Detect COVID-19 in X-rays with Keras, TensorFlow and Deep Learning

• I woke up in the morning, feeling some soreness and weakness.
• When I crawled out of bed, I found a runny nose (although it is already known that a runny nose is not a symptom of COVID-19).
• By the time I got to the bathroom to get a paper scarf, I was already coughing.

UFO Care Minute

COVID-19 — , SARS-CoV-2 (2019-nCoV). — , /, .

• C
• C
• ()

, .

, , .

: |

1. How to collect opensource-dataset of X-ray images of patients with detected COVID-19.
2. «» ( ) .
3. COVID-19 .
4. .

Explanation

How can COVID-19 be detected in x-rays?

COVID-19

1. Parse the metadata.csv file from the repository.
2. Selected all the lines:

Project structure

$ tree --dirsfirst --filelimit 10
.
├── dataset
│   ├── covid [25 entries]
│   └── normal [25 entries]
├── build_covid_dataset.py
├── sample_kaggle_dataset.py
├── train_covid19.py
├── plot.png
└── covid19.model

Training script implementation

# import the necessary packages
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 argparse
import cv2
import os

• scikit-learn , this is a de facto Python machine learning library,
• matplotlib for charting,
• OpenCV for uploading and preprocessing images in a dataset.

# construct the argument parser and parse the arguments
ap = argparse.ArgumentParser()
ap.add_argument("-d", "--dataset", required=True,
    help="path to input dataset")
ap.add_argument("-p", "--plot", type=str, default="plot.png",
    help="path to output loss/accuracy plot")
ap.add_argument("-m", "--model", type=str, default="covid19.model",
    help="path to output loss/accuracy plot")
args = vars(ap.parse_args())

# initialize the initial learning rate, number of epochs to train for,
# and batch size
INIT_LR = 1e-3
EPOCHS = 25
BS = 8

• --dataset: path to the input dataset.
• --plot: optional path to the exit schedule of learning history. By default, the graph is called plot.png unless a different name is specified on the command line.
• --model: optional path to our output COVID-19 definition model. By default, it is called covid19.model.

# grab the list of images in our dataset directory, then initialize
# the list of data (i.e., images) and class images
print("[INFO] loading images...")
imagePaths = list(paths.list_images(args["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)

• We extract from the path ( line 49 ) the class label (covid or normal).
• We load the image, convert it to RGB channels and reduce it to a size of 224x224 pixels to feed a convolutional neural network ( lines 53-55 ).
• Updating lists of data and labels ( lines 58 and 59 ).

# perform one-hot encoding on the labels
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=0.20, stratify=labels, random_state=42)

# initialize the training data augmentation object
trainAug = ImageDataGenerator(
    rotation_range=15,
    fill_mode="nearest")

[[0. 1.]
 [0. 1.]
 [0. 1.]
 ...
 [1. 0.]
 [1. 0.]
 [1. 0.]]

# load the VGG16 network, ensuring the head FC layer sets are left
# off
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

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

# train the head of the network
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)

# make predictions on the testing set
print("[INFO] evaluating network...")
predIdxs = model.predict(testX, batch_size=BS)

# for each image in the testing set we need to find the index of the
# label with corresponding largest predicted probability
predIdxs = np.argmax(predIdxs, axis=1)

# show a nicely formatted classification report
print(classification_report(testY.argmax(axis=1), predIdxs,
    target_names=lb.classes_))

# compute the confusion matrix and and use it to derive the raw
# accuracy, sensitivity, and specificity
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))

• generate a matrix of inaccuracies ( line 133 ),
• we use this matrix to determine the accuracy, sensitivity and specificity ( lines 135-137 ), and then we derive all these metrics ( lines 141-143 ).

# plot the training loss and accuracy
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("Training Loss and Accuracy on COVID-19 Dataset")
plt.xlabel("Epoch #")
plt.ylabel("Loss/Accuracy")
plt.legend(loc="lower left")
plt.savefig(args["plot"])

# serialize the model to disk
print("[INFO] saving COVID-19 detector model...")
model.save(args["model"], save_format="h5")

We train our detector with Keras and TensorFlow

$ python train_covid19.py --dataset dataset
[INFO] loading images...
[INFO] compiling model...
[INFO] training head...
Epoch 1/25
5/5 [==============================] - 20s 4s/step - loss: 0.7169 - accuracy: 0.6000 - val_loss: 0.6590 - val_accuracy: 0.5000
Epoch 2/25
5/5 [==============================] - 0s 86ms/step - loss: 0.8088 - accuracy: 0.4250 - val_loss: 0.6112 - val_accuracy: 0.9000
Epoch 3/25
5/5 [==============================] - 0s 99ms/step - loss: 0.6809 - accuracy: 0.5500 - val_loss: 0.6054 - val_accuracy: 0.5000
Epoch 4/25
5/5 [==============================] - 1s 100ms/step - loss: 0.6723 - accuracy: 0.6000 - val_loss: 0.5771 - val_accuracy: 0.6000
...
Epoch 22/25
5/5 [==============================] - 0s 99ms/step - loss: 0.3271 - accuracy: 0.9250 - val_loss: 0.2902 - val_accuracy: 0.9000
Epoch 23/25
5/5 [==============================] - 0s 99ms/step - loss: 0.3634 - accuracy: 0.9250 - val_loss: 0.2690 - val_accuracy: 0.9000
Epoch 24/25
5/5 [==============================] - 27s 5s/step - loss: 0.3175 - accuracy: 0.9250 - val_loss: 0.2395 - val_accuracy: 0.9000
Epoch 25/25
5/5 [==============================] - 1s 101ms/step - loss: 0.3655 - accuracy: 0.8250 - val_loss: 0.2522 - val_accuracy: 0.9000
[INFO] evaluating network...
              precision    recall  f1-score   support

       covid       0.83      1.00      0.91         5
      normal       1.00      0.80      0.89         5

    accuracy                           0.90        10
   macro avg       0.92      0.90      0.90        10
weighted avg       0.92      0.90      0.90        10

[[5 0]
 [1 4]]
acc: 0.9000
sensitivity: 1.0000
specificity: 0.8000
[INFO] saving COVID-19 detector model...

Auto X-ray Diagnostics

• Of the patients with COVID-19 (true positive cases), using the model, we were able to accurately identify as “COVID-19 positive” in 100% of cases.
• Of the patients who did not have COVID-19 (true negative cases), using the model, we were able to accurately identify as “COVID-19-negative” in only 80% of cases.

Limitations, improvements and further work

Summary

• We took 25 images from his dataset , limiting ourselves to the anteroposterior projection of positively diagnosed cases.
• Then we took 25 pictures of healthy people from the Kaggle Chest X-Ray Images (Pneumonia) dataset.