# BrainNorm: A Foundation Model that knows Normal via Semantic Atlas Pretraining

arXiv: https://arxiv.org/abs/2608.17521 · HTML: https://mlsanity.com/paper/2608.17521/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 73 references that are in the map.
- First posted on arXiv 18 Aug 2026.

## Builds on (most cited first, 24 of 24)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture](https://mlsanity.com/paper/2301.08243/) (2023)
- [MedCLIP: Contrastive Learning from Unpaired Medical Images and Text](https://mlsanity.com/paper/2210.10163/) (2022)
- [Revisiting Feature Prediction for Learning Visual Representations from Video](https://mlsanity.com/paper/2404.08471/) (2024)
- [MedGemma Technical Report](https://mlsanity.com/paper/2507.05201/) (2025)
- [Med3D: Transfer Learning for 3D Medical Image Analysis](https://mlsanity.com/paper/1904.00625/) (2019)
- [Learning to Exploit Temporal Structure for Biomedical Vision-Language Processing](https://mlsanity.com/paper/2301.04558/) (2023)
- [SynthStrip: Skull-Stripping for Any Brain Image](https://mlsanity.com/paper/2203.09974/) (2022)
- [Fast Unsupervised Brain Anomaly Detection and Segmentation with Diffusion Models](https://mlsanity.com/paper/2206.03461/) (2022)
- [Unsupervised Anomaly Localization using Variational Auto-Encoders](https://mlsanity.com/paper/1907.02796/) (2019)
- [Predicting brain age with deep learning from raw imaging data results in a reliable and heritable biomarker](https://mlsanity.com/paper/1612.02572/) (2016)
- [Learning Conditional Deformable Templates with Convolutional Networks](https://mlsanity.com/paper/1908.02738/) (2019)
- [Contrastive Learning with Continuous Proxy Meta-Data for 3D MRI Classification](https://mlsanity.com/paper/2106.08808/) (2021)
- [Enhancing Spatiotemporal Disease Progression Models via Latent Diffusion and Prior Knowledge](https://mlsanity.com/paper/2405.03328/) (2024)
- [Longitudinal Self-Supervised Learning](https://mlsanity.com/paper/2006.06930/) (2020)
- [Multi-modal Vision Pre-training for Medical Image Analysis](https://mlsanity.com/paper/2410.10604/) (2024)
- [Brain Harmony: A Multimodal Foundation Model Unifying Morphology and Function into 1D Tokens](https://mlsanity.com/paper/2509.24693/) (2025)
- [A model of brain morphological changes related to aging and Alzheimer's disease from cross-sectional assessments](https://mlsanity.com/paper/1905.09826/) (2019)
- [Learning Sparse Latent Predictive Foundation Model for Multimodal Neuroimaging](https://mlsanity.com/paper/2606.14957/) (2026)
- [A deformation-based morphometry framework for disentangling Alzheimer's disease from normal aging using learned normal aging templates](https://mlsanity.com/paper/2311.08176/) (2023)
- [Parcel2Progression: An Anatomy-aware Longitudinal Framework for Alzheimer's Disease Diagnosis](https://mlsanity.com/paper/2608.08753/) (2026)

## Abstract (arXiv)

We introduce BrainNorm, a normative foundation model, trained and tested on ~66,000 T1-weighted structural MRI (T1w sMRI) scans. By leveraging language-image style contrastive pretraining on healthy cohorts across ages, BrainNorm learns a Semantic Atlas Latent space (SAL), where each scan is represented as a set of atlas-parcel embeddings. This yields parcel-specific healthy aging template trajectories that support age-consistent template matching and localized deviation scoring relative to a subject's chronological age. Across 6 downstream cohorts, BrainNorm demonstrates generalization evaluated across 25 task-setting combinations spanning age estimation, brain-age gap estimation, parcel identification, and single- & multi-disease classification tasks under direct inference, zero-shot, few-shot & full-data linear-probe settings. The resulting deviation patterns in SAL space enable zero-shot tasks for disease prediction using parcel-wise abnormalities. Fine-tuning on healthy-only cohorts of downstream datasets further improves the performance of various tasks. Across all classification tasks, linear probing on BrainNorm's frozen embeddings outperforms 9 baselines finetuned under end-to-end supervision. Furthermore, the localized deviations identified by BrainNorm across various neurodegenerative disorders closely align with established neurodegeneration pathology in clinical literature.