Recurrent Multigraph Integrator Network for Predicting the Evolution of Population-Driven Brain Connectivity Templates

Learning how to estimate a connectional brain template (CBT) from a population of brain multigraphs, where each graph (e.g., functional) quantifies a particular relationship between pairs of brain regions of interest (ROIs), allows to pin down the unique connectivity patterns shared across individuals. Specifically, a CBT is viewed as an integral representation of a set of highly heterogeneous graphs and ideally meeting the centeredness (i.e., minimum distance to all graphs in the population) and discriminativeness (i.e., distinguishes the healthy from the disordered population) criteria. So far, existing works have been limited to only integrating and fusing a population of brain multigraphs acquired at a single timepoint. In this paper, we unprecedentedly tackle the question: “Given a baseline multigraph population, can we learn how to integrate and forecast its CBT representations at followup timepoints?” Addressing such question is of paramount in predicting common alternations across healthy and disordered populations. To fill this gap, we propose Recurrent Multigraph Integrator Network (ReMINet), the first graph recurrent neural network which infers the baseline CBT of an input population t1 and predicts its longitudinal evolution over time (ti > t1). Our ReMI-Net is composed of recurrent neural blocks with graph convolutional layers using a cross-node message passing to first learn hidden-states embeddings of each CBT node (i.e., brain region of interest) and then predict its evolution at the consecutive timepoint. Moreover, we design a novel time-dependent loss to regularize the CBT evolution trajectory over time and further introduce a cyclic recursion and learnable normalization layer to generate well-centered CBTs from time-dependent hidden-state embeddings. Finally, we derive the CBT adjacency matrix from the learned hidden state graph representation. ReMI-Net significantly outperformed benchmark methods in both centeredness and discriminative connectional biomarker discovery criteria in demented patients. Our ReMI-Net GitHub code is available at https://github.com/basiralab/ReMI-Net.

[1]  Mohamed Ali Mahjoub,et al.  Supervised Multi-topology Network Cross-diffusion for Population-driven Brain Network Atlas Estimation , 2020, MICCAI.

[2]  C. Jack,et al.  Alzheimer's Disease Neuroimaging Initiative , 2008 .

[3]  Yoshua Bengio,et al.  Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling , 2014, ArXiv.

[4]  Yong Yu,et al.  A Review of Recurrent Neural Networks: LSTM Cells and Network Architectures , 2019, Neural Computation.

[5]  Islem Rekik,et al.  Estimation of connectional brain templates using selective multi-view network normalization , 2020, Medical Image Anal..

[6]  O. Sporns,et al.  Network neuroscience , 2017, Nature Neuroscience.

[7]  O. Sporns,et al.  A cross-disorder connectome landscape of brain dysconnectivity , 2019, Nature Reviews Neuroscience.

[8]  Feng Shi,et al.  Study of brain morphology change in Alzheimer’s disease and amnestic mild cognitive impairment compared with normal controls , 2019, General Psychiatry.

[9]  Islem Rekik,et al.  Deep Graph Normalizer: A Geometric Deep Learning Approach for Estimating Connectional Brain Templates , 2020, MICCAI.

[10]  John A. King,et al.  Differentiation of mild cognitive impairment using an entorhinal cortex-based test of virtual reality navigation , 2019, Brain : a journal of neurology.

[11]  Steen Moeller,et al.  The Human Connectome Project: A data acquisition perspective , 2012, NeuroImage.

[12]  Fabrice Wendling,et al.  Brain network similarity: methods and applications , 2019, Network Neuroscience.

[13]  Islem Rekik,et al.  Graph Neural Networks in Network Neuroscience , 2021, ArXiv.

[14]  Matthew F. Glasser,et al.  The Human Connectome Project: Progress and Prospects , 2016, Cerebrum: the Dana Forum on Brain Science.

[15]  Si Zhang,et al.  Graph convolutional networks: a comprehensive review , 2019, Computational Social Networks.

[16]  Zhuowen Tu,et al.  Similarity network fusion for aggregating data types on a genomic scale , 2014, Nature Methods.

[17]  Razvan Pascanu,et al.  Interaction Networks for Learning about Objects, Relations and Physics , 2016, NIPS.

[18]  Zhiyuan Liu,et al.  Graph Neural Networks: A Review of Methods and Applications , 2018, AI Open.

[19]  Samuel S. Schoenholz,et al.  Neural Message Passing for Quantum Chemistry , 2017, ICML.

[20]  Manik Varma,et al.  More generality in efficient multiple kernel learning , 2009, ICML '09.

[21]  Feng Zhang,et al.  Entorhinal cortex: a good biomarker of mild cognitive impairment and mild Alzheimer’s disease , 2016, Reviews in the neurosciences.

[22]  M. Breakspear,et al.  The connectomics of brain disorders , 2015, Nature Reviews Neuroscience.