def get_areal_features(root, features_path, masks_dir, n_bins = 100):
prep_out_path(features_path)
files = os.listdir(root)
df = pd.DataFrame(columns = range(n_bins * 2) + ['name', 'level'])
names = pd.read_csv(labels_file)
print "Starting extraction: ", time_now_str()
for j, f in enumerate(files):
label = names.loc[names['image'] == path.splitext(f)[0]]
start = time.time()
imr = ImageReader(root, f, masks_dir, gray_scale = True)
drusen = get_predicted_region(imr.image, Labels.Drusen)
blood = get_predicted_region(imr.image, Labels.Haemorage)
Bc = np.ones((5, 5))
labels_drusen, n_drusen = mh.label(drusen, Bc)
labels_blood, n_blood = mh.label(blood, Bc)
area = float(cv2.countNonZero(imr.mask))
outp = np.array([], dtype = np.int)
# sizes excluding background
sizes_drusen = mhl.labeled_size(labels_drusen)[1:] / area
sizes_blood = mhl.labeled_size(labels_blood)[1:] / area
hist_druzen, _ = np.histogram(sizes_drusen, n_bins, (0, 1e-3))
hist_blood, _ = np.histogram(sizes_blood, n_bins, (0, 1e-3))
outp = np.r_[outp, hist_druzen]
outp = np.r_[outp, hist_blood]
outp = np.r_[outp, label.values[0]]
df.loc[j] = outp
print "Extracted: {0}, took {1:02.2f} sec ".format(f, time.time() - start)
# write out the csv
df.to_csv(path.join(features_path, prefix + ".csv"), index = False, header=True)
print "Extracted: ", prefix, "@", time_now_str()
def filter_labeled(labeled,
remove_bordering=False,
min_size=None,
max_size=None):
'''Filter labeled regions based on a series of conditions
.. versionadded :: 1.4.1
Parameters
----------
labeled : labeled array
remove_bordering : bool, optional
whether to remove regions that touch the border
min_size : int, optional
Minimum size (in pixels) of objects to keep (default is no minimum)
max_size : int, optional
Maximum size (in pixels) of objects to keep (default is no maximum)
Returns
-------
filtered : labeled array
nr : int
number of new labels
'''
from mahotas.labeled import remove_regions, labeled_size
import mahotas as mh
labeled = _as_labeled(labeled, labeled, 'filter_labeled')
if remove_bordering:
labeled = mh.labeled.remove_bordering(labeled)
labeled, nr = mh.labeled.relabel(labeled)
else:
nr = labeled.max()
to_keep = np.ones(nr + 1, bool)
if min_size is not None or max_size is not None:
sizes = labeled_size(labeled)
if min_size:
to_keep &= (sizes >= min_size)
if max_size:
to_keep &= (sizes <= max_size)
to_keep[0] = True
to_remove = np.where(~to_keep)
labeled = remove_regions(labeled, to_remove)
labeled, nr = mh.labeled.relabel(labeled, inplace=True)
return labeled, nr
def filter_labeled(labeled, remove_bordering=False, min_size=None, max_size=None):
"""Filter labeled regions based on a series of conditions
.. versionadded :: 1.4.1
Parameters
----------
labeled : labeled array
remove_bordering : bool, optional
whether to remove regions that touch the border
min_size : int, optional
Minimum size (in pixels) of objects to keep (default is no minimum)
max_size : int, optional
Maximum size (in pixels) of objects to keep (default is no maximum)
Returns
-------
filtered : labeled array
nr : int
number of new labels
"""
from mahotas.labeled import remove_regions, labeled_size
import mahotas as mh
labeled = _as_labeled(labeled, labeled, "filter_labeled")
if remove_bordering:
labeled = mh.labeled.remove_bordering(labeled)
labeled, nr = mh.labeled.relabel(labeled)
else:
nr = labeled.max()
to_keep = np.ones(nr + 1, bool)
if min_size is not None or max_size is not None:
sizes = labeled_size(labeled)
if min_size:
to_keep &= sizes >= min_size
if max_size:
to_keep &= sizes <= max_size
to_keep[0] = True
to_remove = np.where(~to_keep)
labeled = remove_regions(labeled, to_remove)
labeled, nr = mh.labeled.relabel(labeled, inplace=True)
return labeled, nr
def detectMyotube(self,
segmentationMethod='seg1',
sizeThresh=0,
tophat=True,
tophatImgList=[]):
if tophat == True and tophatImgList == []:
tophatImgList = self.tophatAllPlanes()
elif tophat == True and tophatImgList != []:
#tophatImgList = tophatImgList[tophatImgList.keys()[0]]
tophatImgList = tophatImgList[0]
elif tophat == False:
tophatImgList = self.images
# median -> histeq -> otsu -> segmentation (histeq and otsu by region)
if segmentationMethod == 'seg1':
img_mip = self.maximumIntensityProjection(tophatImgList)
img_median = self.smooth(img_mip)
img_histeq, _ = imtools.histeq(img_median)
T = otsu(np.uint(img_histeq), ignore_zeros=True)
img_bin = (np.uint(img_histeq) > T)
img_labeled, _ = label(img_bin)
markers, counts = self.segmentTubes1(img_labeled, img_histeq)
# segmentation by watershed
img_labeled = img_bin * cwatershed(-distance(img_bin), markers)
result = {
'MIP': img_mip,
'median': img_median,
'histEq': img_histeq,
'otsu': T,
'bin': img_bin
}
# median -> otsu -> segmentation (histeq and otsu by region)
elif segmentationMethod == 'seg2':
img_mip = self.maximumIntensityProjection(tophatImgList)
img_median = self.smooth(img_mip)
T = otsu(np.uint(img_median), ignore_zeros=True)
img_bin = (np.uint(img_median) > T)
img_labeled, _ = label(img_bin)
markers, counts = self.segmentTubes2(img_labeled, img_median)
# segmentation by watershed
img_labeled = img_bin * cwatershed(-distance(img_bin), markers)
result = {
'MIP': img_mip,
'median': img_median,
'otsu': T,
'bin': img_bin
}
# median -> histeq -> otsu -> segmentation (histeq and cut regions less than mean-intensity by region)
elif segmentationMethod == 'seg3':
img_mip = self.maximumIntensityProjection(tophatImgList)
img_median = self.smooth(img_mip)
img_histeq, _ = imtools.histeq(img_median)
T = otsu(np.uint(img_histeq), ignore_zeros=True)
img_bin = (np.uint(img_histeq) > T)
img_labeled, _ = label(img_bin)
markers, counts = self.segmentTubes3(img_labeled, img_histeq)
# segmentation by watershed
img_labeled = img_bin * cwatershed(-distance(img_bin), markers)
result = {
'MIP': img_mip,
'median': img_median,
'histEq': img_histeq,
'otsu': T,
'bin': img_bin
}
# median -> histeq -> otsu -> segmentation (cut regions less than mean-intensity by region)
elif segmentationMethod == 'seg4':
img_mip = self.maximumIntensityProjection(tophatImgList)
img_median = self.smooth(img_mip)
img_histeq, _ = imtools.histeq(img_median)
T = otsu(np.uint(img_histeq), ignore_zeros=True)
img_bin = (np.uint(img_histeq) > T)
img_labeled, _ = label(img_bin)
markers, counts = self.segmentTubes4(img_labeled, img_histeq)
# segmentation by watershed
img_labeled = img_bin * cwatershed(-distance(img_bin), markers)
result = {
'MIP': img_mip,
'median': img_median,
'histEq': img_histeq,
'otsu': T,
'bin': img_bin
}
# median -> otsu -> segmentation (cut regions less than mean-intensity by region)
elif segmentationMethod == 'seg5':
img_mip = self.maximumIntensityProjection(tophatImgList)
img_median = self.smooth(img_mip)
T = otsu(np.uint(img_median), ignore_zeros=True)
img_bin = (np.uint(img_median) > T)
img_labeled, _ = label(img_bin)
markers, counts = self.segmentTubes4(img_labeled, img_median)
# segmentation by watershed
img_labeled = img_bin * cwatershed(-distance(img_bin), markers)
result = {
'MIP': img_mip,
'median': img_median,
'otsu': T,
'bin': img_bin
}
# non-segmentation
else:
img_mip = self.maximumIntensityProjection(tophatImgList)
img_median = self.smooth(img_mip)
img_histeq, _ = imtools.histeq(img_median)
T = otsu(np.uint(img_histeq))
img_bin = (np.uint(img_histeq) > T)
img_labeled, counts = label(img_bin)
result = {
'MIP': img_mip,
'median': img_median,
'histEq': img_histeq,
'otsu': T,
'bin': img_bin
}
print('non-segmentation')
print('Otsu\'s threshold:', T)
print('Found {} objects.'.format(counts))
sizes = labeled_size(img_labeled)
img_labeled = remove_regions_where(
img_labeled, sizes < sizeThresh) #origin 10000, triangle 8585
img_relabeled, counts = relabel(img_labeled)
result['label'] = img_relabeled
result['count'] = counts
print('After filtering and relabeling, there are {} objects left.'.
format(counts))
result['labeledSkeleton'] = self.labeledSkeleton(img_relabeled)
return ProcessImages(result)
extractor = DarkBrightDetector(preprocessed, orig, im_file, masks, is_debug = False)
labels = extractor.find_bright_regions()
drusen = extractor.get_predicted_region(Labels.Drusen)
blood = extractor.get_predicted_region(Labels.Haemorage)
Bc = np.ones((5, 5))
labels_drusen, n_drusen = mh.label(drusen, Bc)
labels_blood, n_blood = mh.label(blood, Bc)
area = float(cv2.countNonZero(extractor.mask))
outp = np.array([], dtype = np.int)
# sizes excluding background
sizes_drusen = mhl.labeled_size(labels_drusen)[1:] / area
sizes_blood = mhl.labeled_size(labels_blood)[1:] / area
hist_druzen, _ = np.histogram(sizes_drusen, n_bins, (0, 1e-3))
hist_blood, _ = np.histogram(sizes_blood, n_bins, (0, 1e-3))
outp = np.r_[outp, hist_druzen]
outp = np.r_[outp, hist_blood]
outp = np.r_[outp, i]
df.loc[j] = outp
j += 1
print "Extracted: {0}, took {1:02.2f} sec ".format(im_file, time.time() - start)
# write out the csv
df.to_csv(path.join(output, prefix + ".txt"), index = False, header=False)
print "Extracted: ", prefix, "@", time_now_str()
def __init__(self,dir=None,roi=None,label_image=None,mask=True,exp_type=None,mask_type=1,split=False,back_ground_subtract=True,plot_back_hist=False,SBtype=1,backf="mean",stim = 400,frametime=25,areathreshold=5):
"""
exp_type 0: error
exp_type 1: 0,3,10,20,30,50,100,50,30,20,10,3,0V
exp_type 2: 0x3,3x3,10x3,20x3,30x3,50x3,100x1,50x3,30x3,20x3,10x3,3x3,0x3Vを１往復
exp_type 3: 0x3,3x3,10x3,20x3,30x3,50x3,100x1
exp_type 4: 0,3,5,10,15,20,25,30,35,40,50,100,50,40,35,30,25,20,15,10,5,3,0Vを５往復
exp_type 5: 0,3,5,10,15,20,25,30,35,40,50,100,50,40,35,30,25,20,15,10,5,3Vを2往復
exp_type 6: 0,5,10,15,20,25,30,35,40,50,100,50,40,35,30,25,20,15,10,5,0Vを2往復
exp_type 7: 0,5,10,15,20,25,30,35,40,50,100,50,40,35,30,25,20,15,10,5,0Vを1往復
exp_type 8: 0,5,10,15,20,25,30,30,25,20,15,10,5,0Vを4往復
"""
"""
SBtype 0:no subtract
SBtype 1:every photos subtract by every photos's background
SBtype 2:every photos subtract by 1 Stream's background
"""
print("program has started")
self.back_ground_subtract = back_ground_subtract
self.exp_type = exp_type
self.dir = dir.replace("\\","/")
self.expname = self.dir.split("/")[-1]
self.back_feature = backf
self.frame_time = frametime
self.area_thresh = areathreshold
self.stim_time = stim
if back_ground_subtract:
if SBtype == 1:self.out_dir=self.dir + "/output_ind_subback_by_"+backf
elif SBtype == 2:self.out_dir=self.dir + "/output_stream_subback_by_"+backf
else:self.out_dir=self.dir + "/output"
try:os.mkdir(self.out_dir)
except:print("output has existed already")
print(self.out_dir)
self.interval = self.get_interval()
self.feature = ("f_basal","b_basal","peak","auc","modified_auc","auc_divided_by_peak")
if split:
stream_dir = glob.glob(dir+"/split/*V*")
stream_dir = [i.replace("\\","/") for i in stream_dir]
else:
stream_fname = glob.glob(dir+"/Stream/*.tif")
stream_fname = [i.replace("\\","/") for i in stream_fname]
streamname = [i.split("/")[-1] for i in stream_fname]
self.Vol_list = [self.get_voltage(i) for i in streamname]
self.Vol_str_list = [str(self.get_voltage(i))+"V" for i in streamname]
all_vol = list(set(self.Vol_list))
repeat_num_each_vol = [self.Vol_list.index(i) for i in all_vol]
self.repeat_num = min(repeat_num_each_vol)
if mask:
start_time = self.get_time()
#read mask image
mask_dir = glob.glob(dir+"/other/"+str(mask_type)+"*mask*.tif")
mask_dir = mask_dir[0].replace("\\","/")
mask_fig = io.imread(mask_dir)
self.labelimage = measure.label(mask_fig)
back_ground_label_dir = glob.glob(dir+"/other/back.tif")
back_ground_label_dir = back_ground_label_dir[0].replace("\\","/")
back_ground_label_image = io.imread(back_ground_label_dir)
back_ground_label = measure.label(back_ground_label_image)
# remove small object
sizes = mal.labeled_size(self.labelimage)
self.labelimage = mal.remove_regions_where(self.labelimage,sizes<self.area_thresh)
self.labelimage,counts = mal.relabel(self.labelimage)
self.label_num = self.labelimage.max()
# get each average of intensity and remove back ground
label_props = regionprops(self.labelimage)
self.label_area = [i.area for i in label_props]
self.back = []
self.intensity_df_list = [self.get_stream_label_intensity(i,back_ground_label,SBtype=SBtype,plot_hist=plot_back_hist) for i in stream_fname]
self.back= pd.DataFrame(self.back)
self.back.columns = ["mean","minimum","median","mode"]
self.back.to_csv(self.out_dir+"/background.csv")
bound = np.linspace(0,self.label_num,self.label_num+1)
norm = colors.BoundaryNorm(boundaries=bound,ncolors=256)
plt.imshow(self.labelimage,cmap ="gist_ncar" ,norm=norm)
cbar=plt.colorbar()
cbar.set_label(label="cell ID")
plt.savefig(self.out_dir+"/labeled_image.png")
end_time=self.get_time()
print("intensity was mesured successfuly!!")
print("times:"+str(int(end_time - start_time))+"s")
elif label_image:
self.labelimage = self.label_ndarray(dir)
self.label_num = self.labelimage.max()
self.intensity_df_list = [self.get_stream_label_intensity(i) for i in stream_dir]
print("intensity was mesured successfuly!!")
label_props = regionprops(self.labelimage)
self.label_area = [i.area for i in label_props]
elif roi :
csv_dir = glob.glob(dir+"/csv/*.csv")
csv_dir = [i.replace("\\","/") for i in csv_dir]
self.intensity_df_list = [pd.read_csv(i) for i in csv_dir ]
time=list(range(len(self.intensity_df_list[0])))
time = [i*self.frame_time for i in time ]
for i in self.intensity_df_list:
i.index=time
self.intensity_df_list = [i.iloc[:,1:] for i in self.intensity_df_list]
print("intensity was mesured successfuly!!")
self.label_num = len(self.intensity_df_list[0].columns)
#self.x_label,self.legend_label = dd.get_x_label(self.exp_type)
#self.get_propaty()
self.save_csv()
is_debug=False)
labels = extractor.find_bright_regions()
drusen = extractor.get_predicted_region(Labels.Drusen)
blood = extractor.get_predicted_region(Labels.Haemorage)
Bc = np.ones((5, 5))
labels_drusen, n_drusen = mh.label(drusen, Bc)
labels_blood, n_blood = mh.label(blood, Bc)
area = float(cv2.countNonZero(extractor.mask))
outp = np.array([], dtype=np.int)
# sizes excluding background
sizes_drusen = mhl.labeled_size(labels_drusen)[1:] / area
sizes_blood = mhl.labeled_size(labels_blood)[1:] / area
hist_druzen, _ = np.histogram(sizes_drusen, n_bins, (0, 1e-3))
hist_blood, _ = np.histogram(sizes_blood, n_bins, (0, 1e-3))
outp = np.r_[outp, hist_druzen]
outp = np.r_[outp, hist_blood]
outp = np.r_[outp, i]
df.loc[j] = outp
j += 1
print "Extracted: {0}, took {1:02.2f} sec ".format(
im_file,
time.time() - start)
# write out the csv