logo

More info
  • ReceivedDec 19, 2017
  • AcceptedApr 18, 2018
  • PublishedMay 14, 2018

Abstract


Funded by

国家优秀青年科学基金(61422204)

国家自然科学基金项目(61473149)


References

[1] Huys Q J M, Maia T V, Frank M J. Computational psychiatry as a bridge from neuroscience to clinical applications. Nat Neurosci, 2016, 19: 404-413 CrossRef PubMed Google Scholar

[2] Dodt H U, Leischner U, Schierloh A. Ultramicroscopy: three-dimensional visualization of neuronal networks in the whole mouse brain. Nat Method, 2007, 4: 331-336 CrossRef PubMed Google Scholar

[3] Hama H, Kurokawa H, Kawano H. Scale: a chemical approach for fluorescence imaging and reconstruction of transparent mouse brain. Nat Neurosci, 2011, 14: 1481-1488 CrossRef PubMed Google Scholar

[4] Kamitani Y, Tong F. Decoding the visual and subjective contents of the human brain. Nat Neurosci, 2005, 8: 679-685 CrossRef PubMed Google Scholar

[5] de Vos F, Schouten T M, Hafkemeijer A. Combining multiple anatomical MRI measures improves Alzheimer's disease classification. Hum Brain Mapp, 2016, 37: 1920-1929 CrossRef PubMed Google Scholar

[6] Zhang D Q, Shen D G. Multi-modal multi-task learning for joint prediction of multiple regression and classification variables in Alzheimer's disease. NeuroImage, 2012, 59: 895-907 CrossRef PubMed Google Scholar

[7] Rubin T N, Koyejo O, Gorgolewski K J. Decoding brain activity using a large-scale probabilistic functional-anatomical atlas of human cognition. PLoS Comput Biol, 2017, 13: e1005649 CrossRef PubMed Google Scholar

[8] Jie B, Zhang D Q, Cheng B. Manifold regularized multitask feature learning for multimodality disease classification. Hum Brain Mapp, 2015, 36: 489-507 CrossRef PubMed Google Scholar

[9] Kong Y Y, Deng Y, Dai Q H. Discriminative clustering and feature selection for brain MRI segmentation. IEEE Signal Process Lett, 2015, 22: 573-577 CrossRef ADS Google Scholar

[10] Kloppel S, Stonnington C M, Chu C. Automatic classification of MR scans in Alzheimer's disease. Brain, 2008, 131: 681-689 CrossRef PubMed Google Scholar

[11] Zhang D Q, Wang Y P, Zhou L P. Multimodal classification of Alzheimer's disease and mild cognitive impairment. NeuroImage, 2011, 55: 856-867 CrossRef PubMed Google Scholar

[12] Zu C, Jie B, Liu M X. Label-aligned multi-task feature learning for multimodal classification of Alzheimer's disease and mild cognitive impairment. Brain Imag Behav, 2016, 10: 1148-1159 CrossRef PubMed Google Scholar

[13] Cheng B, Liu M X, Suk H I. Multimodal manifold-regularized transfer learning for MCI conversion prediction. Brain Imag Behav, 2015, 9: 913-926 CrossRef PubMed Google Scholar

[14] Liu M X, Zhang D Q, Shen D G. View-centralized multi-atlas classification for Alzheimer's disease diagnosis. Hum Brain Mapp, 2015, 36: 1847-1865 CrossRef PubMed Google Scholar

[15] Liu M X, Zhang D Q, Shen D G. Relationship induced multi-template learning for diagnosis of Alzheimer's disease and mild cognitive impairment. IEEE Trans Med Imag, 2016, 35: 1463-1474 CrossRef PubMed Google Scholar

[16] Fan Y, Resnick S M, Wu X Y. Structural and functional biomarkers of prodromal Alzheimer's disease: a high-dimensional pattern classification study. NeuroImage, 2008, 41: 277-285 CrossRef PubMed Google Scholar

[17] Wang Y, Fan Y, Bhatt P. High-dimensional pattern regression using machine learning: from medical images to continuous clinical variables. NeuroImage, 2010, 50: 1519-1535 CrossRef PubMed Google Scholar

[18] Friston K. Learning and inference in the brain. Neural Networks, 2003, 16: 1325-1352 CrossRef PubMed Google Scholar

[19] He Y, Evans A C. Graph theoretical modeling of brain connectivity. Curr Opin Neurol, 2010, 23: 341-350 CrossRef PubMed Google Scholar

[20] Xie T, He Y. Mapping the Alzheimer's brain with connectomics. Front Psychiat, 2011, 2: 77-88 CrossRef PubMed Google Scholar

[21] Guo H, Cao X H, Liu Z F. Machine learning classifier using abnormal brain network topological metrics in major depressive disorder. NeuroReport, 2012, 23: 1006-1011 CrossRef PubMed Google Scholar

[22] Jie B, Wee C Y, Shen D G. Hyper-connectivity of functional networks for brain disease diagnosis. Med Image Anal, 2016, 32: 84-100 CrossRef PubMed Google Scholar

[23] Wee C Y, Yang S, Yap P T. Sparse temporally dynamic resting-state functional connectivity networks for early MCI identification. Brain Imag Behav, 2016, 10: 342-356 CrossRef PubMed Google Scholar

[24] Fei F, Jie B, Zhang D Q. Frequent and discriminative subnetwork mining for mild cognitive impairment classification. Brain Connectivity, 2014, 4: 347-360 CrossRef PubMed Google Scholar

[25] Liu M X, Du J Q, Jie B, et al. Ordinal patterns for connectivity networks in brain disease diagnosis. In: Proceedings of International Conference on Medical Image Computing and Computer-Assisted Intervention, Athens, 2016. Google Scholar

[26] Leroux E, Delcroix N, Dollfus S. Left fronto-temporal dysconnectivity within the language network in schizophrenia: an fMRI and DTI study. Psychiat Res NeuroImag, 2014, 223: 261-267 CrossRef PubMed Google Scholar

[27] Jie B, Zhang D Q, Wee C Y. Topological graph kernel on multiple thresholded functional connectivity networks for mild cognitive impairment classification. Hum Brain Mapp, 2014, 35: 2876-2897 CrossRef PubMed Google Scholar

[28] Jie B, Jiang X, Zu C, et al. The new graph kernels on connectivity networks for identification of MCI. In: Proceedings of International Workshop on Machine Learning and Interpretation in Neuroimaging, Montreal, 2014. Google Scholar

[29] Hariri A R. Imaging genomics. British Med Bull, 2003, 65: 259-270 CrossRef Google Scholar

[30] Glahn D C, Thompson P M, Blangero J. Neuroimaging endophenotypes: strategies for finding genes influencing brain structure and function. Hum Brain Mapp, 2007, 28: 488-501 CrossRef PubMed Google Scholar

[31] Esslinger C, Walter H, Kirsch P. Neural mechanisms of a genome-wide supported psychosis variant. Science, 2009, 324: 605 CrossRef PubMed ADS Google Scholar

[32] Shen L, Kim S, Risacher S L. Whole genome association study of brain-wide imaging phenotypes for identifying quantitative trait loci in MCI and AD: A study of the ADNI cohort. NeuroImage, 2010, 53: 1051-1063 CrossRef PubMed Google Scholar

[33] Yan J, Du L, Yao X, et al. Machine learning in brain imaging genomics. In: Machine Learning and Medical Imaging. Cambridge: Academic Press, 2016. 411--434. Google Scholar

[34] Liu J Y, Calhoun V D. A review of multivariate analyses in imaging genetics. Front Neuroinform, 2014, 8: 19-39 CrossRef PubMed Google Scholar

[35] Hao X K, Yu J Y, Zhang D Q. Identifying genetic associations with MRI-derived measures via tree-guided sparse learning. In: Proceedings of International Conference on Medical Image Computing and Computer-Assisted Intervention, Boston, 2014. 757--764. Google Scholar

[36] Hao X K, Yao X H, Yan J W. Identifying multimodal intermediate phenotypes between genetic risk factors and disease status in Alzheimer's disease. Neuroinform, 2016, 14: 439-452 CrossRef PubMed Google Scholar

[37] Hao X K, Li C X, Du L. Mining outcome-relevant brain imaging genetic associations via three-way sparse canonical correlation analysis in Alzheimer's disease. Sci Rep, 2017, 7: 44272 CrossRef PubMed ADS Google Scholar

[38] Hao X K, Li C X, Yan J W. Identification of associations between genotypes and longitudinal phenotypes via temporally-constrained group sparse canonical correlation analysis. Bioinformatics, 2017, 33: i341-i349 CrossRef PubMed Google Scholar

[39] Smith K. Brain decoding: reading minds. Nature, 2013, 502: 428-430 CrossRef PubMed ADS Google Scholar

[40] Mitchell T M, Shinkareva S V, Carlson A. Predicting human brain activity associated with the meanings of nouns. Science, 2008, 320: 1191-1195 CrossRef PubMed ADS Google Scholar

[41] Haxby J V. Distributed and overlapping representations of faces and objects in ventral temporal cortex. Science, 2001, 293: 2425-2430 CrossRef PubMed ADS Google Scholar

[42] Chen P H, Chen J, Yeshurun Y, et al. A reduced-dimension fMRI shared response model. In: Proceedings of International Conference on Advances in Neural Information Processing Systems, Montreal, 2015. 460--468. Google Scholar

[43] Yousefnezhad M, Zhang D Q. Local discriminant hyperalignment for multi-subject fMRI data alignment. In: Proceedings of International Conference on American Association for Artificial Intelligence, San Francisco, 2017. 59--65. Google Scholar

[44] Yousefnezhad M, Zhang D Q. Deep hyperalignment. In: Proceedings of the 25th Annual Conference on Neural Information Processing Systems, Granada, 2017. Google Scholar

[45] Richiardi J, Eryilmaz H, Schwartz S. Decoding brain states from fMRI connectivity graphs. NeuroImage, 2011, 56: 616-626 CrossRef PubMed Google Scholar

[46] Olivetti E, Veeramachaneni S, Nowakowska E. Bayesian hypothesis testing for pattern discrimination in brain decoding. Pattern Recogn, 2012, 45: 2075-2084 CrossRef Google Scholar

[47] Yousefnezhad M, Zhang D Q. Anatomical pattern analysis for decoding visual stimuli in human brains. Cogn Comput, 2018, 10: 284-295 CrossRef Google Scholar

  • Figure 1

    (Color online) The framework for multi-kernel multi-modality based data fusion

  • Figure 2

    (Color online) The framework of view-centralized multi-Atlas classification method

  • Figure 3

    (Color online) The general framework for brain network analysis

  • Figure 4

    (Color online) The illustration of hyper-graph. (a) A conventional graph in which two nodes are connected together by an edge; (b) a hyper-graph in which each hyper-edge can connect more than two nodes. We denote $v$ as a set of nodes, $e$ as a set of edges; (c) the incidence matrix for the hyper-graph

  • Figure 5

    (Color online) The illustration of ordinal pattern. (a) A weight network; (b) ordinal patterns that contain two and three edges, respectively

  • Figure 6

    (Color online) The general framework for brain imaging genetics association analysis. The dimensionality of genotype (i.e., SNP) and phenotype (i.e., neuroimage) equal to $p$ and $q$, respectively. The goal of association analysis is to detect the SNP loci that can predict the phenotype of brain regions

  • Figure 7

    (Color online) Deep hyper-alignment. Construct the mapping from the original space to the common space by applying deep neural network, and use the rank-$m$ SVD and SGD algorithms to optimize the parameters in the deep neural network