STST-JEPA: Shallow-Target Spatio-Temporal Joint Embedding Prediction Architecture For EEG Self-Supervised Learning

• URL: http://arxiv.org/abs/2607.06629v2
• Date: Thu, 09 Jul 2026 11:36:51 GMT
• Title: STST-JEPA: Shallow-Target Spatio-Temporal Joint Embedding Prediction Architecture For EEG Self-Supervised Learning
• Abstract summary: Brain age is an emerging biomarker whose deviation from chronological age tracks neurological and psychiatric burden.<n>We introduce STST-JEPA, a self-supervised transformer for resting-state and task EEG, pretrained on 47,703 sessions spanning ages 5-81.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Brain age - the age inferred from a physiological recording - is an emerging biomarker whose deviation from chronological age tracks neurological and psychiatric burden, and EEG is an attractive substrate for it because it is cheap, portable, and temporally rich. Yet EEG brain-age models must contend with cross-site montage heterogeneity, small labelled cohorts, and dominant subject-level non-stationarity, and few EEG foundation models have been shown to deliver competitive age regression across the full pediatric to older adult range in which such a biomarker would actually be deployed. We introduce STST-JEPA, a self-supervised transformer for resting-state and task EEG, pretrained on 47,703 sessions spanning ages 5-81 from the brain.space and Healthy Brain Network (HBN) corpora. The model combines a latent-prediction objective - predicting masked-token representations against an EMA-of-tokenizer target - with an auxiliary signal-reconstruction term, applied to 30-second multi-channel windows under spatiotemporal block masks. A lightweight attentive probe trained on frozen pretrained embeddings achieves a best held-out-validation mean absolute error of 3.06 years (r = 0.924) for age regression on 3,367 sessions, against a predict-the-mean baseline of approximately 10 years MAE. With light task-specific finetuning of the model's final layers, the same pretrained encoder achieves rank-1 placements - with the model's native 30-second windows - on the public NeuralBench x brain.space EEG leaderboard for sex classification (balanced accuracy 0.911), age prediction (r = 0.749), and psychopathology composite regression (r = 0.215). We further show that the model's age-prediction residual is negatively correlated with cognitive efficiency over several tasks we examined.

Related papers

• ReMAP: Self-supervised learning to unveil brain representations and vulnerability [3.3233194140188687]
  General anesthesia offers a rare opportunity to observe the human brain under a standardized, controlled perturbation.<n>EEG is almost always reduced to a single proprietary depth index, collapsing a rich trajectory into one number.<n>Here we ask whether the geometry of that trajectory, not merely the depth it reaches, carries clinically meaningful information.
  arXiv  Detail & Related papers  (2026-08-22T17:09:49Z)
• A Gait Foundation Model Predicts Multi-System Health Phenotypes from 3D Skeletal Motion [0.5607972967536581]
  Gait is increasingly recognized as a vital sign, yet current approaches treat it as a symptom of specific pathologies rather than a systemic biomarker.<n>We developed a gait foundation model for 3D skeletal motion from 3,414 deeply phenotyped adults, recorded via a depth camera during five motor tasks.
  arXiv  Detail & Related papers  (2026-03-26T10:21:02Z)
• BrainRotViT: Transformer-ResNet Hybrid for Explainable Modeling of Brain Aging from 3D sMRI [0.3949853729743116]
  We propose Brain ResNet over trained Vision Transformer (BrainRotViT), a hybrid architecture that combines the global context modeling of vision transformers (ViT) with the local refinement of residual CNNs.<n>Our method achieves an MAE of 3.34 years on validation across 11 MRI datasets encompassing more than 130 acquisition sites.<n>Analyses on the brain age gap show that aging patterns are associated with Alzheimer's disease, cognitive impairment, and autism spectrum disorder.
  arXiv  Detail & Related papers  (2025-11-19T07:20:23Z)
• Enhancing Brain Age Estimation with a Multimodal 3D CNN Approach Combining Structural MRI and AI-Synthesized Cerebral Blood Volume Data [14.815462507141163]
  Brain Age Gap Estimation (BrainAGE) offers a neuroimaging biomarker for understanding brain age.<n>Current approaches primarily use T1-weighted magnetic resonance imaging (T1w MRI) data, capturing only structural brain information.<n>We developed a deep learning model using a VGG-based architecture for both modalities and combined their predictions using linear regression.<n>Our model achieved a mean absolute error (MAE) of 3.95 years and an $R2$ of 0.943 on the test set, outperforming existing models trained on similar data.
  arXiv  Detail & Related papers  (2024-12-01T21:54:08Z)
• Brain Tumor Classification on MRI in Light of Molecular Markers [56.99710477905796]
  Co-deletion of the 1p/19q gene is associated with clinical outcomes in low-grade gliomas.<n>This study aims to utilize a specially MRI-based convolutional neural network for brain cancer detection.
  arXiv  Detail & Related papers  (2024-09-29T07:04:26Z)
• Unsupervised Anomaly Detection in 3D Brain MRI using Deep Learning with Multi-Task Brain Age Prediction [53.122045119395594]
  Unsupervised anomaly detection (UAD) in brain MRI with deep learning has shown promising results. We propose deep learning for UAD in 3D brain MRI considering additional age information. Based on our analysis, we propose a novel deep learning approach for UAD with multi-task age prediction.
  arXiv  Detail & Related papers  (2022-01-31T09:39:52Z)
• Predi\c{c}\~ao da Idade Cerebral a partir de Imagens de Resson\^ancia Magn\'etica utilizando Redes Neurais Convolucionais [57.52103125083341]
  Deep learning techniques for brain age prediction from magnetic resonance images are investigated. The identification of biomarkers is useful for detecting an early-stage neurodegenerative process, as well as for predicting age-related or non-age-related cognitive decline. The best result was obtained by the 2D model, which achieved a mean absolute error of 3.83 years.
  arXiv  Detail & Related papers  (2021-12-23T14:51:45Z)
• Voxel-level Importance Maps for Interpretable Brain Age Estimation [70.5330922395729]
  We focus on the task of brain age regression from 3D brain Magnetic Resonance (MR) images using a Convolutional Neural Network, termed prediction model. We implement a noise model which aims to add as much noise as possible to the input without harming the performance of the prediction model. We test our method on 13,750 3D brain MR images from the UK Biobank, and our findings are consistent with the existing neuropathology literature.
  arXiv  Detail & Related papers  (2021-08-11T18:08:09Z)
• Brain Age Estimation From MRI Using Cascade Networks with Ranking Loss [75.03117866578913]
  A novel 3D convolutional network, called two-stage-age-network (TSAN), is proposed to estimate brain age from T1-weighted MRI data. Experiments with $6586$ MRIs showed that TSAN could provide accurate brain age estimation.
  arXiv  Detail & Related papers  (2021-06-06T07:11:25Z)
• Uncertainty-Based Biological Age Estimation of Brain MRI Scans [10.670209276046915]
  We propose a new framework for organ-specific BA estimation utilizing 3D magnetic resonance image (MRI) scans. We demonstrate the correlation between the predicted BAs and the expected cognitive deterioration in Alzheimer's patients.
  arXiv  Detail & Related papers  (2021-03-15T16:08:23Z)
• Patch-based Brain Age Estimation from MR Images [64.66978138243083]
  Brain age estimation from Magnetic Resonance Images (MRI) derives the difference between a subject's biological brain age and their chronological age. Early detection of neurodegeneration manifesting as a higher brain age can potentially facilitate better medical care and planning for affected individuals. We develop a new deep learning approach that uses 3D patches of the brain as well as convolutional neural networks (CNNs) to develop a localised brain age estimator.
  arXiv  Detail & Related papers  (2020-08-29T11:50:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.