Papers
Topics
Authors
Recent
2000 character limit reached

Learning High-Order Relationships of Brain Regions (2312.02203v3)

Published 2 Dec 2023 in q-bio.NC and cs.LG

Abstract: Discovering reliable and informative relationships among brain regions from functional magnetic resonance imaging (fMRI) signals is essential in phenotypic predictions. Most of the current methods fail to accurately characterize those interactions because they only focus on pairwise connections and overlook the high-order relationships of brain regions. We propose that these high-order relationships should be maximally informative and minimally redundant (MIMR). However, identifying such high-order relationships is challenging and under-explored due to the exponential search space and the absence of a tractable objective. In response to this gap, we propose a novel method named HYBRID which aims to extract MIMR high-order relationships from fMRI data. HYBRID employs a CONSTRUCTOR to identify hyperedge structures, and a WEIGHTER to compute a weight for each hyperedge, which avoids searching in exponential space. HYBRID achieves the MIMR objective through an innovative information bottleneck framework named multi-head drop-bottleneck with theoretical guarantees. Our comprehensive experiments demonstrate the effectiveness of our model. Our model outperforms the state-of-the-art predictive model by an average of 11.2%, regarding the quality of hyperedges measured by CPM, a standard protocol for studying brain connections.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (74)
  1. Graph-based deep learning for medical diagnosis and analysis: past, present and future. Sensors, 21(14):4758, 2021.
  2. Deep variational information bottleneck. arXiv preprint arXiv:1612.00410, 2016.
  3. Neurobiological bases of executive function and social-emotional development: Typical and atypical brain changes. Family Relations, 65(1):108–119, 2016.
  4. Estimating or propagating gradients through stochastic neurons for conditional computation. arXiv preprint arXiv:1308.3432, 2013.
  5. Connectome-based predictive modelling of cognitive reserve using task-based functional connectivity. European Journal of Neuroscience, 57(3):490–510, 2023.
  6. Brain functional and effective connectivity based on electroencephalography recordings: A review. Human brain mapping, 43(2):860–879, 2022.
  7. The adolescent brain cognitive development (ABCD) study: Imaging acquisition across 21 sites. Developmental cognitive neuroscience, 32:43–54, 2018.
  8. Tempme: Towards the explainability of temporal graph neural networks via motif discovery. arXiv preprint arXiv:2310.19324, 2023.
  9. Braingb: A benchmark for brain network analysis with graph neural networks. IEEE transactions on medical imaging, 42(2):493–506, 2022a.
  10. Interpretable graph neural networks for connectome-based brain disorder analysis. In International Conference on Medical Image Computing and Computer-Assisted Intervention, pp.  375–385. Springer, 2022b.
  11. Benchmarking functional connectome-based predictive models for resting-state fMRI. NeuroImage, 192:115–134, 2019. ISSN 1053-8119. doi: https://doi.org/10.1016/j.neuroimage.2019.02.062. URL https://www.sciencedirect.com/science/article/pii/S1053811919301594.
  12. Resting-state functional brain connectivity best predicts the personality dimension of openness to experience. Personality neuroscience, 1:e6, 2018a.
  13. A distributed brain network predicts general intelligence from resting-state human neuroimaging data. Philosophical Transactions of the Royal Society B: Biological Sciences, 373(1756):20170284, 2018b.
  14. Functional connectome fingerprinting: Identifying individuals using patterns of brain connectivity. Nature neuroscience, 18(11):1664–1671, 2015.
  15. Combining multiple connectomes improves predictive modeling of phenotypic measures. Neuroimage, 201:116038, 2019.
  16. Infobot: Transfer and exploration via the information bottleneck. arXiv preprint arXiv:1901.10902, 2019.
  17. Task-induced brain state manipulation improves prediction of individual traits. Nature communications, 9(1):2807, 2018.
  18. The individual functional connectome is unique and stable over months to years. Neuroimage, 189:676–687, 2019.
  19. Learning hypergraph-regularized attribute predictors, 2015.
  20. Video object segmentation by hypergraph cut. In 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp.  1738–1745, 2009. doi: 10.1109/CVPR.2009.5206795.
  21. Generalization in reinforcement learning with selective noise injection and information bottleneck. Advances in neural information processing systems, 32, 2019.
  22. Robust l2subscript𝑙2l_{2}italic_l start_POSTSUBSCRIPT 2 end_POSTSUBSCRIPT-hypergraph and its applications. Information Sciences, 501:708–723, 2019.
  23. Unified framework for development, deployment and robust testing of neuroimaging algorithms. Neuroinformatics, 9:69–84, 2011.
  24. High performance hypergraph analytics of domain name system relationships. In HICSS 2019 symposium on cybersecurity big data analytics, 2019.
  25. Fbnetgen: Task-aware GNN-based fMRI analysis via functional brain network generation. In International Conference on Medical Imaging with Deep Learning, pp.  618–637. PMLR, 2022a.
  26. Brain network transformer. Advances in Neural Information Processing Systems, 35:25586–25599, 2022b.
  27. Drop-Bottleneck: Learning discrete compressed representation for noise-robust exploration. arXiv preprint arXiv:2103.12300, 2021.
  28. Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114, 2013.
  29. Complex cognition: the science of human reasoning, problem-solving, and decision-making, 2010.
  30. Metric learning with spectral graph convolutions on brain connectivity networks. NeuroImage, 169:431–442, 2018.
  31. Impaired neural networks for approximate calculation in dyscalculic children: a functional MRI study. Behavioral and Brain Functions, 2(1):1–17, 2006.
  32. Development of neural networks for exact and approximate calculation: A fMRI study. Developmental neuropsychology, 33(4):447–473, 2008.
  33. Toward systems neuroscience in mild cognitive impairment and Alzheimer’s disease: A meta-analysis of 75 fMRI studies. Human brain mapping, 36(3):1217–1232, 2015a.
  34. Putting age-related task activation into large-scale brain networks: a meta-analysis of 114 fMRI studies on healthy aging. Neuroscience & Biobehavioral Reviews, 57:156–174, 2015b.
  35. Graph neural network for interpreting task-fMRI biomarkers. In Medical Image Computing and Computer Assisted Intervention–MICCAI 2019: 22nd International Conference, Shenzhen, China, October 13–17, 2019, Proceedings, Part V 22, pp.  485–493. Springer, 2019.
  36. Braingnn: Interpretable brain graph neural network for fMRI analysis. Medical Image Analysis, 74:102233, 2021.
  37. Construction and multiple feature classification based on a high-order functional hypernetwork on fMRI data. Frontiers in Neuroscience, 16:848363, 2022.
  38. Elastic net hypergraph learning for image clustering and semi-supervised classification. IEEE Transactions on Image Processing, 26(1):452–463, 2017. doi: 10.1109/TIP.2016.2621671.
  39. The neural and genetic basis of executive function: attention, cognitive flexibility, and response inhibition. Pharmacology Biochemistry and Behavior, 123:45–54, 2014.
  40. Significance-aware information bottleneck for domain adaptive semantic segmentation. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pp.  6778–6787, 2019.
  41. A deep learning model for data-driven discovery of functional connectivity. Algorithms, 14(3):75, 2021.
  42. Interpretable and generalizable graph learning via stochastic attention mechanism. In International Conference on Machine Learning, pp.  15524–15543. PMLR, 2022a.
  43. Interpretable geometric deep learning via learnable randomness injection. arXiv preprint arXiv:2210.16966, 2022b.
  44. Neural discrete representation learning. arXiv preprint arXiv:1711.00937, 2017.
  45. Variational discriminator bottleneck: Improving imitation learning, inverse RL, and GANs by constraining information flow. arXiv preprint arXiv:1810.00821, 2018.
  46. Cultural influences on neural basis of inhibitory control. NeuroImage, 139:114–126, 2016.
  47. Context-specific activations are a hallmark of the neural basis of individual differences in general executive function. NeuroImage, 249:118845, 2022.
  48. A deep learning framework for neuroscience. Nature neuroscience, 22(11):1761–1770, 2019.
  49. Automated anatomical labelling atlas 3. Neuroimage, 206:116189, 2020.
  50. Quantifying high-order interdependencies via multivariate extensions of the mutual information. Physical Review E, 100(3):032305, 2019.
  51. Predicting moment-to-moment attentional state. Neuroimage, 114:249–256, 2015.
  52. A neuromarker of sustained attention from whole-brain functional connectivity. Nature neuroscience, 19(1):165–171, 2016.
  53. Functional connectivity predicts changes in attention observed across minutes, days, and months. Proceedings of the National Academy of Sciences, 117(7):3797–3807, 2020.
  54. Neurograph: Benchmarks for graph machine learning in brain connectomics. arXiv preprint arXiv:2306.06202, 2023.
  55. Higher-order organization of multivariate time series. Nature Physics, 19(2):221–229, 2023.
  56. Linked sex differences in cognition and functional connectivity in youth. Cerebral cortex, 25(9):2383–2394, 2015.
  57. Cortical areas interact through a communication subspace. Neuron, 102(1):249–259, 2019.
  58. Using connectome-based predictive modeling to predict individual behavior from brain connectivity. nature protocols, 12(3):506–518, 2017.
  59. Self-supervised learning of brain dynamics from broad neuroimaging data. Advances in Neural Information Processing Systems, 35:21255–21269, 2022.
  60. The information bottleneck method. arXiv preprint physics/0004057, 2000.
  61. Multivariate information theory uncovers synergistic subsystems of the human cerebral cortex. Communications biology, 6(1):451, 2023.
  62. Visual classification by l1subscript𝑙1l_{1}italic_l start_POSTSUBSCRIPT 1 end_POSTSUBSCRIPT-hypergraph modeling. IEEE Transactions on Knowledge and Data Engineering, 27(9):2564–2574, 2015. doi: 10.1109/TKDE.2015.2415497.
  63. Learning efficient multi-agent communication: An information bottleneck approach. In International Conference on Machine Learning, pp.  9908–9918. PMLR, 2020.
  64. Inference-based statistical network analysis uncovers star-like brain functional architectures for internalizing psychopathology in children. arXiv preprint arXiv:2309.11349, 2023.
  65. An efficient and reliable statistical method for estimating functional connectivity in large scale brain networks using partial correlation. Frontiers in neuroscience, 10:123, 2016.
  66. Connectome-Based Predictive Modeling of Individual Anxiety. Cerebral Cortex, 31(6):3006–3020, 01 2021. ISSN 1047-3211. doi: 10.1093/cercor/bhaa407. URL https://doi.org/10.1093/cercor/bhaa407.
  67. Graph information bottleneck. Advances in Neural Information Processing Systems, 33:20437–20448, 2020.
  68. Multi-hypergraph learning-based brain functional connectivity analysis in fMRI data. IEEE transactions on medical imaging, 39(5):1746–1758, 2019.
  69. InfoGCL: Information-aware graph contrastive learning. Advances in Neural Information Processing Systems, 34:30414–30425, 2021.
  70. Graph information bottleneck for subgraph recognition. arXiv preprint arXiv:2010.05563, 2020.
  71. Improving subgraph recognition with variational graph information bottleneck. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp.  19396–19405, 2022.
  72. Dynamic hypergraph structure learning. In IJCAI, pp.  3162–3169, 2018.
  73. Deep hypergraph structure learning, 2022.
  74. Identifying high order brain connectome biomarkers via learning on hypergraph. In Machine Learning in Medical Imaging: 7th International Workshop, MLMI 2016, Held in Conjunction with MICCAI 2016, Athens, Greece, October 17, 2016, Proceedings 7, pp.  1–9. Springer, 2016.
Citations (1)
View on Semantic Scholar

Summary

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

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

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now
Lightbulb Streamline Icon: https://streamlinehq.com

Continue Learning

We haven't generated follow-up questions for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now
List To Do Tasks Checklist Streamline Icon: https://streamlinehq.com

Collections

Sign up for free to add this paper to one or more collections.

User Circle Single Streamline Icon: https://streamlinehq.com Sign Up
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets

This paper has been mentioned in 2 tweets and received 2 likes.

Upgrade to Pro to view all of the tweets about this paper:

Start a free 7-day Pro trial