Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
March 14, 2026NeuroImageOpen Access

An explainable framework for the relationship between dementia and metabolism patterns

View Full Paper
Ask AI
Bookmark
Share

Authors

CVC. Vázquez-GarcíaFMF.J. Martínez-MurciaFSF. Segovia

Discussion

Loading...

Member takes

Overview

This framework analyzes neuroimaging to reveal metabolism patterns associated with dementia, indicating potential clinical uses.

Key Points

  • The research aims to develop an explainable framework that connects metabolism patterns in neuroimaging data to dementia progression.
  • Develop a semi-supervised variational autoencoder (VAE) for neuroimaging analysis.
  • Incorporate a similarity regularization term aligning latent variables with clinical and biomarker measures.
  • Analyze Positron Emission Tomography (PET) scans from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database.
  • Utilize a voxel-wise General Linear Model (GLM) to assess metabolism in key brain regions.
  • Establish a correlation between latent variables and clinical cognitive scores related to dementia severity.
  • Demonstrate reduced metabolism in the hippocampus and major Resting State Networks associated with dementia.
  • Effectively disentangle neuroimaging biomarkers from confounding factors like age and inter-subject variability.

Cite This Study

Vázquez-García et al. (2026) studied this question.

synapsesocial.com/papers/69b4fc7fb39f7826a300d6d4https://doi.org/10.1016/j.neuroimage.2026.121855
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1KS-VAE: A Novel Variational Autoencoder Framework for Understanding Alzheimer’s Disease Progression Using Kolmogorov–Smirnov Guidance2026
  2. 2Stage-aware disentangled conditional VAE for interpretable prediction of cognitive decline2026
  3. 3Latent Representation Learning from 3D Brain MRI for Interpretable Prediction in Multiple Sclerosis2025
  4. 4Bridging Imaging and Clinical Scores in Parkinson’s Progression via Multimodal Self-Supervised Deep Learning2024 · 22 citations
  5. 5Latent Space Projections and Atlases, a Cautionary Tale in Deep Neuroimaging using Autoencoders2026