计算机科学 ›› 2024, Vol. 51 ›› Issue (3): 141-146.doi: 10.11896/jsjkx.230600166
黄硕, 孙亮, 汪美玲, 张道强
HUANG Shuo, SUN Liang, WANG Meiling, ZHANG Daoqiang
摘要: 功能磁共振成像(functional Magnetic Resonance Imaging,fMRI)研究面临的主要挑战之一是不同被试者fMRI数据的异质性。一方面,多被试数据分析对于确定所生成结果跨被试的通用性和有效性至关重要。另一方面,分析多被试者fMRI数据需要在不同被试者的神经活动之间进行准确的解剖和功能校准,以提升最终结果的性能。然而,现有大多数功能校准研究都采用浅层模型来处理多被试者间的复杂关系,这严重束缚了多被试信息的建模能力。为此,提出了一种基于多视图自编码器的功能校准(Multi-view Auto-encoder Functional Alignment,MAFA)方法。具体地,该方法通过重构不同被试者的响应空间来学习节点嵌入,捕获不同被试者之间共享的特征表示,从而创建一个公共的响应空间。此外,通过引入自训练聚类目标,利用高置信度节点作为软标签来监督图聚类过程。在4个数据集上的实验结果表明,相比其他多被试者脑影像功能校准方法,所提方法在解码精度方面取得了最佳效果。
中图分类号:
[1]HAXBY V J,CONNOLLY C A,GUNTUPALLI J S.Decoding Neural Representational Spaces Using Multivariate Pattern Analysis[J].Annual Review of Neuroscience,2014,37:435-456. [2]ZHANG Y,YU Z,LIU J,et al.Neural Decoding of Visual Information Across Different Neural Recording Modalities and Approaches [J].Machine Intelligence Research,2022,19(5):350-365. [3]CAI M,SCHUCK W N,PILLOW W J,et al.A Bayesian Me-thod for Reducing Bias in Neural Representational Similarity Analysis [C]//Proceedings of the 30th International Conference on Neural Information Processing Systems.2016. [4]LORBERT A,RAMADGE J P.Kernel Hyperalignment [C]//Proceedings of the 25th International Conference on Neural Information Processing Systems-Volume 2.2012:1790-1798. [5]HAXBY V J,GUNTUPALLI J S,CONNOLLY C A,et al.A Common,High-dimensional Model of the Representational Space in Human Ventral Temporal Cortex [J].Neuron,2011,72(2):404-416. [6]KRIEGESKORTE N,GOEBEL R,BANDETTINI P.Information-based Functional Brain Mapping [J].Proceedings of the National Academy of Sciences of the United States of America,2006,103(10):3863-3868. [7]YOUSEFNEZHAD M,ZHANG D.Multi-Region Neural Representation:A Novel Model for Decoding Visual Stimuli in Human Brains [C]//Proceedings of the 2017 SIAM International Conference on Data Mining.Society for Industrial and Applied Mathematics.2017:54-62. [8]XU H,LORBERT A,RAMADGE J P,et al.Regularized Hyperalignment of Multi-set fMRI Data [C]//2012 IEEE Statistical Signal Processing Workshop(SSP).IEEE,2012:229-232. [9]CHEN P H,GUNTUPALLI J S,HAXBY V J,et al.Joint SVD-Hyperalignment for Multi-subject fMRI Data Alignment [C]//2014 IEEE International Workshop on Machine Learning for Signal Processing(MLSP).IEEE,2014:1-6. [10]GUNTUPALLI J S,HANKE M,HALCHENKO O Y,et al.A Model of Representational Spaces in Human Cortex [J].Cerebral Cortex,2016,26(6):2919-2934. [11]TALAIRACH J.Co-Planar Stereotaxic Atlas of the HumanBrain:3-Dimensional Proportional System:An Approach to Cere-bral Imaging[M].G.Thieme,1988. [12]ANDREW G,ARORA R,BILMES J,et al.Deep Canonical Correlation Analysis [C]//Proceedings of the International Confe-rence on Machine Learning.New York:ACM Press,2013. [13]BENTON A,KHAYRALLAH H,GUJRAL B,et al.Deep Ge-neralized Canonical Correlation Analysis [C]//Proceedings of the International Conference on Learning Representations.ICLR Press,2017. [14]YOUSEFNEZHAD M,ZHANG D.Deep Hyperalignment [C]//Advances in Neural Information Processing Systems.MIT Press,2017:1603-1611. [15]YOUSEFNEZHAD M,ZHANG D.Local Discriminant Hyperalignment for Multi-subject fMRI Data Alignment [C]//Proceedings of the AAAI Conference on Artificial Intelligence.2017:59-65. [16]YOUSEFNEZHAD M,SELVITELLA A,HAN L X,et al.Supervised Hyperalignment for Multi-subject fMRI Data Alignment [J].IEEE Transactions on Cognitive and Developmental Systems,2020,13(3):475-490. [17]CHEN P H,CHEN J,YESHURUN Y,et al.A Reduced Dimension fMRI Shared Response Model[C]//Proceedings of the Annual Conference on Neural Information Processing Systems.MIT Press,2015:460-468. [18]CHEN P H,ZHU X,ZHANG H,et al.A Convolutional Au-toencoder for Multi-Subject fMRI Data Aggregation [C]//29th Workshop of Representation Learning in Artificial and Biological Neural Networks.2016. [19]FAN S,WANG X,SHI C,et al.One2multi Graph Autoencoder for Multi-view Graph Clustering [C]//Proceedings of the Web Conference 2020.2020:3070-3076. [20]XIE J,GIRSHICK R,FARHADI A.Unsupervised Deep Embedding for Clustering Analysis [C]//International Conference on Machine Learning.PMLR,2016:478-487. [21]LAURENS V D M,HINTON G.Visualizing Data Using t-SNE [J].Journal of Machine Learning Research,2008,9(2605):2579-2605. [22]TOM S M,FOX C R,TREPEL C,et al.The neural basis of loss aversion in decision-making under risk[J].Science,2007,315(5811):515-518. [23]DUNCAN K J,PATTAMADILOK C,KNIERIM I,et al.Consistency and Variability in Functional Localisers [J].Neuro- Image,2009,46(4):1018-1026. [24]WAKEMAN D G,HENSON R N.A Multi-subject,Multi-modal Human Neuroimaging Dataset [J].Scientific Data,2015,2:150001. |
|