Confound Controlled Multimodal Neuroimaging Data Fusion and Its Application to Developmental Disorders.

Researchers created a new way to analyze brain scans that looks at multiple types of brain images together while accounting for factors like age and movement. They tested this on children with ADHD and autism and found specific brain patterns linked to each condition's symptoms. The method was better at identifying differences between children with these conditions and those without them compared to other approaches.

This study developed CR-mCCAR, a new method for analyzing brain imaging data that combines multiple types of scans while controlling for confounding factors like age and motion. The researchers tested this approach on children with ADHD and autism spectrum disorder (ASD). The method identified specific brain network patterns associated with core symptoms in both conditions: striato-thalamo-cortical and salience areas in ADHD, and salience and fronto-temporal areas in ASD. These patterns were linked to clinical symptoms but not influenced by age or head movement during scanning.

The approach showed superior accuracy in distinguishing between children with neurodevelopmental conditions and typically developing controls compared to existing methods, and results were replicated in an independent dataset.

This neuroimaging fusion method could potentially improve diagnostic accuracy for autism and ADHD by identifying reliable brain-based biomarkers. However, the clinical utility requires further validation in larger studies before implementation in diagnostic practice.

Sample size not reported. Study type unclear. Results need validation in larger, more diverse samples. Real-world clinical utility remains to be established. The method's complexity may limit practical implementation in clinical settings.

Multimodal fusion provides multiple benefits over single modality analysis by leveraging both shared and complementary information from different modalities. Notably, supervised fusion enjoys extensive interest for capturing multimodal co-varying patterns associated with clinical measures. A key challenge of brain data analysis is how to handle confounds, which, if unaddressed, can lead to an unrealistic description of the relationship between the brain and clinical measures. Current approaches often rely on linear regression to remove covariate effects prior to fusion, which may lead to information loss, rather than pursue the more global strategy of optimizing both fusion and covariates removal simultaneously.

Thus, we propose "CR-mCCAR" to jointly optimize for confounds within a guided fusion model, capturing co-varying multimodal patterns associated with a specific clinical domain while also discounting covariate effects. Simulations show that CR-mCCAR separate the reference and covariate factors accurately. Functional and structural neuroimaging data fusion reveals co-varying patterns in attention deficit/hyperactivity disorder (ADHD, striato-thalamo-cortical and salience areas) and in autism spectrum disorder (ASD, salience and fronto-temporal areas) that link with core symptoms but uncorrelate with age and motion. These results replicate in an independent cohort.

Downstream classification accuracy between ADHD/ASD and controls is markedly higher for CR-mCCAR compared to fusion and regression separately. CR-mCCAR can be extended to include multiple targets and multiple covariates. Overall, results demonstrate CR-mCCAR can jointly optimize for target components that correlate with the reference(s) while removing nuisance covariates. This approach can improve the meaningful detection of reliable phenotype-linked multimodal biomarkers for brain disorders.