README.md 13 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
**Update 04/15/2020: We released two new models, COVIDNet-CXR Small and COVIDNet-CXR Large, which were trained on a new COVIDx Dataset with both PA and AP X-Rays from Cohen et al, as well as additional COVID-19 X-Ray images from Figure1**
Linda Wang's avatar
Linda Wang committed
6
**Recording to webinar on [How we built COVID-Net in 7 days with Gensynth](https://darwinai.news/fny)**
lindawangg's avatar
lindawangg committed
7

lindawangg's avatar
lindawangg committed
8
<p align="center">
lindawangg's avatar
lindawangg committed
9
	<img src="assets/covidnet-cxr-small-exp.png" alt="photo not available" width="70%" height="70%">
lindawangg's avatar
lindawangg committed
10 11 12
	<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
13

lindawangg's avatar
lindawangg committed
14
**Core COVID-Net team: Linda Wang, Alexander Wong, Zhong Qiu Lin, James Lee, Paul McInnis, Audrey Chung, Matt Ross (City of London), Blake VanBerlo (City of London), Ashkan Ebadi (National Research Council Canada)**\
lindawangg's avatar
lindawangg committed
15
Vision and Image Processing Research Group, University of Waterloo, Canada\
16
DarwinAI Corp., Canada
17

lindawangg's avatar
lindawangg committed
18
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 13,800 chest radiography images across 13,725 patient patient cases from three 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
19

lindawangg's avatar
lindawangg committed
20
For a detailed description of the methodology behind COVID-Net and a full description of the COVIDx dataset, please click [here](https://arxiv.org/abs/2003.09871v3).
21

22
Currently, the COVID-Net team is working on **COVID-RiskNet**, a deep neural network tailored for COVID-19 risk stratification.  Currently this is available as a work-in-progress via included `train_risknet.py` script, help to contribute data and we can improve this tool.
lindawangg's avatar
lindawangg committed
23

24
If you would like to **contribute COVID-19 x-ray images**, please submit to https://figure1.typeform.com/to/lLrHwv. Lets all work together to stop the spread of COVID-19!
lindawangg's avatar
lindawangg committed
25

lindawangg's avatar
lindawangg committed
26
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
27

lindawangg's avatar
lindawangg committed
28
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
lindawangg's avatar
lindawangg committed
29

lindawangg's avatar
lindawangg committed
30 31 32 33 34 35 36 37
The README contains information about:
* [requirements](#requirements) to install on your system
* how to [generate COVIDx dataset](#covidx-dataset)
* steps for [training](#steps-for-training), [evaluation](#steps-for-evaluation) and [inference](#steps-for-inference)
* [results](#results)
* [links to pretrained models](#pretrained-models)

If there are any technical questions after the README and past/current issues have been read, please post an issue or contact:
Desmond Lin's avatar
Desmond Lin committed
38 39 40
* desmond.zq.lin@gmail.com
* paul@darwinai.ca
* jamesrenhoulee@gmail.com
lindawangg's avatar
lindawangg committed
41
* linda.wang513@gmail.com
lindawangg's avatar
lindawangg committed
42
* ashkan.ebadi@nrc-cnrc.gc.ca
lindawangg's avatar
lindawangg committed
43

lindawangg's avatar
lindawangg committed
44 45 46 47 48 49 50 51 52 53 54 55 56
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
57
## Requirements
58 59 60

The main requirements are listed below:

lindawangg's avatar
lindawangg committed
61 62
* Tested with Tensorflow 1.13 and 1.15
* OpenCV 4.2.0
lindawangg's avatar
lindawangg committed
63
* Python 3.6
64 65 66 67 68 69
* Numpy
* Scikit-Learn
* Matplotlib

Additional requirements to generate dataset:

70
* PyDicom
71 72
* Pandas
* Jupyter
lindawangg's avatar
lindawangg committed
73

lindawangg's avatar
lindawangg committed
74
## COVIDx Dataset
lindawangg's avatar
lindawangg committed
75
**Update 04/15/2020: Released new dataset with 152 COVID-19 train and 31 COVID-19 test samples. There are constantly new xray images being added to covid-chestxray-dataset and Figure1 covid dataset so we included train_COVIDx2.txt and test_COVIDx2.txt, which are the xray images we used for training and testing of the CovidNet-CXR models.**
76 77

The current COVIDx dataset is constructed by the following open source chest radiography datasets:
lindawangg's avatar
lindawangg committed
78
* https://github.com/ieee8023/covid-chestxray-dataset
lindawangg's avatar
lindawangg committed
79
* https://github.com/agchung/Figure1-COVID-chestxray-dataset
80
* https://www.kaggle.com/c/rsna-pneumonia-detection-challenge (which came from: https://nihcc.app.box.com/v/ChestXray-NIHCC)
81

lindawangg's avatar
lindawangg committed
82
We especially thank the Radiological Society of North America, National Institutes of Health, Figure1, 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.
83 84

### Steps to generate the dataset
lindawangg's avatar
lindawangg committed
85

86 87
1. Download the datasets listed above
 * `git clone https://github.com/ieee8023/covid-chestxray-dataset.git`
lindawangg's avatar
lindawangg committed
88
 * `git clone https://github.com/agchung/Figure1-COVID-chestxray-dataset`
89 90
 * 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
lindawangg's avatar
lindawangg committed
91
3. Use [create\_COVIDx\_v3.ipynb](create_COVIDx_v3.ipynb) to combine the three dataset to create COVIDx. Make sure to remember to change the file paths.
92
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:
lindawangg's avatar
lindawangg committed
93 94
 * [train\_COVIDx2.txt](train_COVIDx2.txt): This file contains the samples used for training COVIDNet-CXR.
 * [test\_COVIDx2.txt](test_COVIDx2.txt): This file contains the samples used for testing COVIDNet-CXR.
lindawangg's avatar
lindawangg committed
95

96
### COVIDx data distribution
lindawangg's avatar
readme  
lindawangg committed
97

lindawangg's avatar
lindawangg committed
98
Chest radiography images distribution
99 100
|  Type | Normal | Pneumonia | COVID-19 | Total |
|:-----:|:------:|:---------:|:--------:|:-----:|
lindawangg's avatar
lindawangg committed
101 102
| train |  7966  |    5451   |   152    | 13569 |
|  test |   100  |     100   |    31    |   231 |
lindawangg's avatar
stats  
lindawangg committed
103

lindawangg's avatar
lindawangg committed
104
Patients distribution
105 106
|  Type | Normal | Pneumonia | COVID-19 |  Total |
|:-----:|:------:|:---------:|:--------:|:------:|
lindawangg's avatar
lindawangg committed
107 108
| train |  7966  |    5440   |    107   |  13513 |
|  test |   100  |      98   |     14   |    212 |
lindawangg's avatar
readme  
lindawangg committed
109

lindawangg's avatar
lindawangg committed
110
## Training and Evaluation
111 112 113 114
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`
115
* logit tensor: `dense_3/MatMul:0`
116 117 118 119 120 121
* 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
122 123 124 125 126
TF training script from a pretrained model:
1. We provide you with the tensorflow evaluation script, [train_tf.py](train_tf.py)
2. Locate the tensorflow checkpoint files (location of pretrained model)
3. To train from a pretrained model, `python train_tf.py --weightspath models/COVIDNetv2 --metaname model.meta_train --ckptname model-2069`
4. For more options and information, `python train_tf.py --help`
127 128 129 130 131

### Steps for evaluation

1. We provide you with the tensorflow evaluation script, [eval.py](eval.py)
2. Locate the tensorflow checkpoint files
132
3. To evaluate a tf checkpoint, `python eval.py --weightspath models/COVID-Netv2 --metaname model.meta_eval --ckptname model-2069`
133
4. For more options and information, `python eval.py --help`
134

135
### Steps for inference
136 137 138 139
**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
lindawangg's avatar
lindawangg committed
140
3. To inference, `python inference.py --weightspath models/COVIDNet-CXR-Large --metaname model.meta_eval --ckptname model-8485 --imagepath assets/ex-covid.jpeg`
141
4. For more options and information, `python inference.py --help`
lindawangg's avatar
lindawangg committed
142

143 144 145 146 147 148 149
### Steps for Training COVIDNet-Risk

COVIDNet-Risk uses the same architecture as the existing COVIDNet - but instead it predicts the *"number of days since symptom onset"\** for a diagnosed COVID-19 patient based on their chest radiography (same data as COVIDNet). By performing offset stratification, we aim to provide an estimate of prognosis for the patient. Note that the initial dataset is fairly small at the time of writing and we hope to see more results as data increases.

1. Complete data creation and training for COVIDNet (see Training above)
2. run `train_risknet.py` (see `-h` for argument help)

150
*\* note that definition varies between data sources*
151

152
## Results
lindawangg's avatar
lindawangg committed
153
These are the final results for COVIDNet-CXR Small and COVIDNet-CXR Large.
lindawangg's avatar
lindawangg committed
154

lindawangg's avatar
lindawangg committed
155
### COVIDNet-CXR Small
156
<p align="center">
lindawangg's avatar
lindawangg committed
157
	<img src="assets/cm-covidnetcxr-small.png" alt="photo not available" width="50%" height="50%">
158
	<br>
lindawangg's avatar
lindawangg committed
159
	<em>Confusion matrix for COVIDNet-CXR Small on the COVIDx test dataset.</em>
160
</p>
lindawangg's avatar
lindawangg committed
161

162 163 164 165 166 167 168 169 170 171
<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>
lindawangg's avatar
lindawangg committed
172 173 174
    <td class="tg-c3ow">97.0</td>
    <td class="tg-c3ow">90.0</td>
    <td class="tg-c3ow">87.1</td>
175 176
  </tr>
</table></div>
lindawangg's avatar
lindawangg committed
177

lindawangg's avatar
lindawangg committed
178
<div class="tg-wrap" align="center"><table class="tg">
179 180 181 182 183 184 185 186 187
  <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>
lindawangg's avatar
lindawangg committed
188 189 190
    <td class="tg-c3ow">89.8</td>
    <td class="tg-c3ow">94.7</td>
    <td class="tg-c3ow">96.4</td>
191 192 193
  </tr>
</table></div>

lindawangg's avatar
lindawangg committed
194 195

### COVIDNet-CXR Large
lindawangg's avatar
lindawangg committed
196
<p align="center">
lindawangg's avatar
lindawangg committed
197
	<img src="assets/cm-covidnetcxr-large.png" alt="photo not available" width="50%" height="50%">
lindawangg's avatar
lindawangg committed
198
	<br>
lindawangg's avatar
lindawangg committed
199
	<em>Confusion matrix for COVIDNet-CXR Large on the COVIDx test dataset.</em>
lindawangg's avatar
lindawangg committed
200 201
</p>

lindawangg's avatar
lindawangg committed
202
<div class="tg-wrap" align="center"><table class="tg">
lindawangg's avatar
lindawangg committed
203
  <tr>
204
    <th class="tg-7btt" colspan="3">Sensitivity (%)</th>
lindawangg's avatar
lindawangg committed
205 206 207
  </tr>
  <tr>
    <td class="tg-7btt">Normal</td>
208 209
    <td class="tg-7btt">Pneumonia</td>
    <td class="tg-7btt">COVID-19</td>
lindawangg's avatar
lindawangg committed
210 211
  </tr>
  <tr>
lindawangg's avatar
lindawangg committed
212 213 214
    <td class="tg-c3ow">99.0</td>
    <td class="tg-c3ow">89.0</td>
    <td class="tg-c3ow">96.8</td>
lindawangg's avatar
lindawangg committed
215 216 217
  </tr>
</table></div>

lindawangg's avatar
lindawangg committed
218
<div class="tg-wrap" align="center"><table class="tg">
lindawangg's avatar
lindawangg committed
219
  <tr>
220
    <th class="tg-7btt" colspan="3">Positive Predictive Value (%)</th>
lindawangg's avatar
lindawangg committed
221 222 223
  </tr>
  <tr>
    <td class="tg-7btt">Normal</td>
224 225
    <td class="tg-7btt">Pneumonia</td>
    <td class="tg-7btt">COVID-19</td>
lindawangg's avatar
lindawangg committed
226 227
  </tr>
  <tr>
lindawangg's avatar
lindawangg committed
228 229 230
    <td class="tg-c3ow">91.7</td>
    <td class="tg-c3ow">98.9</td>
    <td class="tg-c3ow">90.9</td>
lindawangg's avatar
lindawangg committed
231 232 233
  </tr>
</table></div>

lindawangg's avatar
lindawangg committed
234
## Pretrained Models
235

lindawangg's avatar
lindawangg committed
236 237
|  Type | COVID-19 Sensitivity | # Params (M) | MACs (G) |        Model        |
|:-----:|:--------------------:|:------------:|:--------:|:-------------------:|
lindawangg's avatar
lindawangg committed
238
|  ckpt |         87.1         |     117.4    |   2.26   |[COVIDNet-CXR Small](https://bit.ly/CovidNet-CXR-Small)|
lindawangg's avatar
lindawangg committed
239
|  ckpt |         96.8         |     127.4    |   3.59   |[COVIDNet-CXR Large](https://bit.ly/CovidNet-CXR-Large)|