Disease prediction using graph convolutional networks: Application to Autism Spectrum Disorder and Alzheimer's disease

By Sarah Parisot, Sofia Ira Ktena, Enzo Ferrante, M. J. Lee, Ricardo Guerrero, Ben Glocker, Daniel Rueckert. Medical Image Anal., 2018

743 citations recorded by the source corpus.

HighlightsFirst application of graph convolutional networks for brain analysis in populations.Graph based population model that leverages imaging and non‐imaging data.Experiments on two large and challenging databases: ABIDE and ADNI.Extensive evaluation of all the main components of the method.State of the art performance on both databases. Graphical abstract Figure. No caption available. ABSTRACT Graphs are widely used as a natural framework that captures interactions between individual elements represented as nodes in a graph. In medical applications, specifically, nodes can represent individuals within a potentially large population (patients or healthy controls) accompanied by a set of features, while the graph edges incorporate associations between subjects in an intuitive manner. This representation allows to incorporate the wealth of imaging and non‐imaging information as well as individual subject features simultaneously in disease classification tasks. Previous graph‐based approaches for supervised or unsupervised learning in the context of disease prediction solely focus on pairwise similarities between subjects, disregarding individual characteristics and features, or rather rely on subject‐specific imaging feature vectors and fail to model interactions between them. In this paper, we present a thorough evaluation of a generic framework that leverages both imaging and non‐imaging information and can be used for brain analysis in large populations. This framework exploits Graph Convolutional Networks (GCNs) and involves representing populations as a sparse graph, where its nodes are associated with imaging‐based feature vectors, while phenotypic information is integrated as edge weights. The extensive evaluation explores the effect of each individual component of this framework on disease prediction performance and further compares it to different baselines. The framework performance is tested on two large datasets with diverse underlying data, ABIDE and ADNI, for the prediction of Autism Spectrum Disorder and conversion to Alzheimer's disease, respectively. Our analysis shows that our novel framework can improve over state‐of‐the‐art results on both databases, with 70.4% classification accuracy for ABIDE and 80.0% for ADNI.

Subfields: Artificial Intelligence, Cognitive Neuroscience, Psychiatry and Mental health

View Paper: https://www.semanticscholar.org/paper/6354dad3769ddf9d9537c8a36137788721072a58

How researchers see this paper

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

In Artificial Intelligence

In Cognitive Neuroscience

In Psychiatry and Mental health

Citations in the corpus

ASD-DiagNet: A Hybrid Learning Approach for Detection of Autism Spectrum Disorder Using fMRI Data (2019, methodology): “Parisot et al. [17] proposed a framework based on Graph Convolutional Networks that achieved 70 .”
SIGN: Scalable Inception Graph Neural Networks (2020, background): “…computer graphics Monti et al. (2016), particle physics Choma et al. (2018), chemistry Duvenaud et al. (2015); Gilmer et al. (2017), medicine Parisot et al. (2018), drug repositioning Zitnik et al. (2018), discovery of anti-cancer foods Veselkov et al. (2019), modeling of proteins Gainza et…”
Convolutional Neural Networks for Classification of Alzheimer's Disease: Overview and Reproducible Evaluation (2019, background): “CNNs can also be applied to non-Euclidean spaces, such as graphs of patients (Parisot et al., 2018) or the cortical surface (Mostapha et al.”
Temporal Graph Networks for Deep Learning on Dynamic Graphs (2020, background): “Graphs are ubiquitously used as models for systems of relations and interactions in many ﬁelds [5, 52, 42, 10, 16, 20, 49, 53], in particular, social sciences [68, 43] and biology [76, 62, 18].”
BrainGNN: Interpretable Brain Graph Neural Network for fMRI Analysis (2020, background): “In addition, different from much of the GNN literature ( Parisot et al., 2018; Kazi et al., 2019 ) where populational graphs based on fMRI are modeled by treating each subject as a node on the graph, we model each subject’s brain as one graph and each brain ROI as a node to learn ROI-based graph…”