Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Qurat Ul Ain, Alptekin Temizel, Soyiba Jawed

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.

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

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.

Paper Structure

This paper contains 14 sections, 6 equations, 5 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Proposed Methodology
  3. Data Preprocessing
  4. Feature Extraction Module
  5. Structural Covariance Networks Modeling Module
  6. Classification Module
  7. Model Interpretability (Post-hoc Analysis)
  8. Experimental Evaluation
  9. Data Acquisition
  10. Classification Performance
  11. Interpretability Results
  12. Performance Comparison
  13. Ablation Study
  14. Conclusion and Future Work

Figures (5)

  • Figure 1: Overview of the proposed DuSCN-FusionNet framework for ADHD classification.
  • Figure 2: ROC curve for DuSCN-FusionNet in ADHD vs. HC classification (AUC = 0.778), outperforming random chance.
  • Figure 3: Confusion matrix of DuSCN-FusionNet predictions for ADHD and HCs, summarizing classification performance across subjects.
  • Figure 4: ROI-level interpretability analysis using Grad-CAM on the SCN-CNN branch.
  • Figure 5: Top 12 most salient brain regions identified by Grad-CAM. ROIs above the 90th percentile threshold are retained as candidate structural biomarkers for ADHD classification.