Explainable Normative Modeling for Brain Disorder Identification in Resting-State fMRI
Open Access
- 10 November 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 45 (4) , 1606-1619
Abstract
Accurate identification of brain disorders enables timely intervention and improved patient outcomes. While numerous studies have developed AI models for resting-state functional magnetic resonance imaging (rs-fMRI) analysis, most rely on supervised learning, which can overlook hidden patterns that are less discriminatively associated with labels and require large annotated datasets. To address these limitations, we propose leveraging normative modeling, an unsupervised approach that constructs a model of normality based on healthy controls’ data. Deviations from normality indicate potential disorders. However, applying normative modeling to rs-fMRI faces two significant challenges: constructing normality and ensuring explainability. To tackle these challenges, we propose BRAINEXA, a novel framework enhancing normative modeling for rs-fMRI-based brain disorder identification. Specifically, to construct accurate and stable normality, BRAINEXA introduces a training strategy that predicts more informative regions from less informative regions, discouraging trivial self-supervised learning solutions and improving representation learning without additional overhead. Furthermore, we incorporate spatiotemporal mutual information regularization to preserve distinctiveness between more informative regions and less informative regions during latent encoding, preventing potential representational distortions. For interpretability, BRAINEXA extracts normality-defining (ND) subregions, the core regions that characterize normal brain function. By combining ND subregions with anomaly scores, BRAINEXA can offer region- and connection-wise explanations that help identify clinically meaningful disruptions of normality in an unsupervised setting. We demonstrate the effectiveness of BRAINEXA on four public rs-fMRI datasets: REST-meta-MDD, ABIDE I, ADHD-200, and OASIS-3. Our code is available at https://github.com/ku-milab/BRAINEXA.Keywords
Funding Information
- Institute of Information and Communications Technology Planning and Evaluation (IITP) grant funded by the Ministry of Science and ICT (MSIT), Republic of Korea, National AI Research Laboratory Project (RS-2024-00457882)
- Artificial Intelligence Graduate School Program (RS-2019-II190079)
This publication has 45 references indexed in Scilit:
- A Comprehensive Review of the Oversmoothing in Graph Neural Networks2024
- Automatic diagnosis of schizophrenia and attention deficit hyperactivity disorder in rs-fMRI modality using convolutional autoencoder model and interval type-2 fuzzy regressionCognitive Neurodynamics, 2022
- Hierarchical Bayesian Regression for Multi-site Normative Modeling of Neuroimaging Data2020
- Regularized siamese neural network for unsupervised outlier detection on brain multiparametric magnetic resonance imaging: Application to epilepsy lesion screeningMedical Image Analysis, 2020
- Dissecting the Heterogeneous Cortical Anatomy of Autism Spectrum Disorder Using Normative ModelsBiological Psychiatry: Cognitive Neuroscience and Neuroimaging, 2019
- Mapping the Heterogeneous Phenotype of Schizophrenia and Bipolar Disorder Using Normative ModelsJAMA Psychiatry, 2018
- Long Short-Term Memory2012
- Gaussian Processes in Machine Learning2004
- Automated Anatomical Labeling of Activations in SPM Using a Macroscopic Anatomical Parcellation of the MNI MRI Single-Subject BrainNeuroImage, 2002
- Index for rating diagnostic testsCancer, 1950