Your browser doesn't support javascript.
loading
Learning site-invariant features of connectomes to harmonize complex network measures.
Newlin, Nancy R; Kanakaraj, Praitayini; Li, Thomas; Pechman, Kimberly; Archer, Derek; Jefferson, Angela; Landman, Bennett; Moyer, Daniel.
Afiliación
  • Newlin NR; Department of Computer Science, Vanderbilt University, Nashville, TN, USA.
  • Kanakaraj P; Department of Computer Science, Vanderbilt University, Nashville, TN, USA.
  • Li T; Department of Biomedical Engineering, Vanderbilt University, Nashville, Tennessee, USA.
  • Pechman K; Vanderbilt Memory and Alzheimer's Center, Vanderbilt University Medical Center, Nashville, TN, USA.
  • Archer D; Vanderbilt Memory and Alzheimer's Center, Vanderbilt University Medical Center, Nashville, TN, USA.
  • Jefferson A; Department of Neurology, Vanderbilt University Medical Center, Nashville, TN, USA.
  • Landman B; Vanderbilt Memory and Alzheimer's Center, Vanderbilt University Medical Center, Nashville, TN, USA.
  • Moyer D; Department of Neurology, Vanderbilt University Medical Center, Nashville, TN, USA.
Proc SPIE Int Soc Opt Eng ; 129302024 Feb.
Article en En | MEDLINE | ID: mdl-39220624
ABSTRACT
Multi-site diffusion MRI data is often acquired on different scanners and with distinct protocols. Differences in hardware and acquisition result in data that contains site dependent information, which confounds connectome analyses aiming to combine such multi-site data. We propose a data-driven solution that isolates site-invariant information whilst maintaining relevant features of the connectome. We construct a latent space that is uncorrelated with the imaging site and highly correlated with patient age and a connectome summary measure. Here, we focus on network modularity. The proposed model is a conditional, variational autoencoder with three additional prediction tasks one for patient age, and two for modularity trained exclusively on data from each site. This model enables us to 1) isolate site-invariant biological features, 2) learn site context, and 3) re-inject site context and project biological features to desired site domains. We tested these hypotheses by projecting 77 connectomes from two studies and protocols (Vanderbilt Memory and Aging Project (VMAP) and Biomarkers of Cognitive Decline Among Normal Individuals (BIOCARD) to a common site. We find that the resulting dataset of modularity has statistically similar means (p-value <0.05) across sites. In addition, we fit a linear model to the joint dataset and find that positive correlations between age and modularity were preserved.
Palabras clave
Texto completo
Añadir a Mi BVS
Imprimir
XML
PubMed Links
Buscar en Google

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Idioma: En Revista: Proc SPIE Int Soc Opt Eng Año: 2024 Tipo del documento: Article País de afiliación: Estados Unidos Pais de publicación: Estados Unidos
Texto completo
Añadir a Mi BVS
Imprimir
XML
PubMed Links
Buscar en Google

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Idioma: En Revista: Proc SPIE Int Soc Opt Eng Año: 2024 Tipo del documento: Article País de afiliación: Estados Unidos Pais de publicación: Estados Unidos