Log In Sign Up
Models:
Tobias Harvey
tobiasharvey/
dynamic
0
Downloads: 1
Diff of /README.md [aeb6cc] .. [9f3905]

Switch to unified view

a/README.md b/README.md 
...
 
...
6 
  2) prediction of ejection fraction by entire video or subsampled clips, and
 6 
  2) prediction of ejection fraction by entire video or subsampled clips, and
7 
  3) assessment of cardiomyopathy with reduced ejection fraction.
 7 
  3) assessment of cardiomyopathy with reduced ejection fraction.
8 

  8
  





  9
  
For more details, see the accompanying paper,

  9
  
For more details, see the accompanying paper,





  10
  

  10
  





  11
  
> [**Video-based AI for beat-to-beat assessment of cardiac function**](https://www.nature.com/articles/s41586-020-2145-8)<br/>

  11
  
 [**Video-based AI for beat-to-beat assessment of cardiac function**](https://www.nature.com/articles/s41586-020-2145-8)<br/>





  12
  
  David Ouyang, Bryan He, Amirata Ghorbani, Neal Yuan, Joseph Ebinger, Curt P. Langlotz, Paul A. Heidenreich, Robert A. Harrington, David H. Liang, Euan A. Ashley, and James Y. Zou. <b>Nature</b>, March 25, 2020. https://doi.org/10.1038/s41586-020-2145-8

  12
  
  David Ouyang, Bryan He, Amirata Ghorbani, Neal Yuan, Joseph Ebinger, Curt P. Langlotz, Paul A. Heidenreich, Robert A. Harrington, David H. Liang, Euan A. Ashley, and James Y. Zou. <b>Nature</b>, March 25, 2020. https://doi.org/10.1038/s41586-020-2145-8





  13
  

  13
  





  14
  
Dataset

  14
  
Dataset





  15
  
-------

  15
  
-------





  16
  
We share a deidentified set of 10,030 echocardiogram images which were used for training EchoNet-Dynamic.

  16
  
We share a deidentified set of 10,030 echocardiogram images which were used for training EchoNet-Dynamic.





  17
  
Preprocessing of these images, including deidentification and conversion from DICOM format to AVI format videos, were performed with OpenCV and pydicom. Additional information is at https://echonet.github.io/dynamic/. These deidentified images are shared with a non-commerical data use agreement.

  17
  
Preprocessing of these images, including deidentification and conversion from DICOM format to AVI format videos, were performed with OpenCV and pydicom. Additional information is at https://echonet.github.io/dynamic/. These deidentified images are shared with a non-commerical data use agreement.





  18
  

  18
  





  19
  
Examples

  
  





  20
  
--------

  
  





  21
  

  
  





  22
  
We show examples of our semantic segmentation for nine distinct patients below.

  
  





  23
  
Three patients have normal cardiac function, three have low ejection fractions, and three have arrhythmia.

  
  





  24
  
No human tracings for these patients were used by EchoNet-Dynamic.

  
  





  25
  

  
  





  26
  
| Normal                                 | Low Ejection Fraction                  | Arrhythmia                             |

  
  





  27
  
| ------                                 | ---------------------                  | ----------                             |

  
  





  28
  
| ![](docs/media/0X10A28877E97DF540.gif) | ![](docs/media/0X129133A90A61A59D.gif) | ![](docs/media/0X132C1E8DBB715D1D.gif) |

  
  





  29
  
| ![](docs/media/0X1167650B8BEFF863.gif) | ![](docs/media/0X13CE2039E2D706A.gif ) | ![](docs/media/0X18BA5512BE5D6FFA.gif) |

  
  





  30
  
| ![](docs/media/0X148FFCBF4D0C398F.gif) | ![](docs/media/0X16FC9AA0AD5D8136.gif) | ![](docs/media/0X1E12EEE43FD913E5.gif) |

  
  





  31
  

  19
  





  32
  
Installation

  20
  
Installation





  33
  
------------

  21
  
------------





  34
  

  22
  





  35
  
First, clone this repository and enter the directory by running:

  23
  
First, clone this repository and enter the directory by running: