2020
DOI: 10.3390/s20216001
|View full text |Cite
|
Sign up to set email alerts
|

Population Graph-Based Multi-Model Ensemble Method for Diagnosing Autism Spectrum Disorder

Abstract: With the advancement of brain imaging techniques and a variety of machine learning methods, significant progress has been made in brain disorder diagnosis, in particular Autism Spectrum Disorder. The development of machine learning models that can differentiate between healthy subjects and patients is of great importance. Recently, graph neural networks have found increasing application in domains where the population’s structure is modeled as a graph. The application of graphs for analyzing brain imaging data… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
42
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
6
2
1

Relationship

1
8

Authors

Journals

citations
Cited by 36 publications
(42 citation statements)
references
References 41 publications
0
42
0
Order By: Relevance
“…These solutions, however, are problem specific, and choosing a particular graph definition over the other has remained a challenging problem. Rakhimberdina et al [ 64 ] proposed a population graph-based multi-model ensemble method to deal with this problem. Their results on the ABIDE dataset [ 63 ] showed a 2.91% improvement in comparison to the best result reported for a non-graph solution [ 79 ].…”
Section: Case Studies Of Gnn For Medical Diagnosis and Analysismentioning
confidence: 99%
See 1 more Smart Citation
“…These solutions, however, are problem specific, and choosing a particular graph definition over the other has remained a challenging problem. Rakhimberdina et al [ 64 ] proposed a population graph-based multi-model ensemble method to deal with this problem. Their results on the ABIDE dataset [ 63 ] showed a 2.91% improvement in comparison to the best result reported for a non-graph solution [ 79 ].…”
Section: Case Studies Of Gnn For Medical Diagnosis and Analysismentioning
confidence: 99%
“…Models that infer graph topology from data would be particularly useful when representing diverse types of medical signals with several possible nodes and edges. For ASD analysis, Rakhimberdina et al [ 64 ] used a method to analyse different sets of configurations to build a set of graphs and selected the best performing graph. Jang et al [ 81 ] proposed a model that can automatically extract a multi-layer graph structure and feature representation directly from raw EEG data for affective mental states analysis.…”
Section: Research Challenges and Future Directionsmentioning
confidence: 99%
“…Among the various brain imaging techniques, fMRI is noninvasive and has a high spatial resolution. These characteristics allow fMRI to be used in a wide range of problems, including neurological disorder diagnosis (Rakhimberdina et al, 2020;Zhang et al, 2020) and human visual decoding (Haxby et al, 2001;Kamitani and Tong, 2005;Horikawa and Kamitani, 2017). The recent progress in human visual decoding has shown that beyond merely encoding the information about visual stimuli (Poldrack and Farah, 2015), brain activity captured by fMRI can be used to reconstruct visual stimuli information (Kay et al, 2008;Roelfsema et al, 2018).…”
Section: Visual Decoding Using Fmrimentioning
confidence: 99%
“…Models that infer graph structure from data would be especially useful with a variety of complex micro and macro environments. For example, several works in brain connectivity analysis [133] have demonstrated that learning the graph structure improves classification performance in comparison to approaches where a defined graph topology is used. However, several requirements are still needed to improve the generation process.…”
Section: B Graph Representation and Embedding Knowledgementioning
confidence: 99%