DuSCN-FusionNet: An Interpretable Dual-Channel Structural Covariance Fusion Framework for ADHD Classification Using Structural MRI

2026-03-27

AI Summary

This study addresses the limited reliability and interpretability of existing neuroimaging biomarkers for attention-deficit/hyperactivity disorder (ADHD), which hinder clinical diagnosis. To overcome this, the authors propose a dual-channel structural covariance network (SCN) that separately models regional mean intensity and intra-regional heterogeneity. The framework integrates region-of-interest (ROI)-level variability features with global statistical measures through late fusion. Innovatively adapting Grad-CAM to the SCN architecture, the method generates regional importance scores, thereby enhancing model interpretability and uncovering potential anatomical biomarkers. Evaluated on the ADHD-200 Beijing site dataset, the approach achieves a balanced accuracy of 80.59%, an AUC of 0.778, precision of 81.66%, recall of 80.59%, and an F1-score of 80.27%.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Calibration & Uncertainty Quantification
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• User Modeling, Personalization and Recommendation: User modeling for targeted and personalized online advertising
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Attention Deficit Hyperactivity Disorder (ADHD) is a highly prevalent neurodevelopmental condition; however, its neurobiological diagnosis remains challenging due to the lack of reliable imaging-based biomarkers, particularly anatomical markers. Structural MRI (sMRI) provides a non-invasive modality for investigating brain alterations associated with ADHD; nevertheless, most deep learning approaches function as black-box systems, limiting clinical trust and interpretability. In this work, we propose DuSCN-FusionNet, an interpretable sMRI-based framework for ADHD classification that leverages dual-channel Structural Covariance Networks (SCNs) to capture inter-regional morphological relationships. ROI-wise mean intensity and intra-regional variability descriptors are used to construct intensity-based and heterogeneity-based SCNs, which are processed through an SCN-CNN encoder. In parallel, auxiliary ROI-wise variability features and global statistical descriptors are integrated via late-stage fusion to enhance performance. The model is evaluated using stratified 10-fold cross-validation with a 5-seed ensemble strategy, achieving a mean balanced accuracy of 80.59% and an AUC of 0.778 on the Peking University site of the ADHD-200 dataset. DuSCN-FusionNet further achieves precision, recall, and F1-scores of 81.66%, 80.59%, and 80.27%, respectively. Moreover, Grad-CAM is adapted to the SCN domain to derive ROI-level importance scores, enabling the identification of structurally relevant brain regions as potential biomarkers.

Problem

• ADHD
• structural MRI
• biomarkers
• interpretability
• neurodevelopmental disorder

Innovation

• Structural Covariance Network
• Interpretable Deep Learning
• ADHD Classification
• Dual-Channel Fusion
• Grad-CAM for sMRI