def knn_curve():
# Load training and test data
train_data, train_labels, train_feature_labels = util.create_dataset(
1, 1, 'brain')
test_data, test_labels, test_feature_labels = util.create_dataset(
2, 1, 'brain')
# Normalize data
train_data, test_data = seg.normalize_data(train_data, test_data)
#Define parameters
num_iter = 3
train_size = 100
k = np.array([1, 3, 5, 9, 15, 25, 100])
# k = np.array([1, 5, 9])
#Store errors
test_error = np.empty([len(k), num_iter])
test_error[:] = np.nan
dice = np.empty([len(k), num_iter])
dice[:] = np.nan
## Train and test with different values
for i in np.arange(len(k)):
for j in np.arange(num_iter):
print('k = {}, iter = {}'.format(k[i], j))
#Subsample training set
ix = np.random.randint(len(train_data), size=train_size)
subset_train_data = train_data[ix, :]
subset_train_labels = train_labels[ix, :]
predicted_test_labels = seg.knn_classifier(subset_train_data,
subset_train_labels,
test_data, k[i])
# #Train classifier
# neigh = KNeighborsClassifier(n_neighbors=k[i])
# neigh.fit(subset_train_data, subset_train_labels)
# #Evaluate
# predicted_test_labels = neigh.predict(test_data)
test_error[i,
j] = util.classification_error(test_labels,
predicted_test_labels)
dice[i, j] = util.dice_overlap(test_labels, predicted_test_labels)
## Display results
fig = plt.figure(figsize=(8, 8))
ax1 = fig.add_subplot(111)
p1 = ax1.plot(k, np.mean(test_error, 1), 'r', label='error')
p2 = ax1.plot(k, np.mean(dice, 1), 'k', label='dice')
ax1.set_xlabel('k')
ax1.set_ylabel('error')
ax1.grid()
ax1.legend()
def segmentation_mymethod(train_data,
train_labels,
test_data,
test_labels,
task='brain',
method='nearest neighbour',
testDice=True):
# segments the image based on your own method!
# Input:
# train_data_matrix num_pixels x num_features x num_subjects matrix of
# features
# train_labels_matrix num_pixels x num_subjects matrix of labels
# test_data num_pixels x num_features test data
# task String corresponding to the segmentation task: either 'brain' or 'tissue'
# Output:
# predicted_labels Predicted labels for the test slice
#------------------------------------------------------------------#
#TODO: Implement your method here
if method == 'kmeans':
predicted_labels = seg.kmeans_clustering(test_data, K=4)
elif method == 'nearest neighbour':
predicted_labels = seg.nn_classifier(train_data, train_labels,
test_data)
elif method == 'knn':
predicted_labels = seg.knn_classifier(train_data,
train_labels,
test_data,
k=4)
elif method == 'atlas':
predicted_labels = seg.segmentation_atlas(train_data, train_labels,
test_data)
predicted_labels = predicted_labels.astype(bool)
test_labels = test_labels.astype(bool)
err = util.classification_error(test_labels, predicted_labels)
print('Error:\n{}'.format(err))
if testDice:
dice = util.dice_multiclass(test_labels, predicted_labels)
print('Dice coefficient:\n{}'.format(dice))
#------------------------------------------------------------------#
return predicted_labels
def segmentation_mymethod(train_data_matrix, train_labels_matrix, test_data, task='tissue'):
# segments the image based on your own method!
# Input:
# train_data_matrix num_pixels x num_features x num_subjects matrix of
# features
# train_labels_matrix num_pixels x num_subjects matrix of labels
# test_data num_pixels x num_features test data
# task String corresponding to the segmentation task: either 'brain' or 'tissue'
# Output:
# predicted_labels Predicted labels for the test slice
#------------------------------------------------------------------#
#TODO: Implement your method here
choice_br=[0,1,5,6,7]
train_data= train_data_matrix[:,:,1]
train_labels=train_labels_matrix[:,1]
ix = np.random.randint(len(train_data), size=1000)
train_datann = train_data[:,choice_br]
train_datann = train_datann[ix,:]
train_labels_brain = train_labels>0
train_labelsnn = train_labels_brain[ix]
test_datann = test_data[:,choice_br]
predicted_labelsnn = seg.knn_classifier(train_datann, train_labelsnn, test_datann, 35)
predicted_masknn = predicted_labelsnn.reshape(I.shape)
openimage = scipy.ndimage.morphology.binary_opening(predicted_masknn, iterations=2)
op_imf = openimage.flatten().T.astype(float)
op_imf = op_imf.reshape(-1, 1)
train_data_brain = train_data*op_imf
train_labels_brain = train_data*op_imf
#------------------------------------------------------------------#
return predicted_labels