Unlimited 10-sec 8-leads Deep Fake ECG generator.
Project description
deepfake-ecg
Paper | GitHub | Pre-generated ECGs (150k)
Generate unlimited realistic deepfake ECGs using the deep generative model:Pulse2pulse introduced in our full paper here: https://doi.org/10.1101/2021.04.27.21256189 (DeepFake electrocardiograms: the key for open science for artificial intelligence in medicine)
Installation
Use the package manager pip to install deepfake-ecg generator.
pip install deepfake-ecg
Usage
The generator functions can generate DeepFake ECGs with 8-lead values [lead names from first coloum to eighth colum: 'I','II','V1','V2','V3','V4','V5','V6'] for 10s (5000 values per lead). These 8-leads format can be converted to 12-leads format using the following equations.
lead III value = (lead II value) - (lead I value)
lead aVR value = -0.5*(lead I value + lead II value)
lead aVL value = lead I value - 0.5 * lead II value
lead aVF value = lead II value - 0.5 * lead I value
Run on CPU (default setting)
import deepfakeecg
#deepfakeecg.generate("number of ECG to generate", "Path to generate", "start file ids from this number", "device to run")
deepfakeecg.generate(5, ".", start_id=0, run_device="cpu") # Generate 5 ECGs to the current folder starting from id=0
Run on GPU
import deepfakeecg
#deepfakeecg.generate("number of ECG to generate", "Path to generate", "start file ids from this number", "device to run")
deepfakeecg.generate(5, ".", start_id=0, run_device="cuda") # Generate 5 ECGs to the current folder starting from id=0
Pre-generated DeepFake ECGs and corresponding MUSE reports are here: https://osf.io/6hved/
- In this repository, there are two DeepFake datasets:
1. 150k dataset - Randomly generated 150k DeepFakeECGs
2. Filtered all normals dataset - Only "Normal" ECGs filtered using the MUSE analysis report
A real ECG vs a DeepFake ECG (from left to right):
A sample DeepFake ECG:
Contributing
Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.
Please make sure to update tests as appropriate.
Citation:
@article{ecg-pulse2pulse,
author = {Thambawita, Vajira Lasantha and Isaksen, Jonas L and Hicks, Steven and Ghouse, Jonas and Ahlberg, Gustav and Linneberg, Allan and Grarup, Niels and Ellervik, Christina and Olesen, Morten Salling and Hansen, Torben and Graff, Claus and Holstein-Rathlou, Niels-Henrik and Str{\"u}mke, Inga and Hammer, Hugo L. and Maleckar, Mary M and Halvorsen, P{\aa}l and Riegler, Michael A. and Kanters, J{\o}rgen K.},
doi = {10.1101/2021.04.27.21256189},
elocation-id = {2021.04.27.21256189},
journal = {medRxiv},
publisher = {Cold Spring Harbor Laboratory Press},
title = {DeepFake electrocardiograms: the key for open science for artificial intelligence in medicine},
url = {https://doi.org/10.1101/2021.04.27.21256189},
year = {2021}
}
License
For more details:
Please contact: vajira@simula.no, michael@simula.no
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for deepfake_ecg-1.1.2-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | dff913de571f9d92d95e25eed4a3fe7df0bfee7c66315ba1fa0687acdd11649c |
|
MD5 | 90e915b211a8f9503e9db22c2bf03769 |
|
BLAKE2b-256 | 36d406f4457cafcb4d3e57c5c98bc1a2a82ff0feac66286cd63ca3ad88c1d446 |