Article

Interpretable Transformer Models for rs-fMRI Epilepsy Classification and Biomarker Discovery

2025-09-04

Abstract excerpt

<h4>Background</h4> Automated interpretation of resting-state fMRI (rs-fMRI) for epilepsy diagnosis remains a challenge. We developed a regularized transformer that models parcel-wise spatial patterns and long-range temporal dynamics to classify epilepsy and generate interpretable, network-level candidate biomarkers. <h4>Methods</h4> Inputs were Schaefer-200 parcel time series extracted after standardized prepro...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 6adb764a-94d4-5151-a172-05585fa433b6
DOI: 10.1101/2025.09.02.25334737

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Interpretable Transformer Models for rs-fMRI Epilepsy Classification and Biomarker DiscoveryDOI 10.1101/2025.09.02.25334737Read

Unsupervised Representation Learning Reveals Individualized Neurophysiological ProfilesSemantic proximity Read

BrainLM: A foundation model for brain activity recordingsSemantic proximity Read

PI-FC: Pre-training Individual-specific Functional Connectome through State-invariant Contrastive LearningSemantic proximity Read

The ENIGMA‐Epilepsy working group: Mapping disease from large data setsSemantic proximity Read

Towards a general-purpose foundation model for fMRI analysisSemantic proximity Read

Self-Supervised Data-Driven Approach Defines Pathological High-Frequency Oscillations in HumanSemantic proximity Read

DBTR-AGF: A Dual-Branch Transformer–Recurrent Network with Adaptive Gating for Epileptic Seizure PredictionSemantic proximity Read

Artificial intelligence and MRI: the source of a new epilepsy taxonomySemantic proximity Read

Reliability and disease sensitivity are dissociable properties of EEG foundation-model representationsSemantic proximity Read

Gray Matters: An Efficient Vision Transformer GAN Framework for Predicting Functional Network Connectivity Biomarkers from Brain StructureSemantic proximity Read

Memory network activity flow failures in temporal and frontal lobe epilepsySemantic proximity Read

Local-Global Parcellation of the Human Cerebral Cortex From Intrinsic Functional Connectivity MRISemantic proximity Read