Alzheimer's Disease (AD) is a neurodegenerative process characterized by the accumulation of amyloid-β (Aβ) and tau (τ) proteins leading to neurodegeneration. It has been hypothesizes that the aggregation of these proteins could spread through specific white matter (WM) pathways. To investigate such hypothesis, convolutional neural networks were employed to analyze microstructural alterations induced by the accumulation of Aβ and τ proteins via two classification tasks, relying on mean diffusivity (MD) and fractional anisotropy (FA), achieving competitive performance. A post-hoc analysis via integrated gradients revealed that the splenium of the corpus callosum played a prominent role for both indices, while index-specific were the ventricles and subcortical regions for MD and the corticospinal tract for FA. This supports the assumption that WM pathways might play a key role in misfolded protein distribution and highlights the potential of diffusion imaging for the identification of Aβ and τ proteins spread and accumulation.

Diffusion MRI Allows Capturing the Amyloid-β and τ Proteins Status in Alzheimer’s Disease Continuum

Dolci, Giorgio;Cruciani, Federica;Brusini, Lorenza;Galazzo, Ilaria Boscolo;Menegaz, Gloria
2024-01-01

Abstract

Alzheimer's Disease (AD) is a neurodegenerative process characterized by the accumulation of amyloid-β (Aβ) and tau (τ) proteins leading to neurodegeneration. It has been hypothesizes that the aggregation of these proteins could spread through specific white matter (WM) pathways. To investigate such hypothesis, convolutional neural networks were employed to analyze microstructural alterations induced by the accumulation of Aβ and τ proteins via two classification tasks, relying on mean diffusivity (MD) and fractional anisotropy (FA), achieving competitive performance. A post-hoc analysis via integrated gradients revealed that the splenium of the corpus callosum played a prominent role for both indices, while index-specific were the ventricles and subcortical regions for MD and the corticospinal tract for FA. This supports the assumption that WM pathways might play a key role in misfolded protein distribution and highlights the potential of diffusion imaging for the identification of Aβ and τ proteins spread and accumulation.
2024
Convolutional Neural Network
Integrated Gradient
Post-hoc Analysis
File in questo prodotto:
Non ci sono file associati a questo prodotto.

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: https://hdl.handle.net/11562/1137326
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? ND
social impact