NeuroAlign: Hierarchical Multimodal Fusion of Dynamic and Structural Neuroimaging for MCI Analysis
Quick Answer
NeuroAlign introduces a hierarchical framework for multimodal neuroimaging fusion, achieving competitive MCI/SCD detection across datasets like GUTCM and ADNI.
Quick Take
NeuroAlign introduces a hierarchical framework for multimodal neuroimaging fusion, achieving competitive MCI/SCD detection across datasets like GUTCM and ADNI. Its Dual-Modal Hierarchical Alignment and Synergistic Activation Mapping enhance feature alignment and inspection, revealing modality-specific brain patterns.
Key Points
- NeuroAlign employs Dual-Modal Hierarchical Alignment for effective feature alignment.
- Achieves competitive results in MCI/SCD detection through five-fold validation.
- Utilizes Synergistic Activation Mapping for detailed feature-level inspection.
- Reveals modality-specific brain patterns, aiding multimodal representation analysis.
- Evaluated on multiple datasets including GUTCM, ADNI, and OASIS.
Article Content
From source RSS / original summaryarXiv:2606. 07635v1 Announce Type: new Abstract: Multimodal neuroimaging fusion of functional MRI (fMRI) and diffusion tensor imaging (DTI) provides complementary information for cognitive impairment analysis, but remains challenged by heterogeneous feature spaces and misaligned representations. We propose \textit{NeuroAlign}, a hierarchical framework for structured multimodal fusion.
It introduces (1) \textit{Dual-Modal Hierarchical Alignment} (DMHA), which models multi-scale dynamic connectivity and aligns dynamic-static and functional-structural embeddings; and (2) \textit{Dual-Domain Hierarchical Interaction} (DDHI), which enables fine-grained modulation and global interaction between connectivity- and region-level features.
To support feature-level inspection, we design \textit{Synergistic Activation Mapping} (SAM), a gradient-free, marker-oriented attribution method for DFC, SFC, ALFF, and FA. Evaluated on GUTCM, ADNI, and OASIS under five-fold validation, NeuroAlign achieves competitive MCI/SCD detection and preliminary cross-dataset transferability. Attribution analyses reveal modality-specific and partially consistent brain patterns, providing model-derived evidence for multimodal representation analysis.
Reader Mode unavailable (could not extract clean content).
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CV
See more →LLM-Guided ANN Index Optimization for Human-Object Interaction Retrieval
A phase-aware LLM agent optimizes human-object interaction retrieval, outperforming Optuna TPE by 33.3% and VDTuner by 34.2% on the HICO-DET benchmark. This method enhances throughput by 15.3x over UniIR and demonstrates strong transferability across vector database management systems.