ARXIV:2603.15168 · MEDICAL AI · SUBMITTED 02 APR · 02:30 UTC · FRESHNESS STALE

VerifiedSource: PDF linkedPartialPaperPack: 3 of 4 citation fields filledMissingMissing fields: authorsPartialProof: unverified proof status

Multimodal Connectome Fusion via Cross-Attention for Autism Spectrum Disorder Classification Using Graph Learning

arXiv

A multimodal graph learning framework for improved classification of Autism Spectrum Disorder using integrated imaging data.

Blocked on Code›Score7.0Evidence unverified

Opportunity summary

Pain A multimodal graph learning framework for improved classification of Autism Spectrum Disorder using integrated imaging data.

Evidence 0 refs | 0 sources | 17% coverage

Blocker Evidence unverified

Open Build Read PDF Signal Canvas Track

PROBLEM

A multimodal graph learning framework for improved classification of Autism Spectrum Disorder using integrated imaging data. rs-fMRI has been widely used to identify disruptions in large-scale brain networks, while structural MRI provides complementary information…

METHOD

Full abstract

Autism spectrum disorder (ASD) is a complex neurodevelopmental condition characterized by atypical functional brain connectivity and subtle structural alterations. rs-fMRI has been widely used to identify disruptions in large-scale brain networks, while structural MRI provides complementary information about morphological organization. Despite their complementary nature, effectively integrating these heterogeneous imaging modalities within a unified framework remains challenging. This study proposes a multimodal graph learning framework that preserves the dominant role of functional connectivity while integrating structural imaging and phenotypic information for ASD classification. The proposed framework is evaluated on ABIDE-I dataset. Each subject is represented as a node within a population graph. Functional and structural features are extracted as modality-specific node attributes, while inter-subject relationships are modeled using a pairwise association encoder (PAE) based on phenotypic information. Two Edge Variational GCNs are trained to learn subject-level embeddings. To enable effective multimodal integration, we introduce a novel asymmetric transformer-based cross-attention mechanism that allows functional embeddings to selectively incorporate complementary structural information while preserving functional dominance. The fused embeddings are then passed to a MLP for ASD classification. Using stratified 10-fold cross-validation, the framework achieved an AUC of 87.3% and an accuracy of 84.4%. Under leave-one-site-out cross-validation (LOSO-CV), the model achieved an average cross-site accuracy of 82.0%, outperforming existing methods by approximately 3% under 10-fold cross-validation and 7% under LOSO-CV. The proposed framework effectively integrates heterogeneous multimodal data from the multi-site ABIDE-I dataset, improving automated ASD classification across imaging sites.

RESULT

ScienceToStartup currently rates this 7.0/10 on the public viability pass. To enable effective multimodal integration, we introduce a novel asymmetric transformer-based cross-attention mechanism that allows functional embeddings to selectively incorporate complementary structural information while…

WHY NOW

Medical AI moved forward this cycle; last verified April 2026. Public score 7.0/10.

Continue into Read for claims, analysis, references, and neighboring papers.

Opportunity summary

Score7.0

PainA multimodal graph learning framework for improved classification of Autism Spectrum Disorder using integrated imaging data.

Evidence0 refs | 0 sources | 17% coverage

Blockermissing authors

Analysis summary

A multimodal graph learning framework for improved classification of Autism Spectrum Disorder using integrated imaging data.

VerifiedSource: PDF linkedPartialPaperPack: 3 of 4 citation fields filledMissingMissing fields: authorsPartialProof: unverified proof status

Competitive landscape

A multimodal graph learning framework for improved classification of Autism Spectrum Disorder using integrated imaging data.

Segment

Medical AI

Adoption evidence

No public code link in the paper record yet

Commercial read

7.0/10 public viability

Direct

not classified

Adjacent

not classified

Substitute

not classified

Unknown

not classified

{ "contract_version": "paper-r2", "paper_id": "2f854aa5-b7c5-4359-9fb0-5595bb4931a9", "arxiv_id": "2603.15168", "canonical_route": "/paper/multimodal-connectome-fusion-via-cross-attention-for-autism-spectrum-disorder-classification-using-graph-learning", "active_tab": "synced from current hash by the drawer client", "selected_artifact": "multimodal-connectome-fusion-via-cross-attention-for-autism-spectrum-disorder-classification-using-graph-learning", "endpoints": { "paper_pack": "/api/v1/paper/multimodal-connectome-fusion-via-cross-attention-for-autism-spectrum-disorder-classification-using-graph-learning/paper-pack", "build_passport": "/api/v1/paper/multimodal-connectome-fusion-via-cross-attention-for-autism-spectrum-disorder-classification-using-graph-learning/build-passport", "mcp_resource": "sciencetostartup://surfaces/paper-workspace" } }

{ "surface": "paper", "mode": "paper", "query": "Multimodal Connectome Fusion via Cross-Attention for Autism Spectrum Disorder Classification Using Graph Learning", "normalized_query": "2603.15168", "route": "/paper/multimodal-connectome-fusion-via-cross-attention-for-autism-spectrum-disorder-classification-using-graph-learning", "paper_ref": "multimodal-connectome-fusion-via-cross-attention-for-autism-spectrum-disorder-classification-using-graph-learning", "topic_slug": null, "benchmark_ref": null, "dataset_ref": null }

{ "@context": "https://schema.org", "@graph": [ { "@type": "WebPage", "@id": "https://sciencetostartup.com/paper/multimodal-connectome-fusion-via-cross-attention-for-autism-spectrum-disorder-classification-using-graph-learning#webpage", "url": "https://sciencetostartup.com/paper/multimodal-connectome-fusion-via-cross-attention-for-autism-spectrum-disorder-classification-using-graph-learning", "name": "Multimodal Connectome Fusion via Cross-Attention for Autism Spectrum Disorder Classification Using Graph Learning", "description": "A multimodal graph learning framework for improved classification of Autism Spectrum Disorder using integrated imaging data.", "isPartOf": { "@id": "https://sciencetostartup.com/#website" } }, { "@type": "ScholarlyArticle", "@id": "https://sciencetostartup.com/paper/multimodal-connectome-fusion-via-cross-attention-for-autism-spectrum-disorder-classification-using-graph-learning#scholarlyArticle", "headline": "Multimodal Connectome Fusion via Cross-Attention for Autism Spectrum Disorder Classification Using Graph Learning", "description": "A multimodal graph learning framework for improved classification of Autism Spectrum Disorder using integrated imaging data.", "url": "https://sciencetostartup.com/paper/multimodal-connectome-fusion-via-cross-attention-for-autism-spectrum-disorder-classification-using-graph-learning", "sameAs": "https://arxiv.org/abs/2603.15168", "identifier": { "@type": "PropertyValue", "propertyID": "arXiv", "value": "2603.15168" }, "isAccessibleForFree": true, "isPartOf": { "@id": "https://sciencetostartup.com/#website" }, "datePublished": "2026-03-16T12:02:39.000Z", "additionalProperty": [ { "@type": "PropertyValue", "propertyID": "viabilityScore", "value": 7 }, { "@type": "PropertyValue", "propertyID": "researchDomain", "value": "Medical AI" } ] }, { "@type": "BreadcrumbList", "itemListElement": [ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://sciencetostartup.com" }, { "@type": "ListItem", "position": 2, "name": "Medical AI", "item": "https://sciencetostartup.com/topics" }, { "@type": "ListItem", "position": 3, "name": "Multimodal Connectome Fusion via Cross-Attention for Autism ", "item": "https://sciencetostartup.com/paper/multimodal-connectome-fusion-via-cross-attention-for-autism-spectrum-disorder-classification-using-graph-learning" } ] }, { "@type": "FAQPage", "mainEntity": [ { "@type": "Question", "name": "What products could be built from this research?", "acceptedAnswer": { "@type": "Answer", "text": "Now is the ideal time because of increasing ASD prevalence, rising healthcare costs, and advancements in AI and medical imaging. The global ASD diagnosis market is growing due to better awareness and screening mandates, while healthcare systems face pressure to adopt digital tools for efficiency. Recent improvements in transformer models and graph learning make this multimodal fusion feasible, and regulatory bodies like the FDA are becoming more open to AI-based diagnostic aids, creating a ripe environment for deployment." } }, { "@type": "Question", "name": "What are the practical use cases?", "acceptedAnswer": { "@type": "Answer", "text": "A commercial use case is an AI-powered diagnostic assistant for pediatric neurology clinics, where clinicians upload patient MRI and phenotypic data to receive an automated ASD risk assessment with interpretable insights. This tool would flag high-risk cases for priority review, reduce diagnostic wait times from months to weeks, and provide consistent evaluations across different imaging machines and sites, improving referral accuracy and treatment planning." } } ] } ] }

Competitive landscape

A multimodal graph learning framework for improved classification of Autism Spectrum Disorder using integrated imaging data.

Segment

Medical AI

Adoption evidence

No public code link in the paper record yet

Commercial read

7.0/10 public viability

Direct

not classified

Adjacent

not classified

Substitute

not classified

Unknown

not classified

Multimodal Connectome Fusion via Cross-Attention for Autism Spectrum Disorder Classification Using Graph Learning

Multimodal Connectome Fusion via Cross-Attention for Autism Spectrum Disorder Classification Using Graph Learning

Claim map

Constellation map

Competitive landscape

Buzz

PDF

REFERENCES

Related Papers

Related Resources

Subscribe to the weekly brief

Build artifacts

Brief

Experiment plan

Validation checklist

Scientific founder

Translational engineer

Domain operator

GTM lead

Regulatory/clinical advisor

Timeline

Claim map

Constellation map

Competitive landscape

Buzz

PDF

REFERENCES

Related Papers

Related Resources

Subscribe to the weekly brief

Build artifacts

Brief

Experiment plan

Validation checklist

Scientific founder

Translational engineer

Domain operator

GTM lead

Regulatory/clinical advisor

Timeline