Multi-Site rs-fMRI Domain Alignment for Autism Spectrum Disorder Auxiliary Diagnosis Based on Hyperbolic Space.

Researchers created a new computer program to help diagnose autism using brain scans. The main problem was that brain scan data from different hospitals or research centers looked very different, making diagnosis less accurate. Their new method better handles these differences and improved accuracy by about 4%. This could potentially help doctors make more reliable autism diagnoses using brain imaging technology.

This study developed a novel artificial intelligence algorithm to improve autism spectrum disorder (ASD) diagnostic accuracy using brain imaging data from multiple research sites. The researchers addressed a key challenge in autism diagnosis: brain scan data varies significantly between different research centers, which reduces diagnostic accuracy. Their solution used hyperbolic space embedding, a mathematical approach that better represents brain network structures, combined with domain alignment techniques to reduce site-to-site variations. The algorithm achieved 4.03% improved accuracy compared to existing methods and demonstrated robustness across different data sources.

The approach was also validated on major depressive disorder datasets, suggesting broader applicability for neuropsychiatric conditions.

This computational approach could potentially support clinicians in autism diagnosis using neuroimaging, particularly in multi-site research or clinical networks. However, extensive validation with larger samples and comparison to standard diagnostic procedures would be needed before clinical implementation. The method's ability to handle data heterogeneity could facilitate collaborative research efforts.

Sample size not reported. Study type unclear. Future publication date (2026) suggests preliminary or theoretical work. Limited details on validation datasets, participant characteristics, and real-world clinical testing. No information on comparison with current clinical diagnostic standards.

Increasing the volume of training data can enable the auxiliary diagnostic algorithms for Autism Spectrum Disorder (ASD) to learn more accurate and stable models. However, due to the significant heterogeneity and domain shift in rs-fMRI data across different sites, the accuracy of auxiliary diagnosis remains unsatisfactory. Moreover, there has been limited exploration of multi-source domain adaptation models on ASD recognition, and many existing models lack inherent interpretability, as they do not explicitly incorporate prior neurobiological knowledge such as the hierarchical structure of functional brain networks. To address these challenges, we proposed a domain-adaptive algorithm based on hyperbolic space embedding.

Hyperbolic space is naturally suited for representing the topology of complex networks such as brain functional networks. Therefore, we embedded the brain functional network into hyperbolic space and constructed the corresponding hyperbolic space community network to effectively extract latent representations. To address the heterogeneity of data across different sites and the issue of domain shift, we introduce a constraint loss function, Hyperbolic Maximum Mean Discrepancy (HMMD), to align the marginal distributions in the hyperbolic space. Additionally, we employ class prototype alignment to mitigate discrepancies in conditional distributions across domains.

Experimental results indicate that the proposed algorithm achieves superior classification performance for ASD compared to baseline models, with improved robustness to multi-site heterogeneity. Specifically, our method achieves an average accuracy improvement of 4.03% . Moreover, its generalization capability is further validated through experiments conducted on extra Major Depressive Disorder (MDD) datasets.