Detector automático COVID-19 de imágenes de fluorografía

• Me desperté por la mañana, me siento un poco abrumado.
  
• Cuando me levanté de la cama, ya tenía una fuga de mi nariz (aunque ahora se sabe que la secreción nasal no es un síntoma de COVID-19).
  
• Mientras llegaba al baño para tomar una servilleta, también tosió.

1. Recopilaremos un conjunto de datos abiertos de fluorogramas de pacientes con una prueba positiva para COVID-19.
   
2. Recopilamos una selección de fluorogramas de pacientes sanos.
   
3. Entrenaremos la red neuronal convolucional para detectar automáticamente COVID-19 en las imágenes del conjunto creado.
   
4. Evaluaremos los resultados obtenidos desde un punto de vista educativo.

COVID-19 en fluorogramas

Conjunto de datos

1. Resultado positivo en COVID-19.
   
2. Tipo de pulmones 'posterior-anterior' (PA). Por lo que yo entiendo, este es el tipo de imagen utilizada en imágenes "saludables".

Estructura del proyecto

$ 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
3 directories, 5 files

Implementación

# 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

# 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: ruta al conjunto de datos de entrada
  
• --plot: Una ruta opcional al horario de salida para su historial de aprendizaje. A menos que se especifique lo contrario, el valor predeterminado esplot.png
  
• --model: ruta opcional al modelo de salida; defectocovid19.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)

• Recuperamos la etiqueta de clase ( covido normal) de la ruta .
  
• Lo cargamos imagey procesamos previamente, lo convertimos a RGB y lo redimensionamos a 224 × 224 píxeles, para que esté listo para la red neuronal.
  
• Actualización de listas datay labels.

# perform one-hot encoding on the labels
lb = LabelBinarizer()
labels = lb.fit_transform(labels)
labels = to_categorical(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))

• Generamos una matriz de imprecisiones.
  
• Con su ayuda, calculamos la precisión, la sensibilidad y la especificidad imprimiendo todas estas métricas.

# 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")

Entrenamiento de detectores

$ 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...

Diagnóstico automático de COVID-19 según los resultados de la fluorografía.

• Los pacientes verdaderamente infectados se reconocen en el 100% de los casos.
  
• Los pacientes sanos son reconocidos como saludables con una probabilidad del 80%.

Limitaciones, mejoras y trabajos futuros.

¿Que sigue?

Resumen

• Seleccionamos 25 imágenes del conjunto de datos de Cohen, seleccionando solo la vista posterior-anterior (AP) y un diagnóstico confirmado.
  
• Luego, se seleccionaron 25 imágenes de pacientes sanos de un conjunto de datos con imágenes de fluorografía de Kaggle (neumonía) .