mlsanityData to 14 Oct 2026

Fusing Structural and Functional Connectivities using Disentangled VAE for Detecting MCI

arXiv 2306.09629 ↗First posted 16 Jun 2023eess.IV cs.CV q-bio.NCcited by 0

Not on the map. Why?

Abstract (arXiv)

Brain network analysis is a useful approach to studying human brain disorders because it can distinguish patients from healthy people by detecting abnormal connections. Due to the complementary information from multiple modal neuroimages, multimodal fusion technology has a lot of potential for improving prediction performance. However, effective fusion of multimodal medical images to achieve complementarity is still a challenging problem. In this paper, a novel hierarchical structural-functional connectivity fusing (HSCF) model is proposed to construct brain structural-functional connectivity matrices and predict abnormal brain connections based on functional magnetic resonance imaging (fMRI) and diffusion tensor imaging (DTI). Specifically, the prior knowledge is incorporated into the separators for disentangling each modality of information by the graph convolutional networks (GCN). And a disentangled cosine distance loss is devised to ensure the disentanglement's effectiveness. Moreover, the hierarchical representation fusion module is designed to effectively maximize the combination of relevant and effective features between modalities, which makes the generated structural-functional connectivity more robust and discriminative in the cognitive disease analysis. Results from a wide range of tests performed on the public Alzheimer's Disease Neuroimaging Initiative (ADNI) database show that the proposed model performs better than competing approaches in terms of classification evaluation. In general, the proposed HSCF model is a promising model for generating brain structural-functional connectivities and identifying abnormal brain connections as cognitive disease progresses.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 15 of its 48 references that are in the map. First posted on arXiv 16 Jun 2023.

Builds on

15 of 48 references.

References · 15

  1. 2019An Introduction to Variational Autoencoderscited by 1,000
  2. 2015Diffusion-Convolutional Neural Networkscited by 268
  3. 2017NiftyNet: a deep-learning platform for medical imagingcited by 45
  4. 2020Bidirectional Mapping Generative Adversarial Networks for Brain MR to PET Synthesiscited by 38
  5. 2020Fine Perceptive GANs for Brain MR Image Super-Resolution in Wavelet Domaincited by 24
  6. 2021Source-free unsupervised domain adaptation for cross-modality abdominal multi-organ segmentationcited by 23
  7. 2020Tensorizing GAN with High-Order Pooling for Alzheimer's Disease Assessmentcited by 21
  8. 2021Multimodal Representations Learning and Adversarial Hypergraph Fusion for Early Alzheimer's Disease Predictioncited by 20
  9. 2018Multi-View Graph Convolutional Network and Its Applications on Neuroimage Analysis for Parkinson's Diseasecited by 19
  10. 2021Unsupervised domain adaptation for cross-modality liver segmentation via joint adversarial learning and self-learningcited by 13
  11. 2021Morphological feature visualization of Alzheimer's disease via Multidirectional Perception GANcited by 12
  12. 2023Brain Structure-Function Fusing Representation Learning using Adversarial Decomposed-VAE for Analyzing MCIcited by 5
3 more
  1. 2021A Prior Guided Adversarial Representation Learning and Hypergraph Perceptual Network for Predicting Abnormal Connections of Alzheimer's Diseasecited by 3
  2. 2022Multiscale Autoencoder with Structural-Functional Attention Network for Alzheimer's Disease Predictioncited by 3
  3. 2023Brain Imaging-to-Graph Generation using Adversarial Hierarchical Diffusion Models for MCI Causality Analysiscited by 2

Built on by

Not cited yet.