def main():
filename = '../data/train/image_2473853.jpg'
inp = imread(filename).astype('float32')
plt.imshow(inp, cmap='gray')
plt.show()
print(inp)
print(len(inp.reshape(-1, inp.shape[0], inp.shape[1], 1)))
cnnnet = CNNModel()
conv_layer1, conv_layer2, conv_layer3, network = cnnnet.define_network(
inp.reshape(-1, inp.shape[0], inp.shape[1], 1), 'visual')
model = tflearn.DNN(network,
tensorboard_verbose=0,
checkpoint_path='nodule-classifier.tfl.ckpt')
model.load('nodule-classifier.tfl')
labels = model.predict(inp.reshape(-1, 50, 50, 1))
print("This is the labels :", labels)
if labels[0][1] == 1:
print('The input image is a nodule.')
else:
print('The input image is not a nodule.')
layer_to_be_plotted = [conv_layer1, conv_layer2, conv_layer3]
for idx, layer in enumerate(layer_to_be_plotted):
m2, yhat = get_layer_output(layer, model, inp)
plot_layers(yhat, idx, '../visual_images/conv_layer_')
weights = get_weights(m2, conv_layer1)
plot_layers(weights, 0, '../visual_images/weight_conv_layer_', 6)
plt.show()
def get_predictions(x_test_images, y_test_labels):
"""
Given the test images, cnn network predicted the labels for images.
:param x_test_images: test images
:param y_test_labels: response to labels for the images
:return:
predictions: the predicted probability values of test labels for images
label_predictions: the specific class for each image
"""
cnn_net = CNNModel()
network = cnn_net.define_network(x_test_images)
model = tflearn.DNN(network,
tensorboard_verbose=0,
checkpoint_path='nodule-classifier.tfl.ckpt')
model.load('nodule-classifier.tfl')
predictions = np.vstack(model.predict(x_test_images[:, :, :, :]))
score = model.evaluate(x_test_images, y_test_labels)
print('The total classification accuracy is : ', score)
label_predictions = np.zeros_like(predictions)
label_predictions[np.arange(len(predictions)), predictions.argmax(1)] = 1
return predictions, label_predictions
def main():
mask_extra()
lungs_ROI()
generate_images()
height = 50
width = 50
workpath = '../data/visualization/'
workpath_1 = '../testing_patient/'
file = glob(workpath + '*.npy')
target = file[0][33:-4]
print(target)
file_list = glob('../testing_patient/lungmask_*.npy')
print(file_list)
for file_l in file_list:
if file_l[33:-4] == target:
file_name = file_l[:-4]
print(file_name)
# file_name = '../testing_patient/lungmask_0003_0125'
image = cv2.imread(file_name + '.png')
lung_mask = np.load(workpath_1 + file_name + '.npy')
image_files = np.load(workpath_1 + 'images_' + file_name[28:] + '.npy')
SeletiveSearch(image)
images_path = '../temptation/'
filelist = glob(images_path + '*.png')
filelist.sort(key=lambda x: int(x[18:-4]))
print(filelist)
image_num = len(filelist)
data = np.zeros((image_num, height, width, 1))
for idx in range(image_num):
img = imread(filelist[idx]).astype('float32')
img = img.reshape(-1, img.shape[0], img.shape[1], 1)
data[idx, :, :, :] = img
print(data.shape)
# Read images and corresponding labels
csvfile = open('../testing_patient/predicted_nodules.csv', 'r')
csvReader = csv.reader(csvfile)
images_labels = list(csvReader)
csvfile_1 = open('../testing_patient/file_classes.csv', 'r')
csvReader_1 = csv.reader(csvfile_1)
images_nodules = list(csvReader_1)
real_candidates = []
candidates = []
del images_labels[0]
del images_nodules[0]
for i_l in images_labels:
i_l[1] = eval(i_l[1])
i_l[2] = eval(i_l[2])
candidates.append(i_l[2])
print(images_labels)
print(candidates)
# Get the lung nodule coordinates
for j_l in images_nodules:
if j_l[0] == file_name[19:]:
j_l[1] = eval(j_l[1])
j_l[2] = eval(j_l[2])
real_candidates.append((j_l[1], j_l[2]))
# Mapping the real regions that contain lung nodules
real_nodules = []
for candidate in candidates:
if (candidate[0], candidate[1]) in real_candidates:
real_nodules.append(candidate)
print(real_nodules)
# Feed the data into trained model.
cnnnet = CNNModel()
network = cnnnet.define_network(data, 'testtrain')
model = tflearn.DNN(network,
tensorboard_verbose=0,
checkpoint_path='nodule-classifier.tfl.ckpt')
model.load('nodule-classifier.tfl')
predictions = np.vstack(model.predict(data[:, :, :, :]))
label_predictions = np.zeros_like(predictions)
label_predictions[np.arange(len(predictions)), predictions.argmax(1)] = 1
print(len(label_predictions))
index_list = []
for ind, val in enumerate(label_predictions):
if val[1] == 1:
index_list.append(ind)
print(len(index_list))
print(index_list)
nodule_candidate = []
for i in index_list:
nodule_candidate.append(candidates[i])
print(nodule_candidate)
fig, ax = plt.subplots(2, 2, figsize=[8, 8])
ax[0, 0].imshow(image_files[0], cmap='gray')
ax[0, 1].imshow(image_files[0] * lung_mask[0], cmap='gray')
ax[1, 0].imshow(image)
ax[1, 1].imshow(image)
for x, y, w, h in candidates:
rect = mpatches.Rectangle((x, y),
w,
h,
fill=False,
edgecolor='red',
linewidth=1)
ax[1, 0].add_patch(rect)
#for x, y, w, h in real_nodules:
# rect = mpatches.Rectangle((x, y), w, h, fill=False, edgecolor='yellow', linewidth=1)
# ax[1, 1].add_patch(rect)
for x, y, w, h in nodule_candidate:
rect = mpatches.Rectangle((x - 3, y - 3),
w + 5,
h + 5,
fill=False,
edgecolor='red',
linewidth=1)
ax[1, 1].add_patch(rect)
plt.show()
shutil.rmtree('../temptation')
os.mkdir('../temptation')
Trains a CNN model using tflearn wrapper for tensorflow
"""
import tflearn
import h5py
from models.cnn_model import CNNModel
# Load HDF5 dataset
h5f = h5py.File('../data/train.h5', 'r')
X_train_images = h5f['X']
Y_train_labels = h5f['Y']
h5f2 = h5py.File('../data/val.h5', 'r')
X_val_images = h5f2['X']
Y_val_labels = h5f2['Y']
## Model definition
convnet = CNNModel()
network = convnet.define_network(X_train_images)
model = tflearn.DNN(network, tensorboard_verbose=0, checkpoint_path='nodule-classifier.tfl.ckpt')
model.fit(X_train_images, Y_train_labels, n_epoch=50, shuffle=True, validation_set=(X_val_images, Y_val_labels),
show_metric=True, batch_size=128, snapshot_epoch=False, run_id='nodule-classifier')
model.save("nodule-classifier.tfl")
print("Network trained and saved as nodule-classifier.tfl!")
h5f.close()
h5f2.close()
def main():
height = 50
width = 50
# To get the images from the folder and to sort them as the sequence as csv files
images_path = '../images/'
filelist = glob(images_path + '*.png')
print(filelist)
filelist.sort(key=lambda x: int(x[29:-4]))
# Read images and corresponding labels
csvfile = open('../submission_files/regions_labels.csv', 'r')
csvReader = csv.reader(csvfile)
# images_labels contains the name of images and the labels generated from selective search
images_labels = list(csvReader)
del images_labels[0]
for i_l in images_labels:
i_l[1] = eval(i_l[1])
i_l[2] = eval(i_l[2])
print(len(images_labels))
# Pre-processing the data to generate all dataset.
image_num = len(filelist)
data = np.zeros((image_num, height, width, 1))
for idx in range(image_num):
img = imread(filelist[idx]).astype('float32')
img = img.reshape(-1, img.shape[0], img.shape[1], 1)
data[idx, :, :, :] = img
print(data.shape)
# Feed the data into trained model.
cnnnet = CNNModel()
network = cnnnet.define_network(data, 'testtrain')
model = tflearn.DNN(network,
tensorboard_verbose=0,
checkpoint_path='nodule-classifier.tfl.ckpt')
model.load('nodule-classifier.tfl')
predictions = np.vstack(model.predict(data[:, :, :, :]))
label_predictions = np.zeros_like(predictions)
label_predictions[np.arange(len(predictions)), predictions.argmax(1)] = 1
print(len(label_predictions))
index_list = []
for ind, val in enumerate(label_predictions):
if val[1] == 1:
index_list.append(ind)
images_name = []
for index in index_list:
#print(images_labels[index][0][:18])
images_name.append(images_labels[index][0][:18] + '.png')
images_name2 = list(set(images_name))
images_name2.sort(key=images_name.index)
print(images_name2)
print(len(images_name2))
img_list = glob('../data/test_images/*.png')
img_list.sort()
allimages = []
for l in img_list:
allimages.append(l[20:])
print(allimages)
# Writing the results into the files to show whether the patient contains nodules
f_submission1 = open('../submission_files/predicted_patient_labels.csv',
'w')
writer_1 = csv.writer(f_submission1)
writer_1.writerow(('Patient', 'Predict_Labels'))
for a_img in allimages:
if a_img in images_name2:
writer_1.writerow((a_img, 1))
else:
writer_1.writerow((a_img, 0))
# Writing the results into the submission csv file
f_submission = open('../submission_files/predicted_regions_labels.csv',
'w')
writer = csv.writer(f_submission)
writer.writerow(
('File_name', 'Labels', 'Rect', 'Actual_Nodule', 'Predict_Nodule'))
for i in range(len(images_labels)):
#index = index_list[i]
#print(images_labels[index][0][:])
writer.writerow(
(images_labels[i][0][:], images_labels[i][1], images_labels[i][2],
images_labels[i][3], label_predictions[i][1]))
actual = []
pre = []
for i in range(len(images_labels)):
actual.append(eval(images_labels[i][3]))
pre.append(predictions[i][1])
print(actual)
print(pre)
fpr, tpr, thresholds = roc_curve(actual, pre, pos_label=1)
roc_auc = auc(fpr, tpr)
print("The false positive rate is: ", fpr)
print("The true positive rate is:", tpr)
print(thresholds)
print("The auc is:", roc_auc)
plt.figure()
lw = 2
plt.plot(fpr,
tpr,
color='darkorange',
lw=lw,
label='(AUC = %0.2f)' % roc_auc)
plt.plot([0, 1], [0, 1], color='navy', lw=lw, linestyle='--')
plt.axis('equal')
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
plt.legend(loc='lower right')
plt.show()
csvfile.close()
f_submission.close()
f_submission1.close()