Multi-resolution Graph Neural Network for Identifying Disease-specific Variations in Brain Connectivity

by   Xin Ma, et al.

Convolution Neural Network (CNN) recently have been adopted in several neuroimaging studies for diagnosis capturing disease-specific changes in the brain. While many of these methods are designed to work with images in R^n exploiting regular structure of the domain, they are not well-suited to analyze data with irregular structure such as brain connectivity. As there is significant interest in understanding the altered interactions between different brain regions that lead to neuro-disorders, it is important to develop data-driven methods that work with a population of graph data for traditional prediction tasks. In this regime, we propose a novel CNN-based framework with adaptive graph transforms to learn the most disease-relevant connectome feature maps which have the highest discrimination power across diagnostic categories. The backbone of our framework is a multi-resolution representation of the graph matrix which is steered by a set of wavelet-like graph transforms. In this context, our supervised graph learning framework outperforms conventional graph methods that predict diagnostic label only based on the underlying individual graph. Our extensive experiments on two real datasets of functional and structural brain networks show that our multi-resolution framework achieves significantly higher accuracy, precision and recall in predicting diagnostic labels and identifying disease-specific brain connectivities that are associated with brain disorders such as Attention-Deficit/Hyperactivity Disorder (ADHD) and Alzheimer's Disease (AD).


page 5

page 8


Attention-based 3D CNN with Multi-layer Features for Alzheimer's Disease Diagnosis using Brain Images

Structural MRI and PET imaging play an important role in the diagnosis o...

BrainIB: Interpretable Brain Network-based Psychiatric Diagnosis with Graph Information Bottleneck

Developing a new diagnostic models based on the underlying biological me...

Improving the Level of Autism Discrimination through GraphRNN Link Prediction

Dataset is the key of deep learning in Autism disease research. However,...

Multi-modal Dynamic Graph Network: Coupling Structural and Functional Connectome for Disease Diagnosis and Classification

Multi-modal neuroimaging technology has greatlly facilitated the efficie...

SubCMap: Subject and Condition Specific Effect Maps

Most widely used statistical analysis methods for neuroimaging data iden...

DeepProg: A Transformer-based Framework for Predicting Disease Prognosis

A vast majority of deep learning methods are built to automate diagnosti...

Exploring Heritability of Functional Brain Networks with Inexact Graph Matching

Data-driven brain parcellations aim to provide a more accurate represent...

Please sign up or login with your details

Forgot password? Click here to reset