, Andersson J, et al.Resting-state fMRI in the human connectome project[J]. NeuroImage, 2013, 80: 144-168.
[34] Gordon EM, Laumann TO, Gilmore AW, et al.Precision functional mapping of individual human brains[J]. Neuron, 2017, 95(4): 791-807.
[35] Kong R, Yang Q, Gordon E, et al.Individual-specific areal-level parcellations improve functional connectivity prediction of behavior[J]. Cerebral cortex, 2021, 31(10): 4477-4500.
[36] Urchs S, Armoza J, Moreau C, et al.MIST: a multi-resolution parcellation of functional brain networks[J]. MNI Open Research, 2019, 1: 3-22.
[37] Bellec P, Perlbarg V, Jbabdi S, et al.Identification of large-scale networks in the brain using fmri[J]. NeuroImage, 2006, 29(4): 1231-1243.
[38] Boukhdhir A, Zhang Y, Mignotte M, et al.Unraveling reproducible dynamic states of individual brain functional parcellation[J]. Network Neuroscience, 2021, 5(1): 28-55.
[39] Gordon EM, Laumann TO, Adeyemo B, et al.Individual variability of the system-level organization of the human brain[J]. Cerebral Cortex, 2017, 27(1): 386-399.
[40] Ren Y, Guo L, Guo CC.A connectivity-based parcellation improved functional representation of the human cerebellum[J]. Scientific Reports, 2019, 9(1): 1-12.
[41] Van Den Heuvel M, Mandl R, Hulshoff Pol H. Normalized cut group clustering of resting-state FMRI data[J]. PLoS ONE, 2008, 3(4): e2001-e2012.
[42] Buckner RL, Krienen FM, Castellanos A, et al.The organization of the human cerebellum estimated by intrinsic functional connectivity[J]. Journal of Neurophysiology, 2011, 106(5): 2322-2345.
[43] Bellec P, Rosa-Neto P, Lyttelton OC, et al.Multi-level bootstrap analysis of stable clusters in resting-state fmri[J]. NeuroImage, 2010, 51(3): 1126-1139.
[44] Joliot M, Jobard G, Naveau M, et al.AICHA: an atlas of intrinsic connectivity of homotopic areas[J]. Journal of Neuroscience Methods, 2015, 254: 46-59.
[45] Doucet GE, Labache L, Thompson PM, et al.Atlas55+: brain functional atlas of resting-state networks for late adulthood[J]. Cerebral Cortex, 2021, 31(3): 1719-1731.
[46] Power JD, Cohen AL, Nelson SM, et al.Functional network organization of the human brain[J]. Neuron, 2011, 72(4): 665-678.
[47] Fan L, Li H, Zhuo J, et al.The human brainnetome atlas: a new brain atlas based on connectional architecture[J]. Cerebral Cortex, 2016, 26(8): 3508-3526.
[48] Zhu J, Qiu A.Chinese adult brain atlas with functional and white matter parcellation[J]. Scientific Data, 2022, 9(1): 352-362.
[49] Dadi K, Varoquaux G, Machlouzarides-Shalit A, et al.Fine-grain atlases of functional modes for fMRI analysis[J]. NeuroImage, 2020, 221: 117126-117153.
[50] Dohmatob E, Richard H, Pinho AL, et al.Brain topography beyond parcellations: local gradients of functional maps[J]. NeuroImage, 2021, 229: 117706-117721.
[51] Dadi K, Abraham A, Rahim M, et al.Comparing functional connectivity based predictive models across datasets[C] //2016 International Workshop on Pattern Recognition in Neuroimaging (PRNI). Tranto: IEEE, 2016: 1-4.
[52] Calhoun VD, Sui J, Kiehl K, et al.Exploring the psychosis functional connectome: aberrant intrinsic networks in schizophrenia and bipolar disorder[J]. Frontiers in Psychiatry, 2012, 2: 75-88.
[53] Mueller SG, Weiner MW, Thal LJ, et al.The Alzheimer's disease neuroimaging initiative[J]. Neuroimaging Clinics, 2005, 15(4): 869-877.
[54] Milham MP, Craddock C. Addiction Connectome Preprocessed Initiative (ACPI) [EB/OL]. http://fcon_1000.projects.nitrc.org/indi/ACPI/html/index.html, 2016-05-24/2022-09-02.
[55] Pedregosa F, Varoquaux G, Gramfort A, et al.Scikit-learn: machine learning in Python[J]. Journal of Machine Learning Research, 2011, 12(85): 2825-2830.
[56] Dice LR.Measures of the amount of ecologic association between species[J]. Ecology, 1945, 26(3): 297-302.
[57] Cohen AL, Fair DA, Dosenbach NUF, et al.Defining functional areas in individual human brains using resting functional connectivity MRI[J]. NeuroImage, 2008, 41(1): 45-57.
[58] Cheng H, Zhu H, Zheng Q, et al.Functional parcellation of the hippocampus by semi-supervised clustering of resting state fMRI data[J]. Scientific Reports, 2020, 10(1): 1-16.
[59] Yu SX, Shi J.Multiclass spectral clustering[C] //ICCV'03: Proceedings of the Ninth IEEE International Conference on Computer Vision. Washington, DC: IEEE Computer Society, 2003: 313-319.
[60] Haxby JV, Guntupalli JS, Connolly AC, et al.A common, high-dimensional model of the representational space in human ventral temporal cortex[J]. Neuron, 2011, 72(2): 404-416.
[61] Johansen-Berg H, Behrens TEJ, Robson MD, et al.Changes in connectivity profiles define functionally distinct regions in human medial frontal cortex[J]. Proceedings of the National Academy of Sciences, 2004, 101(36): 13335-13340.
[62] Evans AC, Kamber M, Collins DL, et al.An MRI-based probabilistic atlas of neuroanatomy[M]// Magnetic Resonance Scanning and Epilepsy. Boston: Springer, 1994: 263-274.
[63] Liu H, Qin W, Li W, et al.Connectivity-based parcellation of the human frontal pole with diffusion tensor imaging[J]. Journal of Neuroscience, 2013, 33(16): 6782-6790.
[64] Luo Z, Zeng LL, Qin J, et al.Functional parcellation of human brain precuneus using density-based clustering[J]. Cerebral Cortex, 2020, 30(1): 269-282.
[65] Rodriguez A, Laio A.Clustering by fast search and find of density peaks[J]. Science, 2014, 344(6191): 1492-1496.
[66] Geman S, Geman D.Stochastic relaxation, Gibbs distributions, and the Bayesian restoration of images[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1984, 6(6): 721-741.
[67] Mardia KV.Statistics of directional data[J]. Journal of the Royal Statistical Society: Series B (Methodological), 1975, 37(3): 349-371.
[68] Lashkari D, Vul E, Kanwisher N, et al.Discovering structure in the space of fMRI selectivity profiles[J]. NeuroImage, 2010, 50(3): 1085-1098.
[69] Nowozin S, Lampert CH.Global interactions in random field models: a potential function ensuring connectedness[J]. SIAM Journal on Imaging Sciences, 2010, 3(4): 1048-1074.
[70] Honnorat N, Eavani H, Satterthwaite TD, et al.GraSP: geodesic graph-based segmentation with shape priors for the functional parcellation of the cortex[J]. NeuroImage, 2015, 106: 207-221.
[71] Honnorat N, Satterthwaite TD, Gur RE, et al.sGraSP: a graph-based method for the derivation of subject-specific functional parcellations of the brain[J]. Journal of Neuroscience Methods, 2017, 277: 1-20.
[72] Chong M, Bhushan C, Joshi AA, et al.Individual parcellation of resting fMRI with a group functional connectivity prior[J]. NeuroImage, 2017, 156: 87-100.
[73] Babajani-Feremi A, Soltanian-Zadeh H.Development of a variational scheme for model inversion of multi-area model of brain. Part I: Simulation evaluation[J]. Mathematical Biosciences, 2011, 229(1): 64-75.
[74] Mensch A, Varoquaux G, Thirion B.Compressed online dictionary learning for fast resting-state fMRI decomposition[C] //2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI). Prague:IEEE, 2016: 1282-1285.
[75] Dadi K, Rahim M, Abraham A, et al.Benchmarking functional connectome-based predictive models for resting-state fMRI[J]. NeuroImage, 2019, 192: 115-134.
[76] Olshausen BA, Field DJ.Sparse coding with an overcomplete basis set: a strategy employed by V1?[J]. Vision Research, 1997, 37(23): 3311-3325.
[77] Mensch A, Mairal J, Thirion B, et al.Stochastic subsampling for factorizing huge matrices[J]. IEEE Transactions on Signal Processing, 2017, 66(1): 113-128.
[78] Mensch A, Mairal J, Bzdok D, et al.Learning neural representations of human cognition across many fMRI studies[J]. Advances in Neural Information Processing Systems, 2017, 30: 5883-5893.
[79] Filippini N, MacIntosh BJ, Hough MG, et al. Distinct patterns of brain activity in young carriers of the APOE-ε4 allele[J]. Proceedings of the National Academy of Sciences, 2009, 106(17): 7209-7214.
[80] Baumgartner R, Windischberger C, Moser E.Quantification in functional magnetic resonance imaging: fuzzy clustering vs correlation analysis[J]. Magnetic Resonance Imaging, 1998, 16(2): 115-125.
[81] Bullmore E, Horwitz B, Honey G, et al.How good is good enough in path analysis of fMRI data?[J]. NeuroImage, 2000, 11(4): 289-301.
[82] Liu X, Xie H, Nutter B, et al.High-homogeneity functional parcellation of human brain for investigating robust functional connectivity[C] //2018 IEEE Southwest Symposium on Image Analysis and Interpretation (SSIAI). Las Vegas: IEEE, 2018: 1-4.
[83] Fu Z, Chan SC, Di X, et al.Adaptive covariance estimation of non-stationary processes and its application to infer dynamic connectivity from fMRI[J]. IEEE Transactions on Biomedical Circuits and Systems, 2014, 8(2): 228-239.
[84] Efron B, Tibshirani RJ.An Introduction to the Bootstrap [M]. Florida: CRC Press, 1994.
[85] Fischl B, Salat DH, Busa E, et al.Whole brain segmentation: automated labeling of neuroanatomical structures in the human brain[J]. Neuron, 2002, 33(3): 341-355.
[86] Vincent JL, Patel GH, Fox MD, et al.Intrinsic functional architecture in the anaesthetized monkey brain[J]. Nature, 2007, 447(7140): 83-86.
[87] Honey CJ, Sporns O, Cammoun L, et al.Predicting human resting-state functional connectivity from structural connectivity[J]. Proceedings of the National Academy of Sciences, 2009, 106(6): 2035-2040.
[88] Wig GS, Laumann TO, Petersen SE.An approach for parcellating human cortical areas using resting-state correlations[J]. NeuroImage, 2014, 93: 276-291.
[89] McKeown MJ, Sejnowski TJ. Independent component analysis of fMRI data: examining the assumptions[J]. Human Brain Mapping, 1998, 6(5-6): 368-372.
[90] Beckmann CF.Modelling with independent components[J]. NeuroImage, 2012, 62(2): 891-901.
[91] Yu Q, Du Y, Chen J, et al.Comparing brain graphs in which nodes are regions of interest or independent components: a simulation study[J]. Journal of Neuroscience Methods, 2017, 291: 61-68.
[92] Beucher S, Lantuejoul C.Use of watersheds in contour detection[C] //International Workshop on Image Processing: Real-Time Edge and Motion Detection/Estimation. Rennes: IEEE, 1979: 17-21.
[93] Ojemann JG, Akbudak E, Snyder AZ, et al.Anatomic localization and quantitative analysis of gradient refocused echo-planar fMRI susceptibility artifacts[J]. NeuroImage, 1997, 6(3): 156-167.
[94] Glasser MF, Sotiropoulos SN, Wilson JA, et al.The minimal preprocessing pipelines for the Human Connectome Project[J]. NeuroImage, 2013, 80: 105-124.
[95] Finn ES, Shen X, Holahan JM, et al.Disruption of functional networks in dyslexia: a whole-brain, data-driven analysis of connectivity[J]. Biological Psychiatry, 2014, 76: 397-404.
[96] Nebel MB, Joel SE, Muschelli J, et al.Disruption of functional organization within the primary motor cortex in children with autism[J]. Human Brain Mapping, 2014, 35(2): 567-580.
[97] Zilles K, Palomero-Gallagher N, Grefkes C, et al.Architectonics of the human cerebral cortex and transmitter receptor fingerprints: reconciling functional neuroanatomy and neurochemistry[J]. European Neuropsychopharmacology, 2002, 12(6): 587-599.
[98] Zalesky A, Fornito A, Harding IH, et al.Whole-brain anatomical networks: does the choice of nodes matter?[J]. NeuroImage, 2010, 50(3): 970-983.
[99] Biswal B, Zerrin Yetkin F, Haughton VM, et al.Functional connectivity in the motor cortex of resting human brain using echo-planar MRI[J]. Magnetic Resonance in Medicine, 1995, 34(4): 537-541.
[100] Zarei M, Beckmann CF, Binnewijzend MAA, et al.Functional segmentation of the hippocampus in the healthy human brain and in Alzheimer's disease[J]. NeuroImage, 2013, 66: 28-35.
[101] Badhwar AP, Tam A, Dansereau C, et al.Resting-state network dysfunction in Alzheimer's disease: a systematic review and meta-analysis[J]. Alzheimer's & Dementia: Diagnosis, Assessment & Disease Monitoring, 2017, 8: 73-85.
[102] Zamani Esfahlani F, Faskowitz J, Slack J, et al.Local structure-function relationships in human brain networks across the lifespan[J]. Nature Communications, 2022, 13(1): 2053-2069.
[103] Khosla M, Jamison K, Ngo GH, et al.Machine learning in resting-state fMRI analysis[J]. Magnetic Resonance Imaging, 2019, 64: 101-121.
[104] 梁夏, 王金辉, 贺永. 人脑连接组研究:脑结构网络和脑功能网络[J]. 科学通报, 2010, 55: 1565-1583.
[105] 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: 2035-2052.
[106] Glasser MF, Coalson TS, Robinson EC, et al.A multi-modal parcellation of human cerebral cortex[J]. Nature, 2016, 536(7615): 171-178.
[107] Albano L, Agosta F, Basaia S, et al.Functional connectivity in Parkinson's disease candidates for deep brain stimulation[J]. NPJ Parkinson's Disease, 2022, 8(1): 1-12.
[108] Bruin WB, Abe Y, Alonso P, et al.The functional connectome in obsessive-compulsive disorder: resting-state mega-analysis and machine learning classification for the ENIGMA-OCD consortium[J]. Molecular Psychiatry, 2 May, 2023 [Epub ahead of print].
[109] Talairach J.Co-planar Stereotaxic Atlas of the Human Brain[M]. New York: Thieme Medical Publishers, 1988: 1-122.
[110] Zhao J, Tang C, Nie J.Functional parcellation of individual cerebral cortex based on functional mri[J]. Neuroinformatics, 2020, 18(2): 295-306.
[111] Spisak T, Kincses B, Schlitt F, et al.Pain-free resting-state functional brain connectivity predicts individual pain sensitivity[J]. Nature Communications, 2020, 11(1): 187-199.
[112] Kohoutová L, Atlas LY, Büchel C, et al.Individual variability in brain representations of pain[J]. Nature Neuroscience, 2022, 25(6): 749-759.
[113] Orban P, Doyon J, Petrides M, et al.The richness of task-evoked hemodynamic responses defines a pseudohierarchy of functionally meaningful brain networks[J]. Cerebral Cortex, 2015, 25(9): 2658-2669.
[114] Meskaldji DE, Vasung L, Romascano D, et al.Improved statistical evaluation of group differences in connectomes by screening-filtering strategy with application to study maturation of brain connections between childhood and adolescence[J]. NeuroImage, 2015, 108: 251-264.
[115] Liu H, Stufflebeam SM, Sepulcre J, et al.Evidence from intrinsic activity that asymmetry of the human brain is controlled by multiple factors[J]. Proceedings of the National Academy of Sciences, 2009, 106(48): 20499-20503.
[116] Biswal BB, Mennes M, Zuo XN, et al.Toward discovery science of human brain function[J]. Proceedings of the National Academy of Sciences, 2010, 107(10): 4734-4739.
[117] Kelly C, Uddin LQ, Shehzad Z, et al.Broca's region: linking human brain functional connectivity data and non-human primate tracing anatomy studies[J]. European Journal of Neuroscience, 2010, 32(3): 383-398.
