Exploring Implicit Biological Heterogeneity in ASD Diagnosis Using a Multi-Head Attention Graph Neural Network
Journal of Integrative Neuroscience · 2024
DOI: 10.31083/j.jin2307135 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Integrative Neuroscience, 2024. Verfasst von Hyung-Jun Moon und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Artificial Intelligence, Yonsei University, 03722 Seoul, Republic of Korea. Hauptthemen laut MEDLINE: Autism Spectrum Disorder, Deep Learning. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: IITP grant funded by the Korean government (MSIT), ETRI grant funded by the Korean government.
Abstract (Originalsprache)
Background
Autism spectrum disorder (ASD) is a neurodevelopmental disorder exhibiting heterogeneous characteristics in patients, including variability in developmental progression and distinct neuroanatomical features influenced by sex and age. Recent advances in deep learning models based on functional connectivity (FC) graphs have produced promising results, but they have focused on generalized global activation patterns and failed to capture specialized regional characteristics and accurately assess disease indications.
Methods
To overcome these limitations, we propose a novel deep learning method that models FC with multi-head attention, which enables simultaneous modeling of the intricate and variable patterns of brain connectivity associated with ASD, effectively extracting abnormal patterns of brain connectivity. The proposed method not only identifies region-specific correlations but also emphasizes connections at specific, transient time points from diverse perspectives. The extracted FC is transformed into a graph, assigning weighted labels to the edges to reflect the degree of correlation, which is then processed using a graph neural network capable of handling edge labels.
Results
Experiments on the autism brain imaging data exchange (ABIDE) I and II datasets, which include a heterogeneous cohort, showed superior performance over the state-of-the-art methods, improving accuracy by up to 3.7%p. The incorporation of multi-head attention in FC analysis markedly improved the distinction between typical brains and those affected by ASD. Additionally, the ablation study validated diverse brain characteristics in ASD patients across different ages and sexes, offering insightful interpretations.
Conclusion
These results emphasize the effectiveness of the method in enhancing diagnostic accuracy and its potential in advancing neurological research for ASD diagnosis.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Artificial Intelligence, Yonsei University, 03722 Seoul, Republic of Korea.
- Department of Computer Science, Yonsei University, 03722 Seoul, Republic of Korea.
Förderung
- IITP grant funded by the Korean government (MSIT)
- ETRI grant funded by the Korean government
Zitieren
APA
Moon, H. J., & Cho, S. B. (2024). Exploring Implicit Biological Heterogeneity in ASD Diagnosis Using a Multi-Head Attention Graph Neural Network. Journal of Integrative Neuroscience. https://doi.org/10.31083/j.jin2307135
Vancouver
Moon HJ, Cho SB. Exploring Implicit Biological Heterogeneity in ASD Diagnosis Using a Multi-Head Attention Graph Neural Network. Journal of Integrative Neuroscience. 2024. doi:10.31083/j.jin2307135
BibTeX
@article{Moon2024,
author = {Moon, Hyung-Jun and Cho, Sung-Bae},
title = {Exploring Implicit Biological Heterogeneity in ASD Diagnosis Using a Multi-Head Attention Graph Neural Network},
journal = {Journal of Integrative Neuroscience},
year = {2024},
doi = {10.31083/j.jin2307135}
}
EUVIMED