# AG-JEPA: Anatomically Guided Joint Embedding Predictive Architecture for Neurodegenerative Representation Learning

DevFeed: [AG-JEPA: Anatomically Guided Joint Embedding Predictive Architecture for Neurodegenerative Representation Learning](<https://devfeed.tech/articles/ag-jepa-anatomically-guided-joint-embedding-predictive-architecture-for-neurodegenerative-representation-learning-135165.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.18097>)

Author: Azad Singh, Ayantika Das, Amog Rao, Aiman Farooq, Anirban Porya, Ananya Shukla, Sowbhagya Suresh, Srinivasan Iyengar, Mohit Jain, Mercy Prasanna Ranjit

Published: 2026-11-16T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Representation learning](<https://devfeed.tech/topics/representation-learning.md>), [model architecture](<https://devfeed.tech/topics/model-architecture.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Predictive AI](<https://devfeed.tech/topics/predictive-ai.md>)

Tags: [architecture](<https://devfeed.tech/tags/architecture.md>), [brain](<https://devfeed.tech/tags/brain.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [diagnosis](<https://devfeed.tech/tags/diagnosis.md>), [modeling](<https://devfeed.tech/tags/modeling.md>), [prediction](<https://devfeed.tech/tags/prediction.md>), [representation-learning](<https://devfeed.tech/tags/representation-learning.md>)

## AI overview

AG-JEPA adds anatomical tokens that interact with MRI patch tokens during pretraining, aiming to learn region-specific representations of brain areas relevant to neurodegeneration. Prog-AG-JEPA builds on these representations by modeling disease progression as a conditioned displacement in latent space. Across five diagnosis and progression tasks, AG-JEPA reportedly improves CN/MCI classification AUROC by 8.4 percentage points over the strongest baseline and out-of-distribution CN/AD classification AUROC by 7.1 points on MR-RATE. Prog-AG-JEPA also outperforms the reported baselines on future diagnosis and brain volume change prediction. The supplied abstract does not provide further methodological or evaluation details.

## Source excerpt

arXiv:2611.18097v1 Announce Type: cross Abstract: Brain MRI can reveal early signs of Alzheimers disease (AD) before measurable cognitive decline becomes apparent. However, during the transition from cognitively normal (CN) to mild cognitive impairment (MCI), the disease-related signals are often subtle and confined to only a few brain regions. Existing Joint Embedding Predictive Architecture (JEPA) models learn general structural representations but do not explicitly capture the anatomical regions affected in AD. We propose Anatomically Guided JEPA (AG-JEPA), which introduces anatomical tokens that interact with patch tokens during pretraining to learn region-specific representations from brain regions relevant to neurodegeneration. Building on this representation space, we further propose Prog-AG-JEPA, which models disease progression trajectory as a conditioned latent displacement within this space. We evaluate AG-JEPA across five downstream tasks spanning Alzheimer's disease diagnosis and progression prediction. AG-JEPA improves diagnosis and MCI prognosis, achieving an 8.4 percentage point AUROC gain over the strongest baseline on CN/MCI classification and a 7.1 percentage point gain on out-of-distribution CN/AD classification on the MR-RATE dataset, highlighting its effectiveness across both early-stage detection and cross-cohort generalization. For disease progression modeling, Prog-AG-JEPA consistently outperforms all baselines on future diagnosis and brain volume change prediction, demonstrating the value of anatomically grounded neurodegeneration representations for diagnosis and prognosis.