A Novel GNN Framework Integrating Neuroimaging and Behavioral Information to Understand Adolescent Psychiatric Disorders

Weifeng Yu, Gang Qu, Young-geun Kim, Lei Xu, Aiying Zhang
Proceedings of The 8th International Conference on Medical Imaging with Deep Learning, PMLR 301:1795-1810, 2026.

Abstract

Functional connectivity (FC) is widely used to study various psychiatric disorders, but its consistency is often undermined by significant inter-subject variability. While these differences can be reflected in behavioral characteristics, few studies have combined them with FC. To this end, we propose a novel graph learning framework that enhances the differentiation of psychiatric disorders by integrating FC and behavioral characteristics. Additionally, we apply Grad-CAM to enhance model interpretability by identifying key regions of interest involved in distinguishing individuals with psychiatric disorders from healthy controls. Experiments with the Adolescent Brain Cognitive Development dataset highlighted two critical insights: the thalamus and specific ROIs within the somatomotor and cingulo-opercular networks play a critical role for identifying psychiatric disorders. Additionally, visualization of latent representations demonstrated that individuals with externalizing disorders, specifically Attention Deficit Hyperactivity Disorder and Oppositional Defiant Disorder, can be distinguished from healthy controls. These findings underscore the utility of our graph learning framework for identifying psychiatric disorders and suggest its promise for improving diagnostic accuracy.

Cite this Paper

BibTeX
@InProceedings{pmlr-v301-yu26a, title = {A Novel GNN Framework Integrating Neuroimaging and Behavioral Information to Understand Adolescent Psychiatric Disorders}, author = {Yu, Weifeng and Qu, Gang and Kim, Young-geun and Xu, Lei and Zhang, Aiying}, booktitle = {Proceedings of The 8th International Conference on Medical Imaging with Deep Learning}, pages = {1795--1810}, year = {2026}, editor = {Tasdizen, Tolga and Elhabian, Shireen and Summers, Ronald and Chen, Chen and Koch, Lisa and Zhuang, Yan}, volume = {301}, series = {Proceedings of Machine Learning Research}, month = {09--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v301/main/assets/yu26a/yu26a.pdf}, url = {https://proceedings.mlr.press/v301/yu26a.html}, abstract = {Functional connectivity (FC) is widely used to study various psychiatric disorders, but its consistency is often undermined by significant inter-subject variability. While these differences can be reflected in behavioral characteristics, few studies have combined them with FC. To this end, we propose a novel graph learning framework that enhances the differentiation of psychiatric disorders by integrating FC and behavioral characteristics. Additionally, we apply Grad-CAM to enhance model interpretability by identifying key regions of interest involved in distinguishing individuals with psychiatric disorders from healthy controls. Experiments with the Adolescent Brain Cognitive Development dataset highlighted two critical insights: the thalamus and specific ROIs within the somatomotor and cingulo-opercular networks play a critical role for identifying psychiatric disorders. Additionally, visualization of latent representations demonstrated that individuals with externalizing disorders, specifically Attention Deficit Hyperactivity Disorder and Oppositional Defiant Disorder, can be distinguished from healthy controls. These findings underscore the utility of our graph learning framework for identifying psychiatric disorders and suggest its promise for improving diagnostic accuracy.} }
Endnote
%0 Conference Paper %T A Novel GNN Framework Integrating Neuroimaging and Behavioral Information to Understand Adolescent Psychiatric Disorders %A Weifeng Yu %A Gang Qu %A Young-geun Kim %A Lei Xu %A Aiying Zhang %B Proceedings of The 8th International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2026 %E Tolga Tasdizen %E Shireen Elhabian %E Ronald Summers %E Chen Chen %E Lisa Koch %E Yan Zhuang %F pmlr-v301-yu26a %I PMLR %P 1795--1810 %U https://proceedings.mlr.press/v301/yu26a.html %V 301 %X Functional connectivity (FC) is widely used to study various psychiatric disorders, but its consistency is often undermined by significant inter-subject variability. While these differences can be reflected in behavioral characteristics, few studies have combined them with FC. To this end, we propose a novel graph learning framework that enhances the differentiation of psychiatric disorders by integrating FC and behavioral characteristics. Additionally, we apply Grad-CAM to enhance model interpretability by identifying key regions of interest involved in distinguishing individuals with psychiatric disorders from healthy controls. Experiments with the Adolescent Brain Cognitive Development dataset highlighted two critical insights: the thalamus and specific ROIs within the somatomotor and cingulo-opercular networks play a critical role for identifying psychiatric disorders. Additionally, visualization of latent representations demonstrated that individuals with externalizing disorders, specifically Attention Deficit Hyperactivity Disorder and Oppositional Defiant Disorder, can be distinguished from healthy controls. These findings underscore the utility of our graph learning framework for identifying psychiatric disorders and suggest its promise for improving diagnostic accuracy.
APA
Yu, W., Qu, G., Kim, Y., Xu, L. & Zhang, A.. (2026). A Novel GNN Framework Integrating Neuroimaging and Behavioral Information to Understand Adolescent Psychiatric Disorders. Proceedings of The 8th International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 301:1795-1810 Available from https://proceedings.mlr.press/v301/yu26a.html.

Related Material