Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
169 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

Predicting Infant Brain Connectivity with Federated Multi-Trajectory GNNs using Scarce Data (2401.01383v2)

Published 1 Jan 2024 in q-bio.NC, cs.AI, cs.CV, and cs.LG

Abstract: The understanding of the convoluted evolution of infant brain networks during the first postnatal year is pivotal for identifying the dynamics of early brain connectivity development. Existing deep learning solutions suffer from three major limitations. First, they cannot generalize to multi-trajectory prediction tasks, where each graph trajectory corresponds to a particular imaging modality or connectivity type (e.g., T1-w MRI). Second, existing models require extensive training datasets to achieve satisfactory performance which are often challenging to obtain. Third, they do not efficiently utilize incomplete time series data. To address these limitations, we introduce FedGmTE-Net++, a federated graph-based multi-trajectory evolution network. Using the power of federation, we aggregate local learnings among diverse hospitals with limited datasets. As a result, we enhance the performance of each hospital's local generative model, while preserving data privacy. The three key innovations of FedGmTE-Net++ are: (i) presenting the first federated learning framework specifically designed for brain multi-trajectory evolution prediction in a data-scarce environment, (ii) incorporating an auxiliary regularizer in the local objective function to exploit all the longitudinal brain connectivity within the evolution trajectory and maximize data utilization, (iii) introducing a two-step imputation process, comprising a preliminary KNN-based precompletion followed by an imputation refinement step that employs regressors to improve similarity scores and refine imputations. Our comprehensive experimental results showed the outperformance of FedGmTE-Net++ in brain multi-trajectory prediction from a single baseline graph in comparison with benchmark methods.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (54)
  1. Federated learning based on dynamic regularization. arXiv preprint arXiv:2111.04263 .
  2. A comparative study of machine learning methods for predicting the evolution of brain connectivity from a baseline timepoint. Journal of neuroscience methods 368, 109475.
  3. Suppressing poisoning attacks on federated learning for medical imaging, in: International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer. pp. 673–683.
  4. Voxel-based morphometry—the methods. Neuroimage 11, 805–821.
  5. Mr diffusion tensor spectroscopy and imaging. Biophysical journal 66, 259–267.
  6. Graph neural networks in network neuroscience. IEEE Transactions on Pattern Analysis and Machine Intelligence 45, 5833–5848.
  7. A few-shot learning graph multi-trajectory evolution network for forecasting multimodal baby connectivity development from a baseline timepoint, in: Predictive Intelligence in Medicine: 4th International Workshop, PRIME 2021, Held in Conjunction with MICCAI 2021, Strasbourg, France, October 1, 2021, Proceedings 4, Springer. pp. 11–24.
  8. Provably secure federated learning against malicious clients, in: Proceedings of the AAAI conference on artificial intelligence, pp. 6885–6893.
  9. Pearson correlation coefficient. Noise reduction in speech processing , 1–4.
  10. Predicting the evolution trajectory of population-driven connectional brain templates using recurrent multigraph neural networks. Medical Image Analysis 83, 102649.
  11. Learning-guided infinite network atlas selection for predicting longitudinal brain network evolution from a single observation, in: Medical Image Computing and Computer Assisted Intervention–MICCAI 2019: 22nd International Conference, Shenzhen, China, October 13–17, 2019, Proceedings, Part II 22, Springer. pp. 796–805.
  12. Protein interface prediction using graph convolutional networks. Advances in neural information processing systems 30.
  13. Deciphering interaction fingerprints from protein molecular surfaces using geometric deep learning. Nature Methods 17, 184–192.
  14. Multi-regression based supervised sample selection for predicting baby connectome evolution trajectory from neonatal timepoint. Medical Image Analysis 68, 101853.
  15. Residual embedding similarity-based network selection for predicting brain network evolution trajectory from a single observation, in: Predictive Intelligence in Medicine: Third International Workshop, PRIME 2020, Held in Conjunction with MICCAI 2020, Lima, Peru, October 8, 2020, Proceedings 3, Springer. pp. 12–23.
  16. Foreseeing brain graph evolution over time using deep adversarial network normalizer, in: Predictive Intelligence in Medicine: Third International Workshop, PRIME 2020, Held in Conjunction with MICCAI 2020, Lima, Peru, October 8, 2020, Proceedings 3, Springer. pp. 111–122.
  17. Federated brain graph evolution prediction using decentralized connectivity datasets with temporally-varying acquisitions. IEEE Transactions on Medical Imaging .
  18. Deep learning scaling is predictable, empirically. arXiv preprint arXiv:1712.00409 .
  19. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 .
  20. Longitudinal prediction of infant diffusion mri data via graph convolutional adversarial networks. IEEE transactions on medical imaging 38, 2717–2725.
  21. Graph recurrent networks with attributed random walks, in: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 732–740.
  22. Diffusion tensor imaging. Magnetic resonance neuroimaging: Methods and protocols , 127–144.
  23. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 .
  24. Distance between sets. Nature 234, 34–35.
  25. Simultaneous and consistent labeling of longitudinal dynamic developing cortical surfaces in infants. Medical image analysis 18, 1274–1289.
  26. Federated learning: Challenges, methods, and future directions. IEEE signal processing magazine 37, 50–60.
  27. Federated optimization in heterogeneous networks. Proceedings of Machine learning and systems 2, 429–450.
  28. Efficient graph generation with graph recurrent attention networks. Advances in neural information processing systems 32.
  29. A few thoughts on brain rois. Brain imaging and behavior 5, 189–202.
  30. Communication-efficient learning of deep networks from decentralized data, in: Artificial intelligence and statistics, PMLR. pp. 1273–1282.
  31. Recurrent neural networks. Design and Applications 5, 2.
  32. Multi-modal neuroimaging neural network-based feature detection for diagnosis of alzheimer’s disease. Frontiers in Aging Neuroscience 14, 911220.
  33. Deep evographnet architecture for time-dependent brain graph data synthesis from a single timepoint, in: Predictive Intelligence in Medicine: Third International Workshop, PRIME 2020, Held in Conjunction with MICCAI 2020, Lima, Peru, October 8, 2020, Proceedings, Springer. pp. 144–155.
  34. Analysis of weighted networks. Physical review E 70, 056131.
  35. Node centrality in weighted networks: Generalizing degree and shortest paths. Social networks 32, 245–251.
  36. Social network analysis: a powerful strategy, also for the information sciences. Journal of information Science 28, 441–453.
  37. Disease prediction using graph convolutional networks: application to autism spectrum disorder and alzheimer’s disease. Medical image analysis 48, 117–130.
  38. K-nearest neighbor. Scholarpedia 4, 1883.
  39. Federated multi-trajectory gnns under data limitations for baby brain connectivity forecasting, in: International Workshop on PRedictive Intelligence In MEdicine, Springer. pp. 120–133.
  40. Predicting infant cortical surface development using a 4d varifold-based learning framework and local topography-based shape morphing. Medical image analysis 28, 1–12.
  41. Joint prediction of longitudinal development of cortical surfaces and white matter fibers from neonatal mri. NeuroImage 152, 411–424.
  42. Hybrid approach of relation network and localized graph convolutional filtering for breast cancer subtype classification. arXiv preprint arXiv:1711.05859 .
  43. Federated multi-task learning. Advances in neural information processing systems 30.
  44. Neuroimaging in the early diagnosis of neurodegenerative disease. Translational neurodegeneration 1, 1–6.
  45. Recurrent brain graph mapper for predicting time-dependent brain graph evaluation trajectory, in: Domain Adaptation and Representation Transfer, and Affordable Healthcare and AI for Resource Diverse Global Health: Third MICCAI Workshop, DART 2021, and First MICCAI Workshop, FAIR 2021, Held in Conjunction with MICCAI 2021, Strasbourg, France, September 27 and October 1, 2021, Proceedings 3, Springer. pp. 180–190.
  46. Automated anatomical labeling of activations in spm using a macroscopic anatomical parcellation of the mni mri single-subject brain. Neuroimage 15, 273–289.
  47. Everything is connected: Graph neural networks. Current Opinion in Structural Biology 79, 102538.
  48. Graph attention networks. arXiv preprint arXiv:1710.10903 .
  49. Graphgan: Graph representation learning with generative adversarial nets, in: Proceedings of the AAAI conference on artificial intelligence.
  50. Graph convolutional networks with markov random field reasoning for social spammer detection, in: Proceedings of the AAAI conference on artificial intelligence, pp. 1054–1061.
  51. Molecular dynamics simulations of chemical reactions for use in education. Journal of chemical education 83, 77.
  52. Proportional fairness in federated learning. arXiv preprint arXiv:2202.01666 .
  53. Resting-state functional mri studies on infant brains: a decade of gap-filling efforts. Neuroimage 185, 664–684.
  54. Graph neural networks: A review of methods and applications. AI open 1, 57–81.

Summary

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

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