---
license: cc-by-4.0
language:
- en
tags:
- ecg
- student-teacher
- echocardiograms
---
# EchoingECG (MICCAI 2025)

EchoingECG is a probabilistic student-teacher model designed to improve cardiac function prediction from electrocardiograms (ECGs) by distilling knowledge from echocardiograms (ECHO). This approach leverages uncertainty-aware ECG embeddings and ECHO supervision, integrating Probabilistic Cross-Modal Embeddings (PCME++) and ECHO-CLIP, a vision-language pretrained model, to transfer ECHO knowledge into ECG representations.

Please refer to our github for use: https://github.com/mcintoshML/EchoingECG

![EchoingECG Overview](assets/fig1_overview.png)

## Installation
Clone the repository and install dependencies:
```bash
git clone https://github.com/mcintoshML/EchoingECG.git
cd EchoingECG
pip install -r requirements.txt
```

## Citation
If you use EchoingECG in your research, please cite:
```
@InProceedings{GaoYua_EchoingECG_MICCAI2025,
        author = { Gao, Yuan and Kim, Sangwook and McIntosh, Chris},
        title = { { EchoingECG: An Electrocardiogram Cross-Modal Model for Echocardiogram Tasks } },
        booktitle = {proceedings of Medical Image Computing and Computer Assisted Intervention -- MICCAI 2025},
        year = {2025},
        publisher = {Springer Nature Switzerland},
        volume = {LNCS 15964},
        month = {September},
        page = {175 -- 185}
}
```