def test_simulated_correlations():
# Get standard brain mask
mr_directory = get_data_directory()
standard = "%s/MNI152_T1_2mm_brain_mask.nii.gz" %(mr_directory)
thresholds = [0.0,0.5,1.0,1.5,1.96,2.0]
# Generate random data inside brain mask, run 10 iterations
standard = nibabel.load(standard)
number_values = len(numpy.where(standard.get_data()!=0)[0])
numpy.random.seed(9191986)
for x in range(0,10):
data1 = norm.rvs(size=number_values)
data2 = norm.rvs(size=number_values)
corr = pearsonr(data1,data2)[0]
# Put into faux nifti images
mr1 = numpy.zeros(standard.shape)
mr1[standard.get_data()!=0] = data1
mr1 = nibabel.nifti1.Nifti1Image(mr1,affine=standard.get_affine(),header=standard.get_header())
mr2 = numpy.zeros(standard.shape)
mr2[standard.get_data()!=0] = data2
mr2 = nibabel.nifti1.Nifti1Image(mr2,affine=standard.get_affine(),header=standard.get_header())
pdmask = make_binary_deletion_mask([mr1,mr2])
pdmask = nibabel.Nifti1Image(pdmask,header=mr1.get_header(),affine=mr1.get_affine())
score = calculate_correlation(images = [mr1,mr2],mask=pdmask)
assert_almost_equal(corr,score,decimal=5)
def test_simulated_correlations():
# Get standard brain mask
mr_directory = get_data_directory()
standard = "%s/MNI152_T1_2mm_brain_mask.nii.gz" % (mr_directory)
thresholds = [0.0, 0.5, 1.0, 1.5, 1.96, 2.0]
# Generate random data inside brain mask, run 10 iterations
standard = nibabel.load(standard)
number_values = len(numpy.where(standard.get_data() != 0)[0])
numpy.random.seed(9191986)
for x in range(0, 10):
data1 = norm.rvs(size=number_values)
data2 = norm.rvs(size=number_values)
corr = pearsonr(data1, data2)[0]
# Put into faux nifti images
mr1 = numpy.zeros(standard.shape)
mr1[standard.get_data() != 0] = data1
mr1 = nibabel.nifti1.Nifti1Image(mr1,
affine=standard.get_affine(),
header=standard.get_header())
mr2 = numpy.zeros(standard.shape)
mr2[standard.get_data() != 0] = data2
mr2 = nibabel.nifti1.Nifti1Image(mr2,
affine=standard.get_affine(),
header=standard.get_header())
pdmask = make_binary_deletion_mask([mr1, mr2])
pdmask = nibabel.Nifti1Image(pdmask,
header=mr1.get_header(),
affine=mr1.get_affine())
score = calculate_correlation(images=[mr1, mr2], mask=pdmask)
assert_almost_equal(corr, score, decimal=5)
def save_voxelwise_pearson_similarity_resample(pk1,
pk2,
resample_dim=[4, 4, 4]):
from neurovault.apps.statmaps.models import Similarity, Comparison
# We will always calculate Comparison 1 vs 2, never 2 vs 1
if pk1 != pk2:
sorted_images = get_images_by_ordered_id(pk1, pk2)
image1 = sorted_images[0]
image2 = sorted_images[1]
pearson_metric = Similarity.objects.get(
similarity_metric="pearson product-moment correlation coefficient",
transformation="voxelwise")
# Get standard space brain
mr_directory = get_data_directory()
reference = "%s/MNI152_T1_2mm_brain_mask.nii.gz" % (mr_directory)
image_paths = [image.file.path for image in [image1, image2]]
images_resamp, _ = resample_images_ref(images=image_paths,
reference=reference,
interpolation="continuous",
resample_dim=resample_dim)
# resample_images_ref will "squeeze" images, but we should keep error here for now
for image_nii, image_obj in zip(images_resamp, [image1, image2]):
if len(numpy.squeeze(image_nii.get_data()).shape) != 3:
raise Exception(
"Image %s (id=%d) has incorrect number of dimensions %s" %
(image_obj.name, image_obj.id,
str(image_nii.get_data().shape)))
# Calculate correlation only on voxels that are in both maps (not zero, and not nan)
image1_res = images_resamp[0]
image2_res = images_resamp[1]
binary_mask = make_binary_deletion_mask(images_resamp)
binary_mask = nib.Nifti1Image(binary_mask,
header=image1_res.get_header(),
affine=image1_res.get_affine())
# Will return nan if comparison is not possible
pearson_score = calculate_correlation([image1_res, image2_res],
mask=binary_mask,
corr_type="pearson")
# Only save comparison if is not nan
if not numpy.isnan(pearson_score):
Comparison.objects.update_or_create(
image1=image1,
image2=image2,
similarity_metric=pearson_metric,
similarity_score=pearson_score)
return image1.pk, image2.pk, pearson_score
else:
raise Exception("You are trying to compare an image with itself!")
def save_voxelwise_pearson_similarity_resample(pk1, pk2,resample_dim=[4,4,4]):
from neurovault.apps.statmaps.models import Similarity, Comparison
# We will always calculate Comparison 1 vs 2, never 2 vs 1
if pk1 != pk2:
try:
sorted_images = get_images_by_ordered_id(pk1, pk2)
except Http404:
# files have been deleted in the meantime
return
image1 = sorted_images[0]
image2 = sorted_images[1]
pearson_metric = Similarity.objects.get(
similarity_metric="pearson product-moment correlation coefficient",
transformation="voxelwise")
# Get standard space brain
mr_directory = get_data_directory()
reference = "%s/MNI152_T1_2mm_brain_mask.nii.gz" %(mr_directory)
image_paths = [image.file.path for image in [image1, image2]]
images_resamp, _ = resample_images_ref(images=image_paths,
reference=reference,
interpolation="continuous",
resample_dim=resample_dim)
# resample_images_ref will "squeeze" images, but we should keep error here for now
for image_nii, image_obj in zip(images_resamp, [image1, image2]):
if len(numpy.squeeze(image_nii.get_data()).shape) != 3:
raise Exception("Image %s (id=%d) has incorrect number of dimensions %s"%(image_obj.name,
image_obj.id,
str(image_nii.get_data().shape)))
# Calculate correlation only on voxels that are in both maps (not zero, and not nan)
image1_res = images_resamp[0]
image2_res = images_resamp[1]
binary_mask = make_binary_deletion_mask(images_resamp)
binary_mask = nib.Nifti1Image(binary_mask,header=image1_res.get_header(),affine=image1_res.get_affine())
# Will return nan if comparison is not possible
pearson_score = calculate_correlation([image1_res,image2_res],mask=binary_mask,corr_type="pearson")
# Only save comparison if is not nan
if not numpy.isnan(pearson_score):
Comparison.objects.update_or_create(image1=image1, image2=image2,
similarity_metric=pearson_metric,
similarity_score=pearson_score)
return image1.pk,image2.pk,pearson_score
else:
raise Exception("You are trying to compare an image with itself!")
def assess_similarity(image1_holdout, image2_holdout, predicted_nii1,
predicted_nii2, actual_nii1, actual_nii2):
correct = 0
lookup = dict()
lookup[actual_nii1] = image1_holdout
lookup[actual_nii2] = image2_holdout
lookup[nii1] = image1_holdout
lookup[nii2] = image2_holdout
comparison_df = pandas.DataFrame(
columns=["actual", "predicted", "cca_score"])
comparisons = [[actual_nii1, nii1], [actual_nii1, nii2],
[actual_nii2, nii1], [actual_nii2, nii2]]
count = 0
for comp in comparisons:
name1 = lookup[comp[0]]
name2 = lookup[comp[1]]
corr = calculate_correlation(comp, mask=standard_mask)
comparison_df.loc[count] = [name1, name2, corr]
count += 1
# actual predicted cca_score
#0 3186 3186 0.908997
#1 3186 420 0.485644
#2 420 3186 0.044668
#3 420 420 0.657109
# Save list of [actual,predicted] to add to confusion
predictions = []
# Calculate accuracy
acc1 = comparison_df[comparison_df.actual == image1_holdout]
acc2 = comparison_df[comparison_df.actual == image2_holdout]
# Did we predict image1 to be image1?
if acc1.loc[acc1.predicted == image1_holdout, "cca_score"].tolist(
)[0] > acc1.loc[acc1.predicted == image2_holdout, "cca_score"].tolist()[0]:
correct += 1
predictions.append([image1_holdout,
image1_holdout]) # image 1 predicted to be image 1
else:
predictions.append([image1_holdout,
image2_holdout]) # image 1 predicted to be image 2
# Did we predict image2 to be image2?
if acc2.loc[acc2.predicted == image2_holdout, "cca_score"].tolist(
)[0] > acc2.loc[acc2.predicted == image1_holdout, "cca_score"].tolist()[0]:
correct += 1
predictions.append([image2_holdout,
image2_holdout]) # image 2 predicted to be image 2
else:
predictions.append([image2_holdout,
image1_holdout]) # image 2 predicted to be image 1
return comparison_df, predictions, correct
def assess_similarity(pmid1,pmid2,predicted_nii1,predicted_nii2,actual_nii1,actual_nii2):
lookup = dict()
lookup[actual_nii1] = pmid1
lookup[actual_nii2] = pmid2
lookup[predicted_nii1] = pmid1
lookup[predicted_nii2] = pmid2
comparison_df = pandas.DataFrame(columns=["actual","predicted","cca_score"])
comparisons = [[actual_nii1,predicted_nii1],[actual_nii1,predicted_nii2],[actual_nii2,predicted_nii1],[actual_nii2,predicted_nii2]]
count=0
for comp in comparisons:
name1 = lookup[comp[0]]
name2 = lookup[comp[1]]
corr = calculate_correlation(comp,mask=standard_mask)
comparison_df.loc[count] = [name1,name2,corr]
count+=1
# actual predicted cca_score
#0 3186 3186 0.908997
#1 3186 420 0.485644
#2 420 3186 0.044668
#3 420 420 0.657109
# Calculate accuracy
correct = 0
acc1 = comparison_df[comparison_df.actual==pmid1]
acc2 = comparison_df[comparison_df.actual==pmid2]
# Save list of [actual,predicted] to add to confusion
predictions = []
# Did we predict image1 to be image1?
if acc1.loc[acc1.predicted==pmid1,"cca_score"].tolist()[0] > acc1.loc[acc1.predicted==pmid2,"cca_score"].tolist()[0]:
correct+=1
predictions.append([pmid1,pmid1])
else:
predictions.append([pmid1,pmid2])
# Did we predict image2 to be image2?
if acc2.loc[acc2.predicted==pmid2,"cca_score"].tolist()[0] > acc2.loc[acc2.predicted==pmid1,"cca_score"].tolist()[0]:
correct+=1
predictions.append([pmid2,pmid2])
else:
predictions.append([pmid2,pmid1])
return comparison_df,predictions,correct
shutil.copyfile(zmap, zmap_new)
if len(glob("%s/*.nii.gz" % (outfolder_z))) != images.shape[0]:
raise ValueError("ERROR: not all images were found in final folder %s" % (outfolder_z))
# NEEDED for future analyses,
# moved to https://github.com/vsoch/semantic-image-comparison/tree/master/analysis/wang/data
images.to_csv("%s/contrast_defined_images_filtered.tsv" % results, encoding="utf-8", sep="\t")
## STEP 2: IMAGE SIMILARITY
######################################################
from pybraincompare.compare.mrutils import make_binary_deletion_mask
from pybraincompare.compare.maths import calculate_correlation
""" Usage:
calculate_correlation(images,mask=None,atlas=None,summary=False,corr_type="pearson"):
make_binary_deletion_mask(images)
"""
standard = nibabel.load(standard)
# Function to pad ID with appropriate number of zeros
def pad_zeros(the_id, total_length=6):
return "%s%s" % ((total_length - len(str(the_id))) * "0", the_id)
# Calculate image similarity with pearson correlation
# Feasible to run in serial for small number of images
print "Calculating spatial image similarity with pearson score, complete case analysis (set of overlapping voxels) for pairwise images..."
image_ids = images.image_id.tolist()
simmatrix = pandas.DataFrame(columns=image_ids, index=image_ids)
zeros[standard_mask.get_data() != 0] = vector
return nibabel.Nifti1Image(zeros, affine=standard_mask.get_affine())
count = 0
for neurosynth_map in neurosynth_maps:
concept_name = os.path.basename(neurosynth_map).replace(
"_regparams.nii.gz", "")
concept = get_concept(name=concept_name).json[0]
neurovault_map = "%s/results/classification_final/%s_regparam_z.nii.gz" % (
base, concept["id"])
if neurovault_map in neurovault_maps:
print "Found match for %s" % (concept_name)
nsmap = nibabel.load(neurosynth_map)
nvmap = nibabel.load(neurovault_map)
score = calculate_correlation([nsmap, nvmap], mask=standard_mask)
# Let's also calculate just for overlapping voxels
cca_mask = make_binary_deletion_mask([nsmap, nvmap])
nvoxels = len(cca_mask[cca_mask != 0])
cca_mask = nibabel.Nifti1Image(cca_mask,
affine=standard_mask.get_affine())
cca_score = calculate_correlation([nsmap, nvmap], mask=cca_mask)
# And finally, since we see consistent size of cca mask (meaning not a lot of zeros) let's
# try thresholding at +/- 1. The nsmap needs to be converted to z score
image_df = get_images_df([nsmap, nvmap], mask=standard_mask)
image_df.loc[0] = (image_df.loc[0] -
image_df.loc[0].mean()) / image_df.loc[0].std()
nsmap_thresh = make_brainmap(image_df.loc[0], standard_mask)
nsmap_thresh = apply_threshold(nsmap_thresh, 1.0)
nvmap_thresh = make_brainmap(image_df.loc[1], standard_mask)
nvmap_thresh = apply_threshold(nvmap_thresh, 1.0)
reference=reference,
interpolation="continuous",
resample_dim=[8,8,8])
# SCATTERPLOT COMPARE ---- (with vector input) ---------------------------------------------------
# We are also required to provide atlas labels, colors, and correlations, so we calculate those in advance
# pybraincompare comes with mni atlas at 2 resolutions, 2mm and 8mm
# 8mm is best resolution for rendering data in browser, 2mm is ideal for svg renderings
atlases = get_mni_atlas(voxdims=["8","2"])
atlas = atlases["8"]
atlas_rendering = atlases["2"]
# This function will return a data frame with image vectors, colors, labels
# The images must already be registered / in same space as reference
corrs_df = calculate_correlation(images=images_resamp,mask=ref_resamp,atlas=atlas,corr_type="pearson")
# Option 1: Canvas based, no mouseover of points, will render 100,000's of points
output_directory = "/home/vanessa/Desktop/test"
scatterplot.scatterplot_canvas(image_vector1=corrs_df.INPUT_DATA_ONE,
image_vector2=corrs_df.INPUT_DATA_TWO,
image_names=image_names,
atlas_vector = corrs_df.ATLAS_DATA,
atlas_labels=corrs_df.ATLAS_LABELS,
atlas_colors=corrs_df.ATLAS_COLORS,
output_directory=output_directory)
# Option 2: D3 based, with mouseover of points, limited sampling of images
html_snippet,data_table = scatterplot.scatterplot_compare_vector(image_vector1=corrs_df.INPUT_DATA_ONE,
image_vector2=corrs_df.INPUT_DATA_TWO,
actual_nii2[standard_mask.get_data()!=0] = actual2.tolist()
actual_nii1 = nibabel.Nifti1Image(actual_nii1,affine=standard_mask.get_affine())
actual_nii2 = nibabel.Nifti1Image(actual_nii2,affine=standard_mask.get_affine())
# Make a dictionary to lookup images based on nifti
lookup = dict()
lookup[actual_nii1] = image1_holdout
lookup[actual_nii2] = image2_holdout
lookup[nii1] = image1_holdout
lookup[nii2] = image2_holdout
comparison_df = pandas.DataFrame(columns=["actual","predicted","cca_score"])
comparisons = [[actual_nii1,nii1],[actual_nii1,nii2],[actual_nii2,nii1],[actual_nii2,nii2]]
count=0
for comp in comparisons:
name1 = lookup[comp[0]]
name2 = lookup[comp[1]]
corr = calculate_correlation(comp,mask=standard_mask)
comparison_df.loc[count] = [name1,name2,corr]
count+=1
# actual predicted cca_score
#0 3186 3186 0.908997
#1 3186 420 0.485644
#2 420 3186 0.044668
#3 420 420 0.657109
comparison_dfs = comparison_dfs.append(comparison_df)
# Calculate accuracy
acc1 = comparison_df[comparison_df.actual==image1_holdout]
acc2 = comparison_df[comparison_df.actual==image2_holdout]
# Did we predict image1 to be image1?
affine=standard_mask.get_affine())
# Make a dictionary to lookup images based on nifti
lookup = dict()
lookup[actual_nii1] = image1_holdout
lookup[actual_nii2] = image2_holdout
lookup[nii1] = image1_holdout
lookup[nii2] = image2_holdout
comparison_df = pandas.DataFrame(
columns=["actual", "predicted", "cca_score"])
comparisons = [[actual_nii1, nii1], [actual_nii1, nii2],
[actual_nii2, nii1], [actual_nii2, nii2]]
count = 0
for comp in comparisons:
name1 = lookup[comp[0]]
name2 = lookup[comp[1]]
corr = calculate_correlation(comp, mask=standard_mask)
comparison_df.loc[count] = [name1, name2, corr]
count += 1
# actual predicted cca_score
#0 3186 3186 0.908997
#1 3186 420 0.485644
#2 420 3186 0.044668
#3 420 420 0.657109
comparison_dfs = comparison_dfs.append(comparison_df)
# Calculate accuracy
acc1 = comparison_df[comparison_df.actual == image1_holdout]
acc2 = comparison_df[comparison_df.actual == image2_holdout]
# Did we predict image1 to be image1?
interpolation="continuous",
resample_dim=[8, 8, 8])
# SCATTERPLOT COMPARE ---- (with vector input) ---------------------------------------------------
# We are also required to provide atlas labels, colors, and correlations, so we calculate those in advance
# pybraincompare comes with mni atlas at 2 resolutions, 2mm and 8mm
# 8mm is best resolution for rendering data in browser, 2mm is ideal for svg renderings
atlases = get_mni_atlas(voxdims=["8", "2"])
atlas = atlases["8"]
atlas_rendering = atlases["2"]
# This function will return a data frame with image vectors, colors, labels
# The images must already be registered / in same space as reference
corrs_df = calculate_correlation(images=images_resamp,
mask=ref_resamp,
atlas=atlas,
corr_type="pearson")
# Option 1: Canvas based, no mouseover of points, will render 100,000's of points
output_directory = "/home/vanessa/Desktop/test"
scatterplot.scatterplot_canvas(image_vector1=corrs_df.INPUT_DATA_ONE,
image_vector2=corrs_df.INPUT_DATA_TWO,
image_names=image_names,
atlas_vector=corrs_df.ATLAS_DATA,
atlas_labels=corrs_df.ATLAS_LABELS,
atlas_colors=corrs_df.ATLAS_COLORS,
output_directory=output_directory)
# Option 2: D3 based, with mouseover of points, limited sampling of images
html_snippet, data_table = scatterplot.scatterplot_compare_vector(
image_vector1=corrs_df.INPUT_DATA_ONE,
zmap_new = "%s/%s" %(outfolder_z,os.path.split(zmap)[-1])
shutil.copyfile(zmap,zmap_new)
if len(glob("%s/*.nii.gz" %(outfolder_z))) != images.shape[0]:
raise ValueError("ERROR: not all images were found in final folder %s" %(outfolder_z))
# NEEDED for future analyses,
# moved to https://github.com/vsoch/semantic-image-comparison/tree/master/analysis/wang/data
images.to_csv("%s/contrast_defined_images_filtered.tsv" %results,encoding="utf-8",sep="\t")
## STEP 2: IMAGE SIMILARITY
######################################################
from pybraincompare.compare.mrutils import make_binary_deletion_mask
from pybraincompare.compare.maths import calculate_correlation
""" Usage:
calculate_correlation(images,mask=None,atlas=None,summary=False,corr_type="pearson"):
make_binary_deletion_mask(images)
"""
standard = nibabel.load(standard)
# Function to pad ID with appropriate number of zeros
def pad_zeros(the_id,total_length=6):
return "%s%s" %((total_length - len(str(the_id))) * "0",the_id)
# Calculate image similarity with pearson correlation
# Feasible to run in serial for small number of images
print "Calculating spatial image similarity with pearson score, complete case analysis (set of overlapping voxels) for pairwise images..."
image_ids = images.image_id.tolist()
simmatrix = pandas.DataFrame(columns=image_ids,index=image_ids)
for id1 in image_ids:
def make_brainmap(vector,standard_mask):
zeros = numpy.zeros(standard_mask.shape)
zeros[standard_mask.get_data()!=0] = vector
return nibabel.Nifti1Image(zeros,affine=standard_mask.get_affine())
count=0
for neurosynth_map in neurosynth_maps:
concept_name = os.path.basename(neurosynth_map).replace("_regparams.nii.gz","")
concept = get_concept(name=concept_name).json[0]
neurovault_map = "%s/results/classification_final/%s_regparam_z.nii.gz" %(base,concept["id"])
if neurovault_map in neurovault_maps:
print "Found match for %s" %(concept_name)
nsmap = nibabel.load(neurosynth_map)
nvmap = nibabel.load(neurovault_map)
score = calculate_correlation([nsmap,nvmap],mask=standard_mask)
# Let's also calculate just for overlapping voxels
cca_mask = make_binary_deletion_mask([nsmap,nvmap])
nvoxels = len(cca_mask[cca_mask!=0])
cca_mask = nibabel.Nifti1Image(cca_mask,affine=standard_mask.get_affine())
cca_score = calculate_correlation([nsmap,nvmap],mask=cca_mask)
# And finally, since we see consistent size of cca mask (meaning not a lot of zeros) let's
# try thresholding at +/- 1. The nsmap needs to be converted to z score
image_df = get_images_df([nsmap,nvmap],mask=standard_mask)
image_df.loc[0] = (image_df.loc[0] - image_df.loc[0].mean()) / image_df.loc[0].std()
nsmap_thresh = make_brainmap(image_df.loc[0],standard_mask)
nsmap_thresh = apply_threshold(nsmap_thresh,1.0)
nvmap_thresh = make_brainmap(image_df.loc[1],standard_mask)
nvmap_thresh = apply_threshold(nvmap_thresh,1.0)
cca_mask_thresh = make_binary_deletion_mask([nsmap_thresh,nvmap_thresh])
nvoxels_thresh = len(cca_mask_thresh[cca_mask_thresh!=0])
