BrainNetCNN: Convolutional neural networks for brain networks; towards predicting neurodevelopment

By Jeremy Kawahara, Colin J. Brown, Steven P. Miller, Brian G. Booth, Vann Chau, Ruth E. Grunau, Jill G. Zwicker, Ghassan Hamarneh. NeuroImage, 2017

797 citations recorded by the source corpus.

Abstract We propose BrainNetCNN, a convolutional neural network (CNN) framework to predict clinical neurodevelopmental outcomes from brain networks. In contrast to the spatially local convolutions done in traditional image‐based CNNs, our BrainNetCNN is composed of novel edge‐to‐edge, edge‐to‐node and node‐to‐graph convolutional filters that leverage the topological locality of structural brain networks. We apply the BrainNetCNN framework to predict cognitive and motor developmental outcome scores from structural brain networks of infants born preterm. Diffusion tensor images (DTI) of preterm infants, acquired between 27 and 46 weeks gestational age, were used to construct a dataset of structural brain connectivity networks. We first demonstrate the predictive capabilities of BrainNetCNN on synthetic phantom networks with simulated injury patterns and added noise. BrainNetCNN outperforms a fully connected neural‐network with the same number of model parameters on both phantoms with focal and diffuse injury patterns. We then apply our method to the task of joint prediction of Bayley‐III cognitive and motor scores, assessed at 18 months of age, adjusted for prematurity. We show that our BrainNetCNN framework outperforms a variety of other methods on the same data. Furthermore, BrainNetCNN is able to identify an infant's postmenstrual age to within about 2 weeks. Finally, we explore the high‐level features learned by BrainNetCNN by visualizing the importance of each connection in the brain with respect to predicting the outcome scores. These findings are then discussed in the context of the anatomy and function of the developing preterm infant brain. HighlightsFirst deep convolutional neural network architecture designed for connectomes.Novel convolutional layers for leveraging topological locality in brain networks.Prediction of neurodevelopmental outcomes in preterm infants.Visualization of brain connections learned to be important for prediction.

Subfields: Cognitive Neuroscience, Pediatrics, Perinatology and Child Health, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/ec6d5e9f959aa2c10dff89faf97f1240610464b6

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Neuroscience

In Pediatrics, Perinatology and Child Health

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Deep Learning for Spatio-Temporal Data Mining: A Survey (2019, neutral): “Application domains Related works Transportation [177], [187], [116], [31], [29], [6], [32], [127], [53], [112], [26], [105], [166], [82], [23], [66], [108], [126], [81], [139], [78], [128], [146], [148], [72], [98], [189], [22], [24], [99], [96], [16], [97], [85], [15], [164], [165], [95], [140], [”
Disease prediction using graph convolutional networks: Application to Autism Spectrum Disorder and Alzheimer's disease (2018, methodology): “Kawahara et al. (2017) used a customised version of CNNs n structural connectivity matrices to predict neurodevelopmental utcomes in preterm infants, which operates on the graph spatial omain and, therefore, captures only 1-hop neighbours in the reeptive field of each node.”
Multi-Site Diagnostic Classification of Schizophrenia Using Discriminant Deep Learning with Functional Connectivity MRI (2018, background): “…fcMRI classi ﬁ cation of schizophrenia patients vs. healthy controls with a small sample size ( n = 100) (Kim et al., 2016), illuminating the potential of deep learning in automatic diagnosis of clinical populations(Hazlett et al., 2017; Kawahara et al., 2017; Suk et al., 2013; Zhao et al., 2017).”
3D conditional generative adversarial networks for high-quality PET image estimation at low dose (2018, background): “Convolutional neural networks (CNN) have drawn a tremendous amount of attention in machine learning and medical image analysis areas [14-18].”
A survey on deep learning in medical image analysis (2017, methodology): “Three papers used an architecture leveraging the unique attributes of medical data: two use 3D convolutions (Hosseini-Asl et al., 2016; Payan and Montana, 2015) instead of 2D to classify patients as having Alzheimer; Kawahara et al. (2016b) applied a CNN-like architecture to a brain connectivity gra”
A Comprehensive Survey on Graph Neural Networks (2019, background): “…GNNs to a variety of problems such as program veriﬁcation [17], program reasoning [166], social inﬂuence prediction [167], adversarial attacks prevention [168], electrical health records modeling [169], [170], brain networks [171], event detection [172], and combinatorial optimization [173].”
BrainGNN: Interpretable Brain Graph Neural Network for fMRI Analysis (2020, methodology): “Second, we compared our method with 360 the state-of-the-art deep learning (DL) methods, including BrainNetCNN [24], 361 and other GNN methods: 1) replace Ra-GNN layer with the graph convolutional 362 layers in Li et al.”