EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

The effect of node features on GCN-based brain network classification: an empirical study

Guangyu Wang, Limei Zhang, Lishan Qiao

PeerJ · 2023

DOI: 10.7717/peerj.14835 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PeerJ, 2023. Verfasst von Guangyu Wang und 2 weiteren Autor:innen. Beteiligte Einrichtung: Liaocheng University, Liaocheng, China. Hauptthemen laut MEDLINE: Brain, Brain Diseases. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Shandong Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Brain functional network (BFN) analysis has become a popular technique for identifying neurological/mental diseases. Due to the fact that BFN is a graph, a graph convolutional network (GCN) can be naturally used in the classification of BFN. Different from traditional methods that directly use the adjacency matrices of BFNs to train a classifier, GCN requires an additional input-node features. To our best knowledge, however, there is no systematic study to analyze their influence on the performance of GCN-based brain disorder classification. Therefore, in this study, we conduct an empirical study on various node feature measures, including (1) original fMRI signals, (2) one-hot encoding, (3) node statistics, (4) node correlation, and (5) their combination. Experimental results on two benchmark databases show that different node feature inputs to GCN significantly affect the brain disease classification performance, and node correlation usually contributes higher accuracy compared to original signals and manually extracted statistical features.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

BrainBrain DiseasesHumansBenchmarkingDatabases, FactualEmpirical Research

Stichwörter der Autor:innen

Autism spectrum disorderEmpirical studyGraph convolutional networkMild cognitive impairmentNode features

Autor:innen und Institutionen

  • Liaocheng University, Liaocheng, China.
  • Shandong Jianzhu University, Jinan, China.

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Shandong Province

Zitieren

APA

Wang, G., Zhang, L., & Qiao, L. (2023). The effect of node features on GCN-based brain network classification: an empirical study. PeerJ. https://doi.org/10.7717/peerj.14835

Vancouver

Wang G, Zhang L, Qiao L. The effect of node features on GCN-based brain network classification: an empirical study. PeerJ. 2023. doi:10.7717/peerj.14835

BibTeX
@article{Wang2023,
  author = {Wang, Guangyu and Zhang, Limei and Qiao, Lishan},
  title = {The effect of node features on GCN-based brain network classification: an empirical study},
  journal = {PeerJ},
  year = {2023},
  doi = {10.7717/peerj.14835}
}
Kostenlos starten →