# EchoJEPA: A Latent Predictive Foundation Model for Echocardiography

arXiv: https://arxiv.org/abs/2602.02603 · HTML: https://mlsanity.com/paper/2602.02603/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 40 references that are in the map.
- First posted on arXiv 2 Feb 2026.

## Builds on (most cited first, 15 of 15)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training](https://mlsanity.com/paper/2203.12602/) (2022)
- [Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture](https://mlsanity.com/paper/2301.08243/) (2023)
- [V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning](https://mlsanity.com/paper/2506.09985/) (2025)
- [Albumentations: fast and flexible image augmentations](https://mlsanity.com/paper/1809.06839/) (2018)
- [Revisiting Feature Prediction for Learning Visual Representations from Video](https://mlsanity.com/paper/2404.08471/) (2024)
- [Self-supervised Co-training for Video Representation Learning](https://mlsanity.com/paper/2010.09709/) (2020)
- [Hidden Stratification Causes Clinically Meaningful Failures in Machine Learning for Medical Imaging](https://mlsanity.com/paper/1909.12475/) (2019)
- [BioReason: Incentivizing Multimodal Biological Reasoning within a DNA-LLM Model](https://mlsanity.com/paper/2505.23579/) (2025)
- [Revisiting Data Augmentation for Ultrasound Images](https://mlsanity.com/paper/2501.13193/) (2025)
- [Multimodal Foundation Models For Echocardiogram Interpretation](https://mlsanity.com/paper/2308.15670/) (2023)
- [An Investigation of Memorization Risk in Healthcare Foundation Models](https://mlsanity.com/paper/2510.12950/) (2025)
- [Self-supervised Learning of Echocardiographic Video Representations via Online Cluster Distillation](https://mlsanity.com/paper/2506.11777/) (2025)

## Built on by (most cited first, 13 of 13)

- [LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels](https://mlsanity.com/paper/2603.19312/) (2026)
- [Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application](https://mlsanity.com/paper/2606.12191/) (2026)
- [Learning Sparse Latent Predictive Foundation Model for Multimodal Neuroimaging](https://mlsanity.com/paper/2606.14957/) (2026)
- [Medical world models: representing medical states, modelling clinical dynamics and guiding intervention policies](https://mlsanity.com/paper/2606.16721/) (2026)
- [Medical world models in healthcare: foundations, applications, and challenges for trustworthy clinical translation](https://mlsanity.com/paper/2607.25242/) (2026)
- [Sonata: A Hybrid World Model for Inertial Kinematics under Clinical Data Scarcity](https://mlsanity.com/paper/2604.18058/) (2026)
- [Loud or Silent? A Reusable Framework for Per-Modality Failure Analysis in Multimodal Clinical AI](https://mlsanity.com/paper/2608.01462/) (2026)
- [EchoXFlow: A Beamspace Echocardiography Dataset for Cardiac Motion, Flow, and Function](https://mlsanity.com/paper/2605.05447/) (2026)
- [Cross-Modal Ultrasound-MRI Learning for Fetal Brain Ventricular Volumetry and Abnormality Screening](https://mlsanity.com/paper/2608.14763/) (2026)
- [The segmentation ceiling: why explicit left-ventricular masks do not improve learned ejection-fraction regression](https://mlsanity.com/paper/2609.19730/) (2026)
- [Wrong Organ, Right Physics: Transferring Echocardiography Pretraining to Lung Ultrasound for Tuberculosis Screening](https://mlsanity.com/paper/2610.03290/) (2026)
- [Ultrasound Operator Guidance Using World Modeling and Retrieval Based Action Planning](https://mlsanity.com/paper/2610.06008/) (2026)
- [EchoTab: Learning Measurement-Grounded Representations for Echocardiographic Diagnosis through Tabular Reconstruction](https://mlsanity.com/paper/2610.13599/) (2026)

## Abstract (arXiv)

Foundation models for echocardiography often struggle to disentangle anatomical signal from the stochastic speckle and acquisition artifacts inherent to ultrasound. We present EchoJEPA, a foundation model trained on 18 million echocardiograms across 300K patients, representing the largest pretraining corpus for this modality to date. By leveraging a latent predictive objective, EchoJEPA learns robust anatomical representations that ignore speckle noise. We validate this using a novel multi-view probing framework with frozen backbones, where EchoJEPA outperforms leading baselines by approximately 20% in left ventricular ejection fraction (LVEF) estimation and 17% in right ventricular systolic pressure (RVSP) estimation. The model also exhibits remarkable sample efficiency, reaching 79% view classification accuracy with only 1% of labeled data versus 42% for the best baseline trained on 100%. Crucially, EchoJEPA demonstrates superior generalization, degrading by only 2% under physics-informed acoustic perturbations compared to 17% for competitors. Most remarkably, its zero-shot performance on pediatric patients surpasses fully fine-tuned baselines, establishing latent prediction as a superior paradigm for robust, generalizable medical AI.