# CardioBench: Do Echocardiography Foundation Models Generalize Beyond the Lab?

arXiv: https://arxiv.org/abs/2510.00520 · HTML: https://mlsanity.com/paper/2510.00520/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 38 references that are in the map.
- First posted on arXiv 1 Oct 2025.

## Builds on (most cited first, 23 of 23)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison](https://mlsanity.com/paper/1901.07031/) (2019)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features](https://mlsanity.com/paper/2502.14786/) (2025)
- [Grounded Language-Image Pre-training](https://mlsanity.com/paper/2112.03857/) (2021)
- [FLAVA: A Foundational Language And Vision Alignment Model](https://mlsanity.com/paper/2112.04482/) (2021)
- [BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs](https://mlsanity.com/paper/2303.00915/) (2023)
- [Scaling Open-Vocabulary Image Segmentation with Image-Level Labels](https://mlsanity.com/paper/2112.12143/) (2021)
- [Deep Learning for Segmentation using an Open Large-Scale Dataset in 2D Echocardiography](https://mlsanity.com/paper/1908.06948/) (2019)
- [MedNeXt: Transformer-driven Scaling of ConvNets for Medical Image Segmentation](https://mlsanity.com/paper/2303.09975/) (2023)
- [STU-Net: Scalable and Transferable Medical Image Segmentation Models Empowered by Large-Scale Supervised Pre-training](https://mlsanity.com/paper/2304.06716/) (2023)
- [A Closer Look at the Few-Shot Adaptation of Large Vision-Language Models](https://mlsanity.com/paper/2312.12730/) (2023)
- [FairMedFM: Fairness Benchmarking for Medical Imaging Foundation Models](https://mlsanity.com/paper/2407.00983/) (2024)
- [Are Natural Domain Foundation Models Useful for Medical Image Classification?](https://mlsanity.com/paper/2310.19522/) (2023)
- [High-Throughput Precision Phenotyping of Left Ventricular Hypertrophy with Cardiovascular Deep Learning](https://mlsanity.com/paper/2106.12511/) (2021)
- [Touchstone Benchmark: Are We on the Right Way for Evaluating AI Algorithms for Medical Segmentation?](https://mlsanity.com/paper/2411.03670/) (2024)
- [Early Detection of Myocardial Infarction in Low-Quality Echocardiography](https://mlsanity.com/paper/2010.02281/) (2020)
- [EchoPrime: A Multi-Video View-Informed Vision-Language Model for Comprehensive Echocardiography Interpretation](https://mlsanity.com/paper/2410.09704/) (2024)
- [EchoFM: Foundation Model for Generalizable Echocardiogram Analysis](https://mlsanity.com/paper/2410.23413/) (2024)
- [CardiacNet: Learning to Reconstruct Abnormalities for Cardiac Disease Assessment from Echocardiogram Videos](https://mlsanity.com/paper/2410.20769/) (2024)
- [Multimodal Foundation Models For Echocardiogram Interpretation](https://mlsanity.com/paper/2308.15670/) (2023)

## Built on by (most cited first, 1 of 1)

- [Wrong Organ, Right Physics: Transferring Echocardiography Pretraining to Lung Ultrasound for Tuberculosis Screening](https://mlsanity.com/paper/2610.03290/) (2026)

## Abstract (arXiv)

Foundation models are reshaping medical imaging, yet their application in echocardiography remains limited, hindered by a heavy reliance on private datasets that prevent reproducible comparison. Echocardiography poses unique challenges, including noisy acquisitions, high frame redundancy, and limited diverse public datasets. To address this, we introduce CardioBench, a comprehensive benchmark for echocardiography foundation models. Specifically, CardioBench unifies eight publicly available datasets into a standardized suite spanning four regression and five classification tasks, covering functional, structural, diagnostic, and view recognition endpoints. Leveraging this framework, we evaluate several leading foundation models, including cardiac-specific, biomedical, and general-purpose encoders, under consistent zero-shot, probing, and alignment protocols. Our analysis reveals that while general-purpose encoders transfer well and often close the gap with probing, they struggle significantly with fine-grained distinctions like view classification and subtle pathology recognition. Results indicate that models capturing temporal cardiac dynamics perform best on functional tasks, while retrieval-based approaches generalize more consistently across datasets. By releasing preprocessing, splits, and public evaluation pipelines, CardioBench establishes a reproducible reference point to guide the architectural design of future echocardiography and possibly other medical imaging foundation models.