We are building an open database of COVID-19 cases with chest X-ray or CT images.

In this example, we use ONLY the XRs samples in the dataset labeled as COVID-19. We went the XRs way instead of the CTs since there are more of them. But I agree CTs are better for detection as mentioned here #5 .

The Neural Network source code is based in a post by Adrian Rosebrock in PyImageSearch.

Here, the dataset was divided into two labels: sicks and healthy. The healthy training samples were extracted from this Kaggle contest.

Then for training, we divide into two folders /dataset/sicks and /dataset/healthy, located in the root folder. Each class having the same number of images (around 90).

It's a preliminary approach that may improve substantially once the dataset grows enough.

from tensorflow.keras.preprocessing.image import ImageDataGenerator
from tensorflow.keras.applications import VGG16
from tensorflow.keras.layers import AveragePooling2D
from tensorflow.keras.layers import Dropout
from tensorflow.keras.layers import Flatten
from tensorflow.keras.layers import Dense
from tensorflow.keras.layers import Input
from tensorflow.keras.models import Model
from tensorflow.keras.optimizers import Adam
from tensorflow.keras.utils import to_categorical
from sklearn.preprocessing import LabelBinarizer
from sklearn.model_selection import train_test_split
from sklearn.metrics import classification_report
from sklearn.metrics import confusion_matrix
from imutils import paths
import matplotlib.pyplot as plt
import numpy as np
import cv2
import os
import lime
from lime import lime_image
from skimage.segmentation import mark_boundaries

plt.rcParams["figure.figsize"] = (20,10)

## global params
INIT_LR = 1e-4  # learning rate
EPOCHS = 21  # training epochs
BS = 8  # batch size


## load and prepare data
imagePaths = list(paths.list_images("dataset"))
data = []
labels = []
# loop over the image paths
for imagePath in imagePaths:
    # extract the class label from the filename
    label = imagePath.split(os.path.sep)[-2]
    # load the image, swap color channels, and resize it to be a fixed
    # 224x224 pixels while ignoring aspect ratio
    image = cv2.imread(imagePath)
    image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
    image = cv2.resize(image, (224, 224))
    # update the data and labels lists, respectively
    data.append(image)
    labels.append(label)
# convert the data and labels to NumPy arrays while scaling the pixel
# intensities to the range [0, 1]
data = np.array(data) / 255.0
labels = np.array(labels)

TEST_SET_SIZE = 0.2

lb = LabelBinarizer()
labels = lb.fit_transform(labels)
labels = to_categorical(labels); print(labels)
# partition the data into training and testing splits using 80% of
# the data for training and the remaining 20% for testing
(trainX, testX, trainY, testY) = train_test_split(data, labels,
    test_size=TEST_SET_SIZE, stratify=labels, random_state=42)
# initialize the training data augmentation object
trainAug = ImageDataGenerator(
    rotation_range=15,
    fill_mode="nearest")

## build network
baseModel = VGG16(weights="imagenet", include_top=False,
    input_tensor=Input(shape=(224, 224, 3)))
# construct the head of the model that will be placed on top of the
# the base model
headModel = baseModel.output
headModel = AveragePooling2D(pool_size=(4, 4))(headModel)
headModel = Flatten(name="flatten")(headModel)
headModel = Dense(64, activation="relu")(headModel)
headModel = Dropout(0.5)(headModel)
headModel = Dense(2, activation="softmax")(headModel)
# place the head FC model on top of the base model (this will become
# the actual model we will train)
model = Model(inputs=baseModel.input, outputs=headModel)
# loop over all layers in the base model and freeze them so they will
# *not* be updated during the first training process
for layer in baseModel.layers:
    layer.trainable = False

print("[INFO] compiling model...")
opt = Adam(lr=INIT_LR, decay=INIT_LR / EPOCHS)
model.compile(loss="binary_crossentropy", optimizer=opt,
    metrics=["accuracy"])

## train
print("[INFO] training head...")
H = model.fit_generator(
    trainAug.flow(trainX, trainY, batch_size=BS),
    steps_per_epoch=len(trainX) // BS,
    validation_data=(testX, testY),
    validation_steps=len(testX) // BS,
    epochs=EPOCHS)

print("[INFO] saving COVID-19 detector model...")
model.save("covid19.model", save_format="h5")

## eval
print("[INFO] evaluating network...")
predIdxs = model.predict(testX, batch_size=BS)
predIdxs = np.argmax(predIdxs, axis=1) # argmax for the predicted probability
print(classification_report(testY.argmax(axis=1), predIdxs,
    target_names=lb.classes_))

cm = confusion_matrix(testY.argmax(axis=1), predIdxs)
total = sum(sum(cm))
acc = (cm[0, 0] + cm[1, 1]) / total
sensitivity = cm[0, 0] / (cm[0, 0] + cm[0, 1])
specificity = cm[1, 1] / (cm[1, 0] + cm[1, 1])
# show the confusion matrix, accuracy, sensitivity, and specificity
print(cm)
print("acc: {:.4f}".format(acc))
print("sensitivity: {:.4f}".format(sensitivity))
print("specificity: {:.4f}".format(specificity))


## explain
N = EPOCHS
plt.style.use("ggplot")
plt.figure()
plt.plot(np.arange(0, N), H.history["loss"], label="train_loss")
plt.plot(np.arange(0, N), H.history["val_loss"], label="val_loss")
plt.plot(np.arange(0, N), H.history["accuracy"], label="train_acc")
plt.plot(np.arange(0, N), H.history["val_accuracy"], label="val_acc")
plt.title("Precision of COVID-19 detection.")
plt.xlabel("Epoch #")
plt.ylabel("Loss/Accuracy")
plt.legend(loc="lower left")
plt.savefig("training_plot.png")

for ind in range(10): 
    explainer = lime_image.LimeImageExplainer()
    explanation = explainer.explain_instance(testX[-ind], model.predict,
                                             hide_color=0, num_samples=42)
    print("> label:", testY[ind].argmax(), "- predicted:", predIdxs[ind])
    
    temp, mask = explanation.get_image_and_mask(
    explanation.top_labels[0], positive_only=False, num_features=1, hide_rest=True)
    plt.imshow(mark_boundaries(temp / 2 + 0.5, mask)+testX[ind])
    plt.show()

In the end, you will have some visualizations on how the network is "detecting" (if the evaluation metrics make sense) COVID-19 suspicious region in the XRs.

Comment 1: In my experience, this Lime explanation method can be handy when classifying images and trying to understand what the network is actually "looking at" to make the decision.

Comment 2: I was wondering why the classification accuracy was so high here (and in the original PyImageSearch post). I think it is because the Kaggle dataset is so well standardized that the NN is learning to predict where the X-Ray comes from Kaggle or this dataset instead of classifying healthy/sick. Nevertheless, I feel that the source code is still relevant, and with more XRs data and better preprocessing, we will be able to fix this issue and improve the algorithm.

I thought that it might be more convenient to create a single issue, as @ncovgt2020 has been doing.

• [x] https://radiopaedia.org/cases/covid-19-pneumonia-8?lang=us
• [x] https://radiopaedia.org/cases/covid-19-pneumonia-20?lang=us
• [x] https://radiopaedia.org/cases/covid-19-pneumonia-22?lang=us
• [x] https://radiopaedia.org/cases/covid-19-pneumonia-34?lang=us
• [x] https://radiopaedia.org/cases/covid-19-pneumonia-38?lang=us
• [x] https://radiopaedia.org/cases/covid-19-pneumonia-35?lang=us
• [x] https://radiopaedia.org/cases/covid-19-pneumonia-41?lang=us
• [x] https://radiopaedia.org/cases/covid-19-pneumonia-44?lang=us
• [x] https://radiopaedia.org/cases/covid-19-pneumonia-58?lang=us
• [x] https://radiopaedia.org/cases/covid-19-pneumonia-mild?lang=us
• [x] https://radiopaedia.org/cases/covid-19-pneumonia-67?lang=us
• [x] https://radiopaedia.org/cases/covid-19-pneumonia-bilateral
• [x] https://radiopaedia.org/cases/early-stage-covid-19-pneumonia-1?lang=us

Here, if a patient was ever intubated, I put "Intubated: Y" in all of the patient's images, even if some were from before intubation. Is this the correct decision here? I could not tell if the "intubated" column is at the patient or image level.

Reconstructed images, has extra information (more informative than the original images).

Each cell corresponds to a specific feature, the cell 1 is channel 1, and it's the same for cells 2 and 3, the cell 4 is the reconstructed image (RGB).

Tests (and fixes to make them pass) were added for the following asumptions:

1. All files in images/ are referenced in metadata.csv (a number of unreferenced images deleted)
2. All patients are adults (2 pediatric patients removed)
3. No duplicate images (no change needed)

According to Eurorad's Terms and Conditions, these images are all licensed under Creative Commons License CC BY-NC-SA 4.0.

Does "bedside Chest X-ray" equate to "supine"? I did not make that assumption here, but if it is correct, I could update some of the entries with that extra information.

This should close #72

• Lei P, Mao J, Huang Z, Liu G, Wang P, Song W. Key Considerations for Radiologists When Diagnosing the Novel Coronavirus Disease (COVID-19). Korean J Radiol. 2020 Jan;21:e44. https://doi.org/10.3348/kjr.2020.0190

• Yoon SH, Lee KH, Kim JY, Lee YK, Ko H, Kim KH, Park CM, Kim YH. Chest Radiographic and CT Findings of the 2019 Novel Coronavirus Disease (COVID-19): Analysis of Nine Patients Treated in Korea. Korean J Radiol. 2020 Apr;21(4):494-500. https://doi.org/10.3348/kjr.2020.0132

• Wei J, Xu H, Xiong J, Shen Q, Fan B, Ye C, Dong W, Hu F. 2019 Novel Coronavirus (COVID-19) Pneumonia: Serial Computed Tomography Findings. Korean J Radiol. 2020 Apr;21(4):501-504. https://doi.org/10.3348/kjr.2020.0112

These are also not included in my previous issue #59 on South Korean papers. Obtained with help from https://cafe.naver.com/mskmri/134

• Published online March 5, 2020. https://doi.org/10.3348/kjr.2020.0146 https://kjronline.org/Synapse/Data/PDFData/0068KJR/kjr-21-505.pdf

• Published online March 20, 2020. https://doi.org/10.3348/kjr.2020.0195 https://kjronline.org/Synapse/Data/PDFData/0068KJR/kjr-21-e45.pdf

• Published online March 20, 2020. https://doi.org/10.3348/kjr.2020.0180 https://kjronline.org/Synapse/Data/PDFData/0068KJR/kjr-21-e43.pdf

• Published online March 13, 2020. https://doi.org/10.3348/kjr.2020.0181 https://kjronline.org/Synapse/Data/PDFData/0068KJR/kjr-21-e42.pdf

• Published online March 13, 2020. https://doi.org/10.3348/kjr.2020.0157 https://kjronline.org/Synapse/Data/PDFData/0068KJR/kjr-21-e39.pdf

• Published online February 11, 2020. https://doi.org/10.3348/kjr.2020.0078 https://kjronline.org/Synapse/Data/PDFData/0068KJR/kjr-21-365.pdf

Found using advanced search of the Korean Journal of Radiology kjronline[.]org searching the term "covid-19" filtering for years 2018 - 2020

This closes #52

Radiopaedia did not specify a Creative Commons sub-license, so I chose "CC BY-NC-SA", because the other Radiopaedia images use that license.

Hi I am doing some research on this topic applying CNN with deep learning to create an automated comupter vision based scanner to detect covid posivites and negatives scans.

Here you can find my dataset, I am currently building a CT scans dataset to try and train a model for ct scan other than rx scans. https://github.com/AleGiovanardi/covidhelper/tree/master/dataset/covidct

I also have a source of new rx and cts directly from italian hospital so i will update it periodically. You are welcome to take any of the data in my repo which are missing from here.

You can find also a code which train a model, save it and let you use it to test detection of scans, which is based on Adrian Rosebrock tutorial on pyimagesearch. I am constantyl working to enhance the performance and the accuracy of it.

Also thanks for your great job, this inspired me a lot!

Hi @ieee8023 ,

May I know whether all images present in the folder images contains only the X-Ray image of patients diagnosed with COVID-19 ? Or is it the mix of Chest X-Rays of patients diagnosed with COVID-19, MERS, SARS, and ARDS. Also , If the image folder have mix of all the chest X-Rays of patients diagnosed with COVID-19, MERS, SARS, and ARDS, May I know how to fetch only the image for COVID-19.

With Regards, Aparna

I am doing a research project for various variants. Could you let me know these images belongs to which variant of novel coronavirus or any other source where I can find variant-wise XRay or CT images?

Respected Sir/Madam I am pre final year student and for my major paper I was researching on COVID 19 and I found this dataset very helpful. I want to take official permission from your organization to use this dataset.

Regards Ameya Chawla

Are there any other sources other than this from where one can obtain COVID-19 X-Ray images which also provides a metadata containing the survival label?

Hey: I tried the download that shown on the website is to use the BitTorrent. However, The BitTorrent doesn't give me any reactions after I upload the file to it. Have anyone meets the problem? Please help me with it.

I run browse_page_from_cache.py and then I have a problem with code: AttributeError: type object 'MHTMLCache' has no attribute 'source'. Can you help me fix this? Thank you very much!