2022
DOI: 10.3390/brainsci12070883
|View full text |Cite
|
Sign up to set email alerts
|

Identification of Young High-Functioning Autism Individuals Based on Functional Connectome Using Graph Isomorphism Network: A Pilot Study

Abstract: Accumulated studies have determined the changes in functional connectivity in autism spectrum disorder (ASD) and spurred the application of machine learning for classifying ASD. Graph Neural Network provides a new method for network analysis in brain disorders to identify the underlying network features associated with functional deficits. Here, we proposed an improved model of Graph Isomorphism Network (GIN) that implements the Weisfeiler-Lehman (WL) graph isomorphism test to learn the graph features while ta… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1

Citation Types

0
3
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
4
1
1

Relationship

0
6

Authors

Journals

citations
Cited by 6 publications
(3 citation statements)
references
References 55 publications
0
3
0
Order By: Relevance
“…In the present study, we investigated the predictive value of brain morphology in TD for the continuous distribution of autistic traits. Brain imaging has often been applied in ASD to describe functioning and to identify potential risk markers (e.g., [ 41 , 42 ]). We found that autistic traits correspond to subtle autism-related alterations in brain morphology in typically developing individuals, as well as lying on a continuum in the general adolescent population, even at levels below a clinically revenant cut-off.…”
Section: Discussionmentioning
confidence: 99%
“…In the present study, we investigated the predictive value of brain morphology in TD for the continuous distribution of autistic traits. Brain imaging has often been applied in ASD to describe functioning and to identify potential risk markers (e.g., [ 41 , 42 ]). We found that autistic traits correspond to subtle autism-related alterations in brain morphology in typically developing individuals, as well as lying on a continuum in the general adolescent population, even at levels below a clinically revenant cut-off.…”
Section: Discussionmentioning
confidence: 99%
“…The fundamental algorithm underlying the graph isomorphism network (GIN) model draws inspiration from the Weisfeiler-Lehman [26] (WL) graph isomorphism testing algorithm, which is often referred to as the WL test. This algorithm assesses whether two graphs possess an isomorphic relationship.…”
Section: Basic Graph Isomorphism Network (Gin)mentioning
confidence: 99%
“…Patel et al [32] proposed a multimodal GIN that uses fMRI task data to classify adolescent gender at different stages. Yang et al [33], on the other hand, improved the GIN to learn the features of FCNs while taking into account the importance of each node in the classification and in the identification of brain diseases. Meng et al [34] developed IsoNN, a novel isomorphic neural network that matches the input graph to a template and extracts its isomorphic features for representation learning.…”
Section: B Graph Isomorphism Network For Brain Fcn Analysismentioning
confidence: 99%