Spatiotemporal graphs are a natural representation of dynamic brain activity derived from functional magnetic imaging (fMRI) data. Previous works, however, tend to ignore time dynamics of the brain and focus on static graphs. In this paper, we propose a temporal graph deep generative model (TG-DGM) which clusters brain regions into communities that evolve over time. In particular, subject embeddings capture inter-subject variability and its impact on communities using neural networks. We validate our model on the UK Biobank data. Results of up to 0.81 AUC ROC on the task of biological sex classification demonstrate that injecting time dynamics in our model outperforms a static baseline. Keywords: Temporal Graph, Generative Model, Deep Learning, fMRI

Emilov Spasov, S., Campbell, A., Dimitri, G.M., Di Stefano, A., Scarselli, F., & Lio, P. (2021). TG-DGM: Clustering Brain Activity using a Temporal Graph Deep Generative Mode. In Medical Imaging with Deep Learning 2021.

TG-DGM: Clustering Brain Activity using a Temporal Graph Deep Generative Mode

Giovanna Dimitri;franco scarselli;
2021

Abstract

Spatiotemporal graphs are a natural representation of dynamic brain activity derived from functional magnetic imaging (fMRI) data. Previous works, however, tend to ignore time dynamics of the brain and focus on static graphs. In this paper, we propose a temporal graph deep generative model (TG-DGM) which clusters brain regions into communities that evolve over time. In particular, subject embeddings capture inter-subject variability and its impact on communities using neural networks. We validate our model on the UK Biobank data. Results of up to 0.81 AUC ROC on the task of biological sex classification demonstrate that injecting time dynamics in our model outperforms a static baseline. Keywords: Temporal Graph, Generative Model, Deep Learning, fMRI
Emilov Spasov, S., Campbell, A., Dimitri, G.M., Di Stefano, A., Scarselli, F., & Lio, P. (2021). TG-DGM: Clustering Brain Activity using a Temporal Graph Deep Generative Mode. In Medical Imaging with Deep Learning 2021.
File in questo prodotto:
File Dimensione Formato  
tg_dgm_clustering_brain_activi.pdf

accesso aperto

Tipologia: PDF editoriale
Licenza: PUBBLICO - Pubblico con Copyright
Dimensione 219.24 kB
Formato Adobe PDF
219.24 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/11365/1153557