Characterizing Continuous and Discrete Hybrid Latent Spaces for Structural Connectomes

• URL: http://arxiv.org/abs/2512.02032v1
• Date: Thu, 20 Nov 2025 02:52:17 GMT
• Title: Characterizing Continuous and Discrete Hybrid Latent Spaces for Structural Connectomes
• Abstract summary: Structural connectomes are detailed graphs that map how different brain regions are physically connected.<n>Low-dimensional spaces like PCA and autoencoders are often used to capture major sources of variation.<n>We propose a variational autoencoder (VAE) with a hybrid latent space that jointly models the discrete and continuous components.
• Score: 1.7732287904031832
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Structural connectomes are detailed graphs that map how different brain regions are physically connected, offering critical insight into aging, cognition, and neurodegenerative diseases. However, these connectomes are high-dimensional and densely interconnected, which makes them difficult to interpret and analyze at scale. While low-dimensional spaces like PCA and autoencoders are often used to capture major sources of variation, their latent spaces are generally continuous and cannot fully reflect the mixed nature of variability in connectomes, which include both continuous (e.g., connectivity strength) and discrete factors (e.g., imaging site). Motivated by this, we propose a variational autoencoder (VAE) with a hybrid latent space that jointly models the discrete and continuous components. We analyze a large dataset of 5,761 connectomes from six Alzheimer's disease studies with ten acquisition protocols. Each connectome represents a single scan from a unique subject (3579 females, 2182 males), aged 22 to 102, with 4338 cognitively normal, 809 with mild cognitive impairment (MCI), and 614 with Alzheimer's disease (AD). Each connectome contains 121 brain regions defined by the BrainCOLOR atlas. We train our hybrid VAE in an unsupervised way and characterize what each latent component captures. We find that the discrete space is particularly effective at capturing subtle site-related differences, achieving an Adjusted Rand Index (ARI) of 0.65 with site labels, significantly outperforming PCA and a standard VAE followed by clustering (p < 0.05). These results demonstrate that the hybrid latent space can disentangle distinct sources of variability in connectomes in an unsupervised manner, offering potential for large-scale connectome analysis.

Related papers

• A Multimodal Explainable Deep Learning Framework for Alzheimer's Disease Diagnosis using 3D Magnetic Resonance Imaging and Clinical Data [1.2482871069947656]
  Dementia is a major and growing global health burden, with Alzheimer's disease (AD) accounting for most cases.<n>We developed an explainable multimodal framework pairing a 3D CNN encoder for T1-weighted MRI with a feedforward network for harmonized clinical and demographic data.<n>Our findings show that multimodal performance and explanations are task, modality, fusion, and cohort-dependent.
  arXiv  Detail & Related papers  (2026-09-11T04:02:52Z)
• Disentangling Co-Occurring Retinal Pathologies with Saliency-Guided Sparse Expert Routing [3.332219204498619]
  We propose a novel architecture that resolves this via sparse conditional computation.<n>We show that expert routing aligns with localized lesions and geometrically maps co-occurring cases.
  arXiv  Detail & Related papers  (2026-08-10T15:43:43Z)
• Multi-Source Multi-View Graph Domain Adaptation with Hyperbolic Residual Encoding for Cross-Site MDD Identification from rs-fMRI [7.161131821089437]
  Cross-site identification of major depressive disorder (MDD) from resting-state functional magnetic resonance imaging (rs-fMRI) is hindered by inter-site distribution shifts and heterogeneous functional connectivity (FC) views.<n>These views capture complementary neural relationships but exhibit distinct site biases and graph topologies.<n>Our framework achieves 73.60% mean accuracy and 71.90% AUC.
  arXiv  Detail & Related papers  (2026-07-31T15:30:16Z)
• Dementia Etiology Diagnosis via Collaborative Meta Knowledge Enhancement [81.27196033392559]
  We propose a Collaborative Meta Knowledge Enhancement (COME) framework for dementia etiology diagnosis.<n>COME injects multi-center acquisition semantics, source identifiers, and modality indicators as heterogeneity-aware embeddings into a unified Transformer architecture for scale-up training.<n>Our method achieves state-of-the-art in-domain performance with a mean macro-averaged AUC of 85.62% and a 4.29-point gain over the strongest baseline.
  arXiv  Detail & Related papers  (2026-07-24T04:26:47Z)
• Artemis: Anatomy-Resolved inTervention for Eliminating Multimodal NeuroImage confounderS [39.37223141220675]
  Multimodal neuroimaging enables non-invasive analysis of brain networks using graph neural networks.<n> demographic factors such as age and sex systematically confound the relationship between brain connectivity and clinical outcomes.<n>We propose Artemis, a region-level causal framework that bridges this gap with causal intervention at each brain region independently.
  arXiv  Detail & Related papers  (2026-06-10T05:10:36Z)
• Unsupervised learning of acquisition variability in structural connectomes via hybrid latent space modeling [3.0508963681559913]
  Acquisition differences across sites, scanners, and protocols in dMRI introduce variability that complicates structural connectome analysis.<n>This motivates deep learning models that can represent high-dimensional connectomes in a low-dimensional space while explicitly separating acquisition-related effects from biological variation.<n>Recent hybrid latent-space models combine discrete and continuous components to address this, but typically require manual capacity tuning to ensure the discrete component captures the intended variability.
  arXiv  Detail & Related papers  (2026-05-13T16:11:49Z)
• A Unified Framework for Joint Detection of Lacunes and Enlarged Perivascular Spaces [3.9313804276175506]
  Cerebral small vessel disease (CSVD) markers, specifically enlarged perivascular spaces (EPVS) and lacunae, present a unique challenge in medical image analysis.<n>We propose a morphologydecoupled framework where Zero- Gated CrossTask Attention exploits dense EPVS context to guide sparse lacune detection.
  arXiv  Detail & Related papers  (2026-03-04T16:30:46Z)
• DNA: Uncovering Universal Latent Forgery Knowledge [39.19379714306656]
  forgery detection capability is already encoded within pre-trained models.<n>DNA framework employs a coarse-to-fine excavation mechanism.<n>Hifi-Gen is a high-fidelity synthetic benchmark built upon the very latest models.
  arXiv  Detail & Related papers  (2026-01-30T03:48:30Z)
• R-GenIMA: Integrating Neuroimaging and Genetics with Interpretable Multimodal AI for Alzheimer's Disease Progression [63.97617759805451]
  Early detection of Alzheimer's disease requires models capable of integrating macro-scale neuroanatomical alterations with micro-scale genetic susceptibility.<n>We introduce R-GenIMA, an interpretable multimodal large language model that couples a novel ROI-wise vision transformer with genetic prompting.<n>R-GenIMA achieves state-of-the-art performance in four-way classification across normal cognition, subjective memory concerns, mild cognitive impairment, and AD.
  arXiv  Detail & Related papers  (2025-12-22T02:54:10Z)
• A Multi-scale Fused Graph Neural Network with Inter-view Contrastive Learning for Spatial Transcriptomics Data Clustering [7.214595408714774]
  stMFG is proposed, a multi-scale interactive fusion graph network that introduces layer-wise cross-view attention to dynamically integrate spatial and gene features after each convolution.<n>It outperforms state-of-the-art methods, achieving up to 14% ARI improvement on certain slices.
  arXiv  Detail & Related papers  (2025-12-18T05:13:55Z)
• Enhanced Graph Convolutional Network with Chebyshev Spectral Graph and Graph Attention for Autism Spectrum Disorder Classification [0.0]
  This paper presents a Graph Convolutional Network (GCN) model, incorporating Chebyshev Spectral Graph Convolution and Graph Attention Networks (GAT)<n>The model is trained using stratified five-fold cross-validation with a total input dimension of 5,206 features per individual.<n>Extensive trials demonstrate the enhanced model's superiority, achieving a test accuracy of 74.82% and an AUC of 0.82 on the entire dataset.
  arXiv  Detail & Related papers  (2025-11-27T07:33:31Z)
• Cross-Attention Fusion of MRI and Jacobian Maps for Alzheimer's Disease Diagnosis [5.955559082904072]
  We propose a cross-attention fusion framework to model the intrinsic relationship between sMRI intensity and JSM-derived deformations for Alzheimer's disease classification.<n>Cross-attention fusion achieves superior performance, with mean ROC-AUC scores of 0.903 for AD vs. cognitively normal (CN) and 0.692 for mild cognitive impairment (MCI) vs. CN.<n>Despite its strong performance, our model remains highly efficient, with only 1.56 million parameters--over 40 times fewer than ResNet-34 (63M) and Swin UNETR (61.98M)
  arXiv  Detail & Related papers  (2025-03-01T18:50:46Z)
• Reflecting Topology Consistency and Abnormality via Learnable Attentions for Airway Labeling [19.269806092729468]
  airway anatomical labeling is crucial for clinicians to identify and navigate complex bronchial structures during bronchoscopy.<n>Previous methods are prone to generate inconsistent predictions.<n>This paper proposes a novel method that enhances topological consistency and improves the detection of abnormal airway branches.
  arXiv  Detail & Related papers  (2024-10-31T12:04:30Z)
• ADformer: A Multi-Granularity Spatial-Temporal Transformer for EEG-Based Alzheimer Detection [42.72554952799386]
  EEG has emerged as a cost-effective and efficient tool to support neurologists in the detection of Alzheimer's Disease (AD)<n>We propose ADformer, a novel multi-granularity spatial-temporal transformer designed to capture both temporal and spatial features from raw EEG signals.<n> Experimental results demonstrate that ADformer consistently outperforms existing methods, achieving subject-level F1 scores of 92.82%, 89.83%, 67.99%, and 83.98% on the 4 datasets, respectively.
  arXiv  Detail & Related papers  (2024-08-17T14:10:41Z)
• Spatial-Temporal DAG Convolutional Networks for End-to-End Joint Effective Connectivity Learning and Resting-State fMRI Classification [42.82118108887965]
  Building comprehensive brain connectomes has proved to be fundamental importance in resting-state fMRI (rs-fMRI) analysis. We model the brain network as a directed acyclic graph (DAG) to discover direct causal connections between brain regions. We propose Spatial-Temporal DAG Convolutional Network (ST-DAGCN) to jointly infer effective connectivity and classify rs-fMRI time series.
  arXiv  Detail & Related papers  (2023-12-16T04:31:51Z)
• CLCLSA: Cross-omics Linked embedding with Contrastive Learning and Self Attention for multi-omics integration with incomplete multi-omics data [47.2764293508916]
  Integration of heterogeneous and high-dimensional multi-omics data is becoming increasingly important in understanding genetic data. One obstacle faced when performing multi-omics data integration is the existence of unpaired multi-omics data due to instrument sensitivity and cost. We propose a deep learning method for multi-omics integration with incomplete data by Cross-omics Linked unified embedding with Contrastive Learning and Self Attention.
  arXiv  Detail & Related papers  (2023-04-12T00:22:18Z)
• Hierarchical Graph Convolutional Network Built by Multiscale Atlases for Brain Disorder Diagnosis Using Functional Connectivity [48.75665245214903]
  We propose a novel framework to perform multiscale FCN analysis for brain disorder diagnosis. We first use a set of well-defined multiscale atlases to compute multiscale FCNs. Then, we utilize biologically meaningful brain hierarchical relationships among the regions in multiscale atlases to perform nodal pooling.
  arXiv  Detail & Related papers  (2022-09-22T04:17:57Z)
• Superficial White Matter Analysis: An Efficient Point-cloud-based Deep Learning Framework with Supervised Contrastive Learning for Consistent Tractography Parcellation across Populations and dMRI Acquisitions [68.41088365582831]
  White matter parcellation classifies tractography streamlines into clusters or anatomically meaningful tracts. Most parcellation methods focus on the deep white matter (DWM), whereas fewer methods address the superficial white matter (SWM) due to its complexity. We propose a novel two-stage deep-learning-based framework, Superficial White Matter Analysis (SupWMA), that performs an efficient parcellation of 198 SWM clusters from whole-brain tractography.
  arXiv  Detail & Related papers  (2022-07-18T23:07:53Z)
• Identifying Autism Spectrum Disorder Based on Individual-Aware Down-Sampling and Multi-Modal Learning [4.310840361752551]
  We propose a novel feature extraction method for fMRI that can learn a personalized lowe-resolution representation of the entire brain networking. The present model has achieved a mean classification accuracy of 85.95% and a mean AUC of 0.92, which is better than the state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-09-19T14:22:55Z)
• G-MIND: An End-to-End Multimodal Imaging-Genetics Framework for Biomarker Identification and Disease Classification [49.53651166356737]
  We propose a novel deep neural network architecture to integrate imaging and genetics data, as guided by diagnosis, that provides interpretable biomarkers. We have evaluated our model on a population study of schizophrenia that includes two functional MRI (fMRI) paradigms and Single Nucleotide Polymorphism (SNP) data.
  arXiv  Detail & Related papers  (2021-01-27T19:28:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.