import matplotlib.pyplot as plt

import pandas as pd

import numpy as np

import seaborn as sns

import keras

from keras.models import Sequential

from keras.layers import Dense, Conv2D , MaxPool2D , Flatten , Dropout , BatchNormalization

from keras.preprocessing.image import ImageDataGenerator

from sklearn.model_selection import train_test_split

from sklearn.metrics import classification_report,confusion_matrix

from keras.callbacks import ReduceLROnPlateau

import cv2

import os

labels = ['PNEUMONIA', 'NORMAL']

img_size = 150

def get_training_data(data_dir):

data = []

for label in labels:

path = os.path.join(data_dir, label)

class_num = labels.index(label)

for img in os.listdir(path):

try:

img_arr = cv2.imread(os.path.join(path, img), cv2.IMREAD_GRAYSCALE)

resized_arr = cv2.resize(img_arr, (img_size, img_size)) # Reshaping images to preferred size

data.append([resized_arr, class_num])

except Exception as e:

print(e)

return np.array(data)

train = get_training_data('/content/drive/MyDrive/chest-xray-pneumonia/chest_xray/train')

test = get_training_data('/content/drive/MyDrive/chest-xray-pneumonia/chest_xray/test')

val = get_training_data('/content/drive/MyDrive/chest-xray-pneumonia/chest_xray/val')

l = []

for i in train:

if(i[1] == 0):

l.append("Pneumonia")

else:

l.append("Normal")

sns.set_style('darkgrid')

sns.countplot(l)

plt.figure(figsize = (5,5))

plt.imshow(train[0][0], cmap='gray')

plt.title(labels[train[0][1]])

plt.figure(figsize = (5,5))

plt.imshow(train[-1][0], cmap='gray')

plt.title(labels[train[-1][1]])

x_train = []

y_train = []

x_val = []

y_val = []

x_test = []

y_test = []

for feature, label in train:

x_train.append(feature)

y_train.append(label)

for feature, label in test:

x_test.append(feature)

y_test.append(label)

for feature, label in val:

x_val.append(feature)

y_val.append(label)

x_train = np.array(x_train) / 255

x_val = np.array(x_val) / 255

x_test = np.array(x_test) / 255

x_train = x_train.reshape(-1, img_size, img_size, 1)

y_train = np.array(y_train)

x_val = x_val.reshape(-1, img_size, img_size, 1)

y_val = np.array(y_val)

x_test = x_test.reshape(-1, img_size, img_size, 1)

y_test = np.array(y_test)

datagen = ImageDataGenerator(

featurewise_center=False,

samplewise_center=False,

featurewise_std_normalization=False,

samplewise_std_normalization=False,

zca_whitening=False,

rotation_range = 30,

zoom_range = 0.2,

width_shift_range=0.1,

height_shift_range=0.1,

horizontal_flip = True,

vertical_flip=False)

datagen.fit(x_train)

model = Sequential()

model.add(Conv2D(32 , (3,3) , strides = 1 , padding = 'same' , activation = 'relu' , input_shape = (150,150,1)))

model.add(BatchNormalization())

model.add(MaxPool2D((2,2) , strides = 2 , padding = 'same'))

model.add(Conv2D(64 , (3,3) , strides = 1 , padding = 'same' , activation = 'relu'))

model.add(Dropout(0.1))

model.add(BatchNormalization())

model.add(MaxPool2D((2,2) , strides = 2 , padding = 'same'))

model.add(Conv2D(64 , (3,3) , strides = 1 , padding = 'same' , activation = 'relu'))

model.add(BatchNormalization())

model.add(MaxPool2D((2,2) , strides = 2 , padding = 'same'))

model.add(Conv2D(128 , (3,3) , strides = 1 , padding = 'same' , activation = 'relu'))

model.add(Dropout(0.2))

model.add(BatchNormalization())

model.add(MaxPool2D((2,2) , strides = 2 , padding = 'same'))

model.add(Conv2D(256 , (3,3) , strides = 1 , padding = 'same' , activation = 'relu'))

model.add(Dropout(0.2))

model.add(BatchNormalization())

model.add(MaxPool2D((2,2) , strides = 2 , padding = 'same'))

model.add(Flatten())

model.add(Dense(units = 128 , activation = 'relu'))

model.add(Dropout(0.2))

model.add(Dense(units = 1 , activation = 'sigmoid'))

model.compile(optimizer = "rmsprop" , loss = 'binary_crossentropy' , metrics = ['accuracy'])

model.summary()

learning_rate_reduction = ReduceLROnPlateau(monitor='val_accuracy', patience = 2, verbose=1,factor=0.3, min_lr=0.000001)

history = model.fit(datagen.flow(x_train,y_train, batch_size = 32) ,epochs = 12 , validation_data = datagen.flow(x_val, y_val) ,callbacks = [learning_rate_reduction])

print("Loss of the model is - " , model.evaluate(x_test,y_test)[0])

print("Accuracy of the model is - " , model.evaluate(x_test,y_test)[1]*100 , "%")

epochs = [i for i in range(12)]

fig , ax = plt.subplots(1,2)

train_acc = history.history['accuracy']

train_loss = history.history['loss']

val_acc = history.history['val_accuracy']

val_loss = history.history['val_loss']

fig.set_size_inches(20,10)

ax[0].plot(epochs , train_acc , 'go-' , label = 'Training Accuracy')

ax[0].plot(epochs , val_acc , 'ro-' , label = 'Validation Accuracy')

ax[0].set_title('Training & Validation Accuracy')

ax[0].legend()

ax[0].set_xlabel("Epochs")

ax[0].set_ylabel("Accuracy")

ax[1].plot(epochs , train_loss , 'g-o' , label = 'Training Loss')

ax[1].plot(epochs , val_loss , 'r-o' , label = 'Validation Loss')

ax[1].set_title('Testing Accuracy & Loss')

ax[1].legend()

ax[1].set_xlabel("Epochs")

ax[1].set_ylabel("Training & Validation Loss")

plt.show()

predictions = model.predict(x_test)

predictions = predictions.reshape(1,-1)[0]

y_pred = np.where(predictions > 0.5,1,0)

predictions[:15]

print(classification_report(y_test, y_pred, target_names = ['Pneumonia (Class 0)','Normal (Class 1)']))

cm = confusion_matrix(y_test,y_pred)

cm

cm = pd.DataFrame(cm , index = ['0','1'] , columns = ['0','1'])

correct = np.nonzero(predictions == y_test)[0]

incorrect = np.nonzero(predictions != y_test)[0]

i = 0

for c in correct[:6]:

plt.subplot(3,2,i+1)

plt.xticks([])

plt.yticks([])

plt.imshow(x_test[c].reshape(150,150), cmap="gray", interpolation='none')

plt.title("Predicted Class {},Actual Class {}".format(predictions[c], y_test[c]))

plt.tight_layout()

i += 1

i = 0

for c in incorrect[:6]:

plt.subplot(3,2,i+1)

plt.xticks([])

plt.yticks([])

plt.imshow(x_test[c].reshape(150,150), cmap="gray", interpolation='none')

plt.title("Predicted Class {},Actual Class {}".format(predictions[c], y_test[c]))

plt.tight_layout()

i += 1

`python3 main.py` Detection of lung cancer using CNN

Here the data is taken from the kaggle.com

Dataset Link:https://www.kaggle.com/code/tarunm561/lung-cancer-detection-using-cnn/input