README.md 10.9 KB
Newer Older
1 2
# COVID-Net Open Source Initiative

3 4
**Note: The COVID-Net models provided here are intended to be used as reference models that can be built upon and enhanced as new data becomes available. They are currently at a research stage and not yet intended as production-ready models (not meant for direct clinicial diagnosis), and we are working continuously to improve them as new data becomes available. Please do not use COVID-Net for self-diagnosis and seek help from your local health authorities.**

lindawangg's avatar
lindawangg committed
5
<p align="center">
6
	<img src="assets/covidnet-small-exp.png" alt="photo not available" width="70%" height="70%">
lindawangg's avatar
lindawangg committed
7 8 9
	<br>
	<em>Example chest radiography images of COVID-19 cases from 2 different patients and their associated critical factors (highlighted in red) as identified by GSInquire.</em>
</p>
lindawangg's avatar
test  
lindawangg committed
10

11
**Core COVID-Net team: Linda Wang, Alexander Wong, Zhong Qiu Lin, James Lee, Paul McInnis**
12 13
Vision and Image Processing Research Group, University of Waterloo, Canada
DarwinAI Corp., Canada
14

15
The COVID-19 pandemic continues to have a devastating effect on the health and well-being of the global population.  A critical step in the fight against COVID-19 is effective screening of infected patients, with one of the key screening approaches being radiological imaging using chest radiography.  It was found in early studies that patients present abnormalities in chest radiography images that are characteristic of those infected with COVID-19.  Motivated by this, a number of artificial intelligence (AI) systems based on deep learning have been proposed and results have been shown to be quite promising in terms of accuracy in detecting patients infected with COVID-19 using chest radiography images.  However, to the best of the authors' knowledge, these developed AI systems have been closed source and unavailable to the research community for deeper understanding and extension, and unavailable for public access and use.  Therefore, in this study we introduce COVID-Net, a deep convolutional neural network design tailored for the detection of COVID-19 cases from chest radiography images that is open source and available to the general public.  We also describe the chest radiography dataset leveraged to train COVID-Net, which we will refer to as COVIDx and is comprised of 16,756 chest radiography images across 13,645 patient cases from two open access data repositories.  Furthermore, we investigate how COVID-Net makes predictions using an explainability method in an attempt to gain deeper insights into critical factors associated with COVID cases, which can aid clinicians in improved screening. **By no means a production-ready solution**, the hope is that the open access COVID-Net, along with the description on constructing the open source COVIDx dataset, will be leveraged and build upon by both researchers and citizen data scientists alike to accelerate the development of highly accurate yet practical deep learning solutions for detecting COVID-19 cases and accelerate treatment of those who need it the most.
lindawangg's avatar
lindawangg committed
16

17 18 19
For a detailed description of the methodology behind COVID-Net and a full description of the COVIDx dataset, please click [here](assets/COVID_Netv2.pdf).

Currently, the COVID-Net team is working on COVID-RiskNet, a deep neural network tailored for COVID-19 risk stratification.  Stay tuned as we make it available soon.
lindawangg's avatar
lindawangg committed
20

lindawangg's avatar
lindawangg committed
21 22
If you would like to contribute COVID-19 x-ray images, please contact us at linda.wang513@gmail.com and a28wong@uwaterloo.ca or alex@darwinai.ca. Lets all work together to stop the spread of COVID-19!

lindawangg's avatar
lindawangg committed
23
If you are a researcher or healthcare worker and you would like access to the GSInquire tool to use to interpret COVID-Net results on your data or existing data, please reach out to a28wong@uwaterloo.ca or alex@darwinai.ca
lindawangg's avatar
lindawangg committed
24

lindawangg's avatar
lindawangg committed
25 26
Our desire is to encourage broad adoption and contribution to this project. Accordingly this project has been licensed under the GNU Affero General Public License 3.0. Please see [license file](LICENSE.md) for terms. If you would like to discuss alternative licensing models, please reach out to us at: linda.wang513@gmail.com and a28wong@uwaterloo.ca or alex@darwinai.ca.

Desmond Lin's avatar
Desmond Lin committed
27 28 29 30
If there are any technical questions, please contact:
* desmond.zq.lin@gmail.com
* paul@darwinai.ca
* jamesrenhoulee@gmail.com
lindawangg's avatar
lindawangg committed
31

lindawangg's avatar
lindawangg committed
32 33 34 35 36 37 38 39 40 41 42 43 44
If you find our work useful, can cite our paper using:

```
@misc{wang2020covidnet,
    title={COVID-Net: A Tailored Deep Convolutional Neural Network Design for Detection of COVID-19 Cases from Chest Radiography Images},
    author={Linda Wang and Alexander Wong},
    year={2020},
    eprint={2003.09871},
    archivePrefix={arXiv},
    primaryClass={cs.CV}
}
```

lindawangg's avatar
lindawangg committed
45
## Requirements
46 47 48

The main requirements are listed below:

lindawangg's avatar
lindawangg committed
49 50
* Tested with Tensorflow 1.13 and 1.15
* OpenCV 4.2.0
lindawangg's avatar
lindawangg committed
51
* Python 3.6
52
* Numpy
53
* OpenCV
54 55 56 57 58
* Scikit-Learn
* Matplotlib

Additional requirements to generate dataset:

59
* PyDicom
60 61
* Pandas
* Jupyter
lindawangg's avatar
lindawangg committed
62

lindawangg's avatar
lindawangg committed
63
## COVIDx Dataset
64

lindawangg's avatar
lindawangg committed
65
**Update: we have released the brand-new COVIDx dataset with 16,756 chest radiography images across 13,645 patient cases.**
66 67

The current COVIDx dataset is constructed by the following open source chest radiography datasets:
lindawangg's avatar
lindawangg committed
68
* https://github.com/ieee8023/covid-chestxray-dataset
69 70 71 72 73
* https://www.kaggle.com/c/rsna-pneumonia-detection-challenge

We especially thank the Radiological Society of North America and others involved in the RSNA Pneumonia Detection Challenge, and Dr. Joseph Paul Cohen and the team at MILA involved in the COVID-19 image data collection project, for making data available to the global community.

### Steps to generate the dataset
lindawangg's avatar
lindawangg committed
74

75 76 77 78 79 80 81 82
1. Download the datasets listed above
 * `git clone https://github.com/ieee8023/covid-chestxray-dataset.git`
 * go to this [link](https://www.kaggle.com/c/rsna-pneumonia-detection-challenge/data) to download the RSNA pneumonia dataset
2. Create a `data` directory and within the data directory, create a `train` and `test` directory
3. Use [create\_COVIDx\_v2.ipynb](create_COVIDx_v2.ipynb) to combine the two dataset to create COVIDx. Make sure to remember to change the file paths.
4. We provide the train and test txt files with patientId, image path and label (normal, pneumonia or COVID-19). The description for each file is explained below:
 * [train\_COVIDx.txt](train_COVIDx.txt): This file contains the samples used for training.
 * [test\_COVIDx.txt](test_COVIDx.txt): This file contains the samples used for testing.
lindawangg's avatar
lindawangg committed
83

84
### COVIDx data distribution
lindawangg's avatar
readme  
lindawangg committed
85

lindawangg's avatar
lindawangg committed
86
Chest radiography images distribution
87 88
|  Type | Normal | Pneumonia | COVID-19 | Total |
|:-----:|:------:|:---------:|:--------:|:-----:|
lindawangg's avatar
lindawangg committed
89
| train |  7966  |    8514   |    66    | 16546 |
90
|  test |   100  |     100   |    10    |   210 |
lindawangg's avatar
stats  
lindawangg committed
91

lindawangg's avatar
lindawangg committed
92
Patients distribution
93 94 95
|  Type | Normal | Pneumonia | COVID-19 |  Total |
|:-----:|:------:|:---------:|:--------:|:------:|
| train |  7966  |    5429   |    48    |  13443 |
96
|  test |   100  |      98   |     5    |    203 |
lindawangg's avatar
readme  
lindawangg committed
97

lindawangg's avatar
lindawangg committed
98
## Training and Evaluation
99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119
The network takes as input an image of shape (N, 224, 224, 3) and outputs the softmax probabilities as (N, 3), where N is the number of batches.
If using the TF checkpoints, here are some useful tensors:

* input tensor: `input_1:0`
* output tensor: `dense_3/Softmax:0`
* label tensor: `dense_3_target:0`
* class weights tensor: `dense_3_sample_weights:0`
* loss tensor: `loss/mul:0`

### Steps for training
Releasing TF training script from pretrained model soon.
<!--1. To train from scratch, `python train.py`
2. To train from an existing hdf5 file, `python train.py --checkpoint output/example/cp-0.hdf5`
3. For more options and information, `python train.py --help`
4. If you have a GenSynth account, to convert hdf5 file to TF checkpoints,
`python export_to_meta.py --weightspath output/example --weightspath cp-0.hdf5`-->  

### Steps for evaluation

1. We provide you with the tensorflow evaluation script, [eval.py](eval.py)
2. Locate the tensorflow checkpoint files
120
3. To evaluate a tf checkpoint, `python eval.py --weightspath models/COVID-Netv2 --metaname model.meta_eval --ckptname model-2069`
121
4. For more options and information, `python eval.py --help`
122

123
### Steps for inference
124 125 126 127 128 129
**DISCLAIMER: Do not use this prediction for self-diagnosis. You should check with your local authorities for the latest advice on seeking medical assistance.**

1. Download a model from the [pretrained models section](#pretrained-models)
2. Locate models and xray image to be inferenced
3. To inference, `python inference.py --weightspath models/COVID-Netv2 --metaname model.meta_eval --ckptname model-2069 --imagepath assets/ex-covid.jpeg`
4. For more options and information, `python inference.py --help`
lindawangg's avatar
lindawangg committed
130

131 132
## Results
These are the final results for COVID-Net Small and COVID-Net Large.   
lindawangg's avatar
lindawangg committed
133

134 135 136 137 138 139
### COVIDNet Small
<p align="center">
	<img src="assets/cm-covidnet-small.png" alt="photo not available" width="50%" height="50%">
	<br>
	<em>Confusion matrix for COVID-Net on the COVIDx test dataset.</em>
</p>
lindawangg's avatar
lindawangg committed
140

141 142 143 144 145 146 147 148 149 150 151 152 153 154 155
<div class="tg-wrap" align="center"><table class="tg">
  <tr>
    <th class="tg-7btt" colspan="3">Sensitivity (%)</th>
  </tr>
  <tr>
    <td class="tg-7btt">Normal</td>
    <td class="tg-7btt">Pneumonia</td>
    <td class="tg-7btt">COVID-19</td>
  </tr>
  <tr>
    <td class="tg-c3ow">95.0</td>
    <td class="tg-c3ow">91.0</td>
    <td class="tg-c3ow">80.0</td>
  </tr>
</table></div>
lindawangg's avatar
lindawangg committed
156

157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173
<div class="tg-wrap"><table class="tg">
  <tr>
    <th class="tg-7btt" colspan="3">Positive Predictive Value (%)</th>
  </tr>
  <tr>
    <td class="tg-7btt">Normal</td>
    <td class="tg-7btt">Pneumonia</td>
    <td class="tg-7btt">COVID-19</td>
  </tr>
  <tr>
    <td class="tg-c3ow">91.3</td>
    <td class="tg-c3ow">93.8</td>
    <td class="tg-c3ow">88.9</td>
  </tr>
</table></div>

### COVID-Net Large
lindawangg's avatar
lindawangg committed
174
<p align="center">
175
	<img src="assets/cm-covidnet-large.png" alt="photo not available" width="50%" height="50%">
lindawangg's avatar
lindawangg committed
176 177 178 179
	<br>
	<em>Confusion matrix for COVID-Net on the COVIDx test dataset.</em>
</p>

lindawangg's avatar
lindawangg committed
180
<div class="tg-wrap" align="center"><table class="tg">
lindawangg's avatar
lindawangg committed
181
  <tr>
182
    <th class="tg-7btt" colspan="3">Sensitivity (%)</th>
lindawangg's avatar
lindawangg committed
183 184 185
  </tr>
  <tr>
    <td class="tg-7btt">Normal</td>
186 187
    <td class="tg-7btt">Pneumonia</td>
    <td class="tg-7btt">COVID-19</td>
lindawangg's avatar
lindawangg committed
188 189
  </tr>
  <tr>
190 191 192
    <td class="tg-c3ow">94.0</td>
    <td class="tg-c3ow">90.0</td>
    <td class="tg-c3ow">90.0</td>
lindawangg's avatar
lindawangg committed
193 194 195 196 197
  </tr>
</table></div>

<div class="tg-wrap"><table class="tg">
  <tr>
198
    <th class="tg-7btt" colspan="3">Positive Predictive Value (%)</th>
lindawangg's avatar
lindawangg committed
199 200 201
  </tr>
  <tr>
    <td class="tg-7btt">Normal</td>
202 203
    <td class="tg-7btt">Pneumonia</td>
    <td class="tg-7btt">COVID-19</td>
lindawangg's avatar
lindawangg committed
204 205
  </tr>
  <tr>
206 207 208
    <td class="tg-c3ow">90.4</td>
    <td class="tg-c3ow">93.8</td>
    <td class="tg-c3ow">90.0</td>
lindawangg's avatar
lindawangg committed
209 210 211
  </tr>
</table></div>

lindawangg's avatar
lindawangg committed
212
## Pretrained Models
213

lindawangg's avatar
lindawangg committed
214 215
|  Type | COVID-19 Sensitivity | # Params (M) | MACs (G) |        Model        |
|:-----:|:--------------------:|:------------:|:--------:|:-------------------:|
lindawangg's avatar
lindawangg committed
216 217
|  ckpt |         80.0         |     116.6    |   2.26   |[COVID-Net Small](https://drive.google.com/file/d/1xrxK9swFVlFI-WAYcccIgm0tt9RgawXD/view?usp=sharing)|
|  ckpt |         90.0         |     126.6    |   3.59   |[COVID-Net Large](https://drive.google.com/file/d/1djqWcxzRehtyJV9EQsppj1YdgsP2JRQy/view?usp=sharing)|