Abstract
Developing new diagnostic models based on the underlying biological mechanisms rather than subjective symptoms for psychiatric disorders is an emerging consensus. Recently, machine learning (ML)-based classifiers using functional connectivity (FC) for psychiatric disorders and healthy controls (HCs) are developed to identify brain markers. However, existing ML-based diagnostic models are prone to overfitting (due to insufficient training samples) and perform poorly in new test environments. Furthermore, it is difficult to obtain explainable and reliable brain biomarkers elucidating the underlying diagnostic decisions. These issues hinder their possible clinical applications. In this work, we propose BrainIB, a new graph neural network (GNN) framework to analyze functional magnetic resonance images (fMRI), by leveraging the famed information bottleneck (IB) principle. BrainIB is able to identify the most informative edges in the brain (i.e., subgraph) and generalizes well to unseen data. We evaluate the performance of BrainIB against three baselines and seven state-of-the-art (SOTA) brain network classification methods on three psychiatric datasets and observe that our BrainIB always achieves the highest diagnosis accuracy. It also discovers the subgraph biomarkers that are consistent with clinical and neuroimaging findings.
| Original language | English |
|---|---|
| Pages (from-to) | 13066-13079 |
| Number of pages | 14 |
| Journal | IEEE Transactions on Neural Networks and Learning Systems |
| Volume | 36 |
| Issue number | 7 |
| Early online date | 13 Sept 2024 |
| DOIs | |
| Publication status | Published - Jul 2025 |
Bibliographical note
Publisher Copyright:© 2012 IEEE.
Funding
Manuscript received 13 June 2022; revised 27 May 2023 and 11 June 2024; accepted 20 August 2024. Date of publication 13 September 2024; date of current version 9 July 2025. This work was supported in part by the National Natural Science Foundation of China under Grant 62088102, Grant U21A20485, and Grant 62311540022; and in part by the Research Council of Norway under Grant 309439. (Kaizhong Zheng, Shujian Yu, and Baojuan Li contributed equally to this work.) (Corresponding authors: Shujian Yu; Badong Chen.) This work involved human subjects or animals in its research. Approval of all ethical and experimental procedures and protocols was granted by the local institutional review boards.
Keywords
- Brain network
- functional magnetic resonance imaging (fMRI)
- graph neural network (GNN)
- information bottleneck (IB)
- psychiatric diagnosis
Fingerprint
Dive into the research topics of 'BrainIB: Interpretable Brain Network-Based Psychiatric Diagnosis With Graph Information Bottleneck'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver