In [95]:
%matplotlib inline
import pandas as pd
import numpy as np
import scipy.stats as stats
import matplotlib.pyplot as plt
import mia


Warning: Cannot change to a different GUI toolkit: qt. Using osx instead.

Loading and Preprocessing

Loading the hologic and synthetic datasets.


In [56]:
hologic = pd.DataFrame.from_csv("hologic_blobs.csv")
phantom = pd.DataFrame.from_csv("synthetic_blobs.csv")

Loading the meta data for the real and synthetic datasets.


In [57]:
hologic_meta = mia.analysis.create_hologic_meta_data(hologic, "meta_data/real_meta.csv")
phantom_meta = mia.analysis.create_synthetic_meta_data(phantom, "meta_data/synthetic_meta.csv")
phantom_meta.index.name = 'img_name'

Prepare the BI-RADS/VBD labels for both datasets.


In [58]:
hologic_labels = hologic_meta.drop_duplicates().BIRADS
phantom_labels = phantom_meta['VBD.1']

class_labels = pd.concat([hologic_labels, phantom_labels])
class_labels.index.name = "img_name"
labels = mia.analysis.remove_duplicate_index(class_labels)[0]

Creating Features

Create blob features from distribution of blobs


In [59]:
hologic_blob_features = mia.analysis.features_from_blobs(hologic)
phantom_blob_features = mia.analysis.features_from_blobs(phantom)

Take a random subset of the real mammograms. This is important so that each patient is not over represented.


In [60]:
hologic_blob_features['patient_id'] = hologic_meta.drop_duplicates()['patient_id']
hologic_blob_features_subset = mia.analysis.create_random_subset(hologic_blob_features, 
                                                                 'patient_id')

Take a random subset of the phantom mammograms. This is important so that each case is not over represented.


In [61]:
syn_feature_meta = mia.analysis.remove_duplicate_index(phantom_meta)
phantom_blob_features['phantom_name'] = syn_feature_meta.phantom_name.tolist()
phantom_blob_features_subset = mia.analysis.create_random_subset(phantom_blob_features, 'phantom_name')

Combine the features from both datasets.


In [62]:
features = pd.concat([hologic_blob_features_subset, phantom_blob_features_subset])
assert features.shape[0] == 96
features.head()


Out[62]:
blob_count avg_radius std_radius min_radius max_radius small_radius_count med_radius_count large_radius_count density upper_dist_count 25% 50% 75%
p214-010-60001-cr.png 78 19.054538 17.506086 8 90.509668 68 4 6 40.749811 22 8 11.313708 22.627417
p214-010-60005-cl.png 97 20.132590 23.255605 8 181.019336 94 2 1 41.456308 27 8 11.313708 22.627417
p214-010-60008-ml.png 310 18.777405 24.388840 8 181.019336 299 5 6 37.667995 68 8 11.313708 16.000000
p214-010-60012-cr.png 185 13.947419 7.884251 8 45.254834 152 28 5 47.292289 63 8 11.313708 16.000000
p214-010-60013-cr.png 141 21.821567 30.666648 8 181.019336 134 1 6 44.586708 38 8 11.313708 22.627417

Filter some features, such as the min, to remove noise.


In [63]:
selected_features = features.drop(['min_radius'], axis=1)

Compare Real and Synthetic Features

Compare the distributions of features detected from the real mammograms and the phantoms using the Kolmogorov-Smirnov two sample test.


In [64]:
ks_stats = [list(stats.ks_2samp(hologic_blob_features[col], 
                                phantom_blob_features[col]))
                                for col in selected_features.columns]

ks_test = pd.DataFrame(ks_stats, columns=['KS', 'p-value'], index=selected_features.columns)
ks_test.to_latex("tables/blob_features_ks.tex")
ks_test


Out[64]:
KS p-value
blob_count 0.341667 2.774753e-07
avg_radius 0.847222 1.360953e-42
std_radius 0.711111 3.929143e-30
max_radius 0.363889 3.327680e-08
small_radius_count 0.319444 2.024353e-06
med_radius_count 0.338889 3.583275e-07
large_radius_count 0.733333 5.112303e-32
density 0.169444 4.114705e-02
upper_dist_count 0.345833 1.883393e-07
25% 0.358333 5.726005e-08
50% 0.743056 7.334764e-33
75% 0.777778 5.796838e-36

Dimensionality Reduction

t-SNE

Running t-SNE to obtain a two dimensional representation.


In [65]:
real_index = hologic_blob_features_subset.index
phantom_index = phantom_blob_features_subset.index

In [66]:
kwargs = {
    'learning_rate': 200,
    'perplexity': 30,
    'verbose': 1
}

In [67]:
SNE_mapping_2d = mia.analysis.tSNE(selected_features, n_components=2, **kwargs)


[t-SNE] Computing pairwise distances...
[t-SNE] Computed conditional probabilities for sample 96 / 96
[t-SNE] Mean sigma: 1.641093
[t-SNE] Error after 72 iterations with early exaggeration: 12.697723
[t-SNE] Error after 144 iterations: 0.495631

In [68]:
mia.plotting.plot_mapping_2d(SNE_mapping_2d, real_index, phantom_index, labels)
plt.savefig('figures/mappings/blob_SNE_mapping_2d.png', dpi=300)


Running t-SNE to obtain a 3 dimensional mapping


In [98]:
SNE_mapping_3d = mia.analysis.tSNE(selected_features, n_components=3, **kwargs)


[t-SNE] Computing pairwise distances...
[t-SNE] Computed conditional probabilities for sample 96 / 96
[t-SNE] Mean sigma: 1.641093
[t-SNE] Error after 100 iterations with early exaggeration: 14.272421
[t-SNE] Error after 300 iterations: 2.104165

In [99]:
mia.plotting.plot_mapping_3d(SNE_mapping_3d, real_index, phantom_index, labels)


Out[99]:
<matplotlib.axes._subplots.Axes3DSubplot at 0x10cca73d0>

Isomap

Running Isomap to obtain a 2 dimensional mapping


In [71]:
iso_kwargs = {
    'n_neighbors': 4,
}

In [72]:
iso_mapping_2d = mia.analysis.isomap(selected_features, n_components=2, **iso_kwargs)

In [73]:
mia.plotting.plot_mapping_2d(iso_mapping_2d, real_index, phantom_index, labels)
plt.savefig('figures/mappings/blob_iso_mapping_2d.png', dpi=300)



In [74]:
iso_mapping_3d = mia.analysis.isomap(selected_features, n_components=3, **iso_kwargs)

In [100]:
mia.plotting.plot_mapping_3d(iso_mapping_3d, real_index, phantom_index, labels)


Out[100]:
<matplotlib.axes._subplots.Axes3DSubplot at 0x10c306810>

Locally Linear Embedding

Running locally linear embedding to obtain 2d mapping


In [76]:
lle_kwargs = {
    'n_neighbors': 4,
}

In [77]:
lle_mapping_2d = mia.analysis.lle(selected_features, n_components=2, **lle_kwargs)

In [78]:
mia.plotting.plot_mapping_2d(lle_mapping_2d, real_index, phantom_index, labels)
plt.savefig('figures/mappings/blob_lle_mapping_2d.png', dpi=300)



In [79]:
lle_mapping_3d = mia.analysis.lle(selected_features, n_components=3, **lle_kwargs)

In [101]:
mia.plotting.plot_mapping_3d(lle_mapping_3d,real_index, phantom_index, labels)


Out[101]:
<matplotlib.axes._subplots.Axes3DSubplot at 0x10d9d7810>

Quality Assessment of Dimensionality Reduction

Assess the quality of the DR against measurements from the co-ranking matrices. First create co-ranking matrices for each of the dimensionality reduction mappings


In [81]:
max_k = 50

In [82]:
SNE_mapping_2d_cm = mia.coranking.coranking_matrix(selected_features, SNE_mapping_2d)
iso_mapping_2d_cm = mia.coranking.coranking_matrix(selected_features, iso_mapping_2d)
lle_mapping_2d_cm = mia.coranking.coranking_matrix(selected_features, lle_mapping_2d)

SNE_mapping_3d_cm = mia.coranking.coranking_matrix(selected_features, SNE_mapping_3d)
iso_mapping_3d_cm = mia.coranking.coranking_matrix(selected_features, iso_mapping_3d)
lle_mapping_3d_cm = mia.coranking.coranking_matrix(selected_features, lle_mapping_3d)

2D Mappings


In [83]:
SNE_trustworthiness_2d = [mia.coranking.trustworthiness(SNE_mapping_2d_cm, k) 
                          for k in range(1, max_k)]
iso_trustworthiness_2d = [mia.coranking.trustworthiness(iso_mapping_2d_cm, k) 
                          for k in range(1, max_k)]
lle_trustworthiness_2d = [mia.coranking.trustworthiness(lle_mapping_2d_cm, k) 
                          for k in range(1, max_k)]

In [84]:
trustworthiness_df = pd.DataFrame([SNE_trustworthiness_2d,
                                   iso_trustworthiness_2d,
                                   lle_trustworthiness_2d], 
                                   index=['SNE', 'Isomap', 'LLE']).T
trustworthiness_df.plot()
plt.savefig('figures/quality_measures/blob_trustworthiness_2d.png', dpi=300)



In [85]:
SNE_continuity_2d = [mia.coranking.continuity(SNE_mapping_2d_cm, k) for k in range(1, max_k)]
iso_continuity_2d = [mia.coranking.continuity(iso_mapping_2d_cm, k) for k in range(1, max_k)]
lle_continuity_2d = [mia.coranking.continuity(lle_mapping_2d_cm, k) for k in range(1, max_k)]

In [86]:
continuity_df = pd.DataFrame([SNE_continuity_2d,
                              iso_continuity_2d,
                              lle_continuity_2d], 
                              index=['SNE', 'Isomap', 'LLE']).T
continuity_df.plot()
plt.savefig('figures/quality_measures/blob_continuity_2d.png', dpi=300)



In [87]:
SNE_lcmc_2d = [mia.coranking.LCMC(SNE_mapping_2d_cm, k) for k in range(2, max_k)]
iso_lcmc_2d = [mia.coranking.LCMC(iso_mapping_2d_cm, k) for k in range(2, max_k)]
lle_lcmc_2d = [mia.coranking.LCMC(lle_mapping_2d_cm, k) for k in range(2, max_k)]

In [88]:
lcmc_df = pd.DataFrame([SNE_lcmc_2d,
                        iso_lcmc_2d,
                        lle_lcmc_2d], 
                        index=['SNE', 'Isomap', 'LLE']).T
lcmc_df.plot()
plt.savefig('figures/quality_measures/blob_lcmc_2d.png', dpi=300)


3D Mappings


In [89]:
SNE_trustworthiness_3d = [mia.coranking.trustworthiness(SNE_mapping_3d_cm, k) 
                          for k in range(1, max_k)]
iso_trustworthiness_3d = [mia.coranking.trustworthiness(iso_mapping_3d_cm, k) 
                          for k in range(1, max_k)]
lle_trustworthiness_3d = [mia.coranking.trustworthiness(lle_mapping_3d_cm, k) 
                          for k in range(1, max_k)]

In [90]:
trustworthiness3d_df = pd.DataFrame([SNE_trustworthiness_3d,
                                   iso_trustworthiness_3d,
                                   lle_trustworthiness_3d], 
                                   index=['SNE', 'Isomap', 'LLE']).T
trustworthiness3d_df.plot()
plt.savefig('figures/quality_measures/blob_trustworthiness_3d.png', dpi=300)



In [91]:
SNE_continuity_3d = [mia.coranking.continuity(SNE_mapping_3d_cm, k) for k in range(1, max_k)]
iso_continuity_3d = [mia.coranking.continuity(iso_mapping_3d_cm, k) for k in range(1, max_k)]
lle_continuity_3d = [mia.coranking.continuity(lle_mapping_3d_cm, k) 
for k in range(1, max_k)]

In [92]:
continuity3d_df = pd.DataFrame([SNE_continuity_3d,
                              iso_continuity_3d,
                              lle_continuity_3d], 
                              index=['SNE', 'Isomap', 'LLE']).T
continuity3d_df.plot()
plt.savefig('figures/quality_measures/blob_continuity_3d.png', dpi=300)



In [93]:
SNE_lcmc_3d = [mia.coranking.LCMC(SNE_mapping_3d_cm, k) for k in range(2, max_k)]
iso_lcmc_3d = [mia.coranking.LCMC(iso_mapping_3d_cm, k) for k in range(2, max_k)]
lle_lcmc_3d = [mia.coranking.LCMC(lle_mapping_3d_cm, k) for k in range(2, max_k)]

In [94]:
lcmc3d_df = pd.DataFrame([SNE_lcmc_3d,
                        iso_lcmc_3d,
                        lle_lcmc_3d], 
                        index=['SNE', 'Isomap', 'LLE']).T
lcmc3d_df.plot()
plt.savefig('figures/quality_measures/blob_lcmc_3d.png', dpi=300)