Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
144 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

DynDepNet: Learning Time-Varying Dependency Structures from fMRI Data via Dynamic Graph Structure Learning (2209.13513v3)

Published 27 Sep 2022 in cs.LG, stat.AP, and stat.ML

Abstract: Graph neural networks (GNNs) have demonstrated success in learning representations of brain graphs derived from functional magnetic resonance imaging (fMRI) data. However, existing GNN methods assume brain graphs are static over time and the graph adjacency matrix is known prior to model training. These assumptions contradict evidence that brain graphs are time-varying with a connectivity structure that depends on the choice of functional connectivity measure. Incorrectly representing fMRI data with noisy brain graphs can adversely affect GNN performance. To address this, we propose DynDepNet, a novel method for learning the optimal time-varying dependency structure of fMRI data induced by downstream prediction tasks. Experiments on real-world fMRI datasets, for the task of sex classification, demonstrate that DynDepNet achieves state-of-the-art results, outperforming the best baseline in terms of accuracy by approximately 8 and 6 percentage points, respectively. Furthermore, analysis of the learned dynamic graphs reveals prediction-related brain regions consistent with existing neuroscience literature.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (81)
  1. Deriving reproducible biomarkers from multi-site resting-state data: An autism-based example. NeuroImage, 147:736–745, 2017.
  2. Gender differences in cognitive theory of mind revealed by transcranial direct current stimulation on medial prefrontal cortex. Scientific reports, 7(1):1–9, 2017.
  3. Learning on graph with laplacian regularization. Advances in neural information processing systems, 19, 2006.
  4. A deep graph neural network architecture for modelling spatio-temporal dynamics in resting-state functional mri data. Medical Image Analysis, 79:102471, 2022.
  5. An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv preprint arXiv:1803.01271, 2018.
  6. Males and females differ in brain activation during cognitive tasks. Neuroimage, 30(2):529–538, 2006.
  7. Bonferroni, C. Teoria statistica delle classi e calcolo delle probabilita. Pubblicazioni del R Istituto Superiore di Scienze Economiche e Commericiali di Firenze, 8:3–62, 1936.
  8. Signature verification using a” siamese” time delay neural network. Advances in neural information processing systems, 6, 1993.
  9. The chronnectome: time-varying connectivity networks as the next frontier in fmri data discovery. Neuron, 84(2):262–274, 2014.
  10. Spectral temporal graph neural network for multivariate time-series forecasting. Advances in neural information processing systems, 33:17766–17778, 2020.
  11. Time–frequency dynamics of resting-state brain connectivity measured with fmri. Neuroimage, 50(1):81–98, 2010.
  12. On the properties of neural machine translation: Encoder-decoder approaches. arXiv preprint arXiv:1409.1259, 2014.
  13. Braingb: A benchmark for brain network analysis with graph neural networks. arXiv preprint arXiv:2204.07054, 2022.
  14. An optimal transportation approach for assessing almost stochastic order. In The Mathematics of the Uncertain, pp.  33–44. Springer, 2018.
  15. Likelihood ratio statistics for autoregressive time series with a unit root. Econometrica: journal of the Econometric Society, pp. 1057–1072, 1981.
  16. Donoho, D. L. De-noising by soft-thresholding. IEEE transactions on information theory, 41(3):613–627, 1995.
  17. Deep dominance - how to properly compare deep neural models. In Korhonen, A., Traum, D. R., and Màrquez, L. (eds.), Proceedings of the 57th Conference of the Association for Computational Linguistics, ACL 2019, Florence, Italy, July 28- August 2, 2019, Volume 1: Long Papers, pp.  2773–2785. Association for Computational Linguistics, 2019.
  18. The human brainnetome atlas: a new brain atlas based on connectional architecture. Cerebral cortex, 26(8):3508–3526, 2016.
  19. Functional connectome fingerprinting: identifying individuals using patterns of brain connectivity. Nature neuroscience, 18(11):1664–1671, 2015.
  20. Friston, K. J. Functional and effective connectivity in neuroimaging: a synthesis. Human brain mapping, 2(1-2):56–78, 1994.
  21. Spatio-temporal graph convolution for resting-state fmri analysis. In International Conference on Medical Image Computing and Computer-Assisted Intervention, pp.  528–538. Springer, 2020.
  22. The minimal preprocessing pipelines for the human connectome project. Neuroimage, 80:105–124, 2013.
  23. Framewise phoneme classification with bidirectional lstm and other neural network architectures. Neural networks, 18(5-6):602–610, 2005.
  24. Inductive representation learning on large graphs. Advances in neural information processing systems, 30, 2017.
  25. Array programming with NumPy. Nature, 585(7825):357–362, 2020. ISSN 1476-4687. URL https://doi.org/10.1038/s41586-020-2649-2.
  26. Deep neural networks and kernel regression achieve comparable accuracies for functional connectivity prediction of behavior and demographics. NeuroImage, 206:116276, 2020.
  27. A deep learning based approach identifies regions more relevant than resting-state networks to the prediction of general intelligence from resting-state fmri. Human Brain Mapping, 42(18):5873–5887, 2021.
  28. Long short-term memory. Neural computation, 9(8):1735–1780, 1997.
  29. Squeeze-and-excitation networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp.  7132–7141, 2018.
  30. Spatio-temporal directed acyclic graph learning with attention mechanisms on brain functional time series and connectivity. Medical Image Analysis, 77:102370, 2022.
  31. Functional magnetic resonance imaging, volume 1. Sinauer Associates Sunderland, 2004.
  32. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In International conference on machine learning, pp. 448–456. PMLR, 2015.
  33. The organization of thinking: What functional brain imaging reveals about the neuroarchitecture of complex cognition. Cognitive, Affective, & Behavioral Neuroscience, 7(3):153–191, 2007.
  34. Learning time varying graphs. In 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.  2826–2830. Ieee, 2017.
  35. Fbnetgen: Task-aware gnn-based fmri analysis via functional brain network generation. arXiv preprint arXiv:2205.12465, 2022.
  36. Brainnetcnn: Convolutional neural networks for brain networks; towards predicting neurodevelopment. NeuroImage, 146:1038–1049, 2017.
  37. Understanding graph isomorphism network for rs-fmri functional connectivity analysis. Frontiers in neuroscience, pp.  630, 2020.
  38. Learning dynamic graph representation of brain connectome with spatio-temporal attention. Advances in Neural Information Processing Systems, 34:4314–4327, 2021.
  39. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014.
  40. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907, 2016.
  41. Principles and open questions in functional brain network reconstruction. Human Brain Mapping, 42(11):3680–3711, 2021.
  42. Graph neural network for interpreting task-fmri biomarkers. In International Conference on Medical Image Computing and Computer-Assisted Intervention, pp.  485–493. Springer, 2019.
  43. Braingnn: Interpretable brain graph neural network for fmri analysis. Medical Image Analysis, 74:102233, 2021.
  44. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101, 2017.
  45. The effect of anticipation and the specificity of sex differences for amygdala and hippocampus function in emotional memory. Proceedings of the National Academy of Sciences, 103(38):14200–14205, 2006.
  46. A deep learning model for data-driven discovery of functional connectivity. Algorithms, 14(3):75, 2021.
  47. The default mode network in healthy individuals: a systematic review and meta-analysis. Brain connectivity, 7(1):25–33, 2017.
  48. Gender differences in dynamic functional connectivity based on resting-state fmri. In 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp.  2940–2943. IEEE, 2017.
  49. Specific and segregated changes to the functional connectome evoked by the processing of emotional faces: A task-based connectome study. Scientific Reports, 10(1):1–14, 2020.
  50. Birds of a feather: Homophily in social networks. Annual review of sociology, pp.  415–444, 2001.
  51. Rethinking measures of functional connectivity via feature extraction. Scientific reports, 10(1):1–17, 2020.
  52. Murphy, K. P. Machine learning: a probabilistic perspective, chapter 14.4.3, pp.  492–493. MIT press, 2012a.
  53. Murphy, K. P. Machine learning: a probabilistic perspective, chapter 14.5.2, pp.  498–504. MIT press, 2012b.
  54. Rectified linear units improve restricted boltzmann machines. In Proceedings of the 27th International Conference on International Conference on Machine Learning, pp.  807–814, 2010.
  55. TorchMetrics - Measuring Reproducibility in PyTorch, 2022. URL https://github.com/Lightning-AI/metrics.
  56. Wavenet: A generative model for raw audio. arXiv preprint arXiv:1609.03499, 2016.
  57. Pytorch: An imperative style, high-performance deep learning library. arXiv preprint arXiv:1912.01703, 2019.
  58. Scikit-learn: Machine learning in python. the Journal of machine Learning research, 12:2825–2830, 2011.
  59. Studying brain organization via spontaneous fmri signal. Neuron, 84(4):681–696, 2014.
  60. Python Core Team. Python: A dynamic, open source programming language. Python Software Foundation, 2019. URL https://www.python.org/. Python version 3.7.
  61. Why comparing single performance scores does not allow to draw conclusions about machine learning approaches. arXiv preprint arXiv:1803.09578, 2018.
  62. Deepfmri: End-to-end deep learning for functional connectivity and classification of adhd using fmri. Journal of neuroscience methods, 335:108506, 2020.
  63. Linked sex differences in cognition and functional connectivity in youth. Cerebral cortex, 25(9):2383–2394, 2015.
  64. Structured sequence modeling with graph convolutional recurrent networks. In International conference on neural information processing, pp.  362–373. Springer, 2018.
  65. Sporns, O. Graph theory methods: applications in brain networks. Dialogues in clinical neuroscience, 2022.
  66. Going deeper with convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp.  1–9, 2015.
  67. deep-significance-easy and meaningful statistical significance testing in the age of neural networks. arXiv preprint arXiv:2204.06815, 2022.
  68. The wu-minn human connectome project: an overview. Neuroimage, 80:62–79, 2013.
  69. Attention is all you need. Advances in neural information processing systems, 30, 2017.
  70. Graph attention networks. arXiv preprint arXiv:1710.10903, 2017.
  71. Graph-based network analysis of resting-state functional mri. Frontiers in systems neuroscience, pp.  16, 2010.
  72. Graph wavenet for deep spatial-temporal graph modeling. arXiv preprint arXiv:1906.00121, 2019.
  73. A comprehensive survey on graph neural networks. IEEE transactions on neural networks and learning systems, 32(1):4–24, 2020a.
  74. Connecting the dots: Multivariate time series forecasting with graph neural networks. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp.  753–763, 2020b.
  75. Spatial temporal graph convolutional networks for skeleton-based action recognition. In Thirty-second AAAI conference on artificial intelligence, 2018.
  76. The organization of the human cerebral cortex estimated by intrinsic functional connectivity. Journal of neurophysiology, 2011.
  77. Graph-revised convolutional network. In Joint European conference on machine learning and knowledge discovery in databases, pp.  378–393. Springer, 2020.
  78. Functional annotation of human cognitive states using deep graph convolution. NeuroImage, 231:117847, 2021.
  79. Heterogeneous graph structure learning for graph neural networks. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, pp.  4697–4705, 2021.
  80. A dynamic graph convolutional neural network framework reveals new insights into connectome dysfunctions in adhd. Neuroimage, 246:118774, 2022.
  81. A survey on graph structure learning: Progress and opportunities. arXiv e-prints, pp.  arXiv–2103, 2021.
Citations (2)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now