def delete_internal_leaves_jsome2jall(jall_name, jsome_name):
#disconnect vertices from g that are disconnect in h
try:
g, attributes = graph_analysis.input_graph(
jall_name, ["history", "vertex_offsets"])
print("Successfully read in the %s\n" % jall_name)
except:
print("Error reading in the %s\n" % jall_name)
h = graph_analysis.input_graph(jsome_name)
if len(g.vertices) != len(h.vertices):
print "ERROR: delete_internal_leaves_jsome2jall, the number of vertices of g and h are not equal!!\nAborted!"
exit(0)
for i in xrange(len(g.vertices)):
if len(h.vertices[i].edges) == 0:
g.disconnect_vertex(i)
out_name = jall_name[:-3] + "_delleave.db"
history = '\n>>> %s: delete_internal_leaves on join_all using the join_some result' % (
ctime(time())) ##argv = ['code.py', 'input.db', 'output']
if attributes.has_key("history"):
history = attributes["history"] + "\n" + history
del attributes['history']
graph_analysis.output_graph(out_name, g, history, attributes)
print("Succefully wrote the %s\n" % out_name)
return out_name
"The --clobber option is needed to overwrite an existing file."
##1. borrow from delete_internal_leaves to find segments that are inside
##2. borrow from smooth_graph to decide which one is parent and which is daughter branch that needs to be deleted
##3. borrow from adjust_junction to find the nearest connection point with preserving the topology
history = '>>> %s: %s' % (time.ctime(time.time()), string.join(argv))
ls = []
if options.labels:
ls = options.labels.split(',')
ls = [int(l) for l in ls]
g, attributes = graph_analysis.input_graph(input_file,
["history", "vertex_offsets"])
occlusions, encompassing_e = detect_internal_segments(
g, ls, options.scale, options.offset)
for e in occlusions.keys():
if e not in encompassing_e: #this way only edges that have no other edge inside them will be deleted
g.remove_edge(e)
#NOTE: what we should actually do is to check if all the vertices of an edge are inside another edge => remove that edge
# if not, then only disconnect_vertex of those inside, then reconnect the rest of the vertices to the encompassing_e
if attributes.has_key("history"):
history = attributes["history"] + "\n" + history
del attributes['history']
output_file = output_file.replace("_groundtruthlabel", "")
output_file = output_file.replace("_cyl", "")
else:
print len(args), ": ", args
parser.error("incorrect number of arguments")
if options.remap:
output_file = output_file[:-4] + "_remap.mnc"
if not options.mask:
output_file = output_file[:-4] + "_notmasked.mnc"
print output_file
if not options.clobber and os.path.exists(output_file):
raise SystemExit, \
"The --clobber option is needed to overwrite an existing file."
g = graph_analysis.input_graph(input_file)
#g= graph_analysis.input_graph("/micehome/sghanavati/Documents/data/journal1data_c57_feb13/LOO_final_revised/autolabel_c57_1_4_S_cyl.db")
#g= graph_analysis.input_graph("./c57_1_9Nov12/c57_1_graph_add_coverage_delleave_radi1.06_smooth2_simplified_rmisolate_features_groundtruthlabel_cyl_revised.db")
mr_atlas_file = "/projects/souris/sghanavati/data/c57_male_female_mri_atlas/c57_brain_segmentation_mnc2_merged_reg2vascular.mnc"
##mr_atlas_file = "/projects/souris/sghanavati/data/c57_male_female_mri_atlas/c57_brain_segmentation_mnc2_merged_reg2vascular_downsample_merge.mnc"
##labels = [2,43,102,143,122,8,5,108,105,35,135,13,236,111,191,190,91,90,200,9,7,10,196,96,198,68,227,168,169,46,12,49,45,14,15,17,18,3,4]
#arteries : 8:108,5:105,135:35,111:35,236:35,191:91,190:90,68:168,227:169
if not options.labels:
labels = [
122, 8, 5, 108, 105, 35, 135, 13, 236, 111, 191, 190, 91, 90, 68,
227, 168, 169, 46, 12, 49, 45, 14, 15, 17, 18, 3, 4
]
if options.veins:
labels = [
if not options.clobber and os.path.exists(output_file):
raise SystemExit, \
"The --clobber option is needed to overwrite an existing file."
radius_threshold = options.radius_threshold
length_threshold = options.length_threshold
intermed_threshold = options.intermed_threshold
if not options.clobber and os.path.exists(output_file):
raise SystemExit, \
"The --clobber option is needed to overwrite an existing file."
try:
g, attributes = graph_analysis.input_graph(
input_file, ["history", "vertex_offsets"
]) # open graph data and copy contents to memory
#g = graph_analysis.input_graph("tree_mask_blur_delleaves.db")
print("Succefully read in the input.db\n")
except:
print("Error reading in the input.db\n")
h = copy.deepcopy(g)
# simplify h by reducing to vessel segments
graph_analysis.simplify_graph_retaining_intermediaries(h)
# estimate lengths and average diameters of each segment
graph_analysis.estimate_edge_diameters(h)
graph_analysis.estimate_edge_lengths(h)
remove_edge_num = 0
for e in h.edge_list():
ltriples = options.landmark3.split(',')
labeltriples = []
for pair in ltriples:
labels = pair.split(':')
labels = [int(l) for l in labels]
labeltriples.append(set(labels))
all_l = [list(l)[0] for l in labeltriples] + [
list(l)[1] for l in labeltriples
] + [list(l)[2] for l in labeltriples]
unique_triple_l = []
for l in all_l:
if l not in unique_triple_l:
unique_triple_l.append(l)
if len(args) == 2:
g = graph_analysis.input_graph(input_file)
landmarks = []
according_l = []
#for e in g.edge_list():
#if len(vessel_analysis.find_neighbor_edges_asymmetrical(g,e,0)) not in [0,2]:
#print e,":", vessel_analysis.find_neighbor_edges_asymmetrical(g,e,0)
#if len(vessel_analysis.find_neighbor_edges_asymmetrical(g,e,1)) not in [0,2]:
#print e,":", vessel_analysis.find_neighbor_edges_asymmetrical(g,e,1)
if options.landmark:
for e in g.edge_list():
if g.edge_property(e, 'label') in unique_l:
e1_neighbs = vessel_analysis.find_neighbor_edges_asymmetrical(
g, e, 0)
e2_neighbs = vessel_analysis.find_neighbor_edges_asymmetrical(
if options.labels:
ls = options.labels.split(',')
ls = [int(l) for l in ls]
else:
ls = labelNumeric2Name.keys()
if options.combine_labels:
lpairs = options.combine_labels.split(',')
labelpairs = {}
for pair in lpairs:
plabels = pair.split(':')
plabels = [int(l) for l in plabels]
labelpairs[plabels[0]] = plabels[1]
ref = graph_analysis.input_graph(groundturht_file)
g = graph_analysis.input_graph(test_file)
g_gd = graph_analysis.input_graph(test_file_gd)
g_s = graph_analysis.input_graph(test_file_s)
for e in g.edge_list():
if int(g.edge_property(e, 'cyl_label')) in labelpairs.keys():
g.set_edge_property(
e, 'cyl_label', labelpairs[int(g.edge_property(e,
'cyl_label'))])
for e in g_gd.edge_list():
if int(g_gd.edge_property(e, 'cyl_label')) in labelpairs.keys():
g_gd.set_edge_property(
e, 'cyl_label',
labelpairs[int(g_gd.edge_property(e, 'cyl_label'))])
else:
input_files = args[0:-1]
output_file = args[-1]
if not options.clobber and os.path.exists(output_file):
raise SystemExit, \
"The --clobber option is needed to overwrite an existing file."
label_vals = {}
weight_vals = {}
weighted_label_vals = {}
for input_file in input_files:
# reads in the graph to be labeled
try:
g, attributes = graph_analysis.input_graph(
input_file, ["history", "vertex_offsets"])
print("Succefully read in the %s\n" % input_file)
except:
print("Error reading in the %s\n" % input_file)
for e in g.edge_list():
l = g.edge_property(e, 'label')
if l not in weight_vals.keys():
weight_vals[l] = 0
if l not in weighted_label_vals.keys():
weighted_label_vals[l] = 0
if options.labelprop == 'estimated_label':
weight_vals[l] += g.edge_property(
e, 'diameter') * g.edge_property(
e, 'diameter') * g.edge_property(
e, 'length') #cylinder volume = pi*r^2*length
print(cmd)
sys.stdout.flush()
os.system(cmd)
cmd = ("modify_db_intermediaries.py %s %s %s" %
(input_file[:-3] + "graph2graph.db", ref_graph,
output_file[:-3] + "_nofeature.db"))
print(cmd)
sys.stdout.flush()
os.system(cmd)
#output_file = output_file[:-3]+"_intm.db"
try:
g, attributes = graph_analysis.input_graph(
output_file[:-3] + "_nofeature.db",
["history", "vertex_offsets"
]) # open graph data and copy contents to memory
#g = graph_analysis.input_graph("tree_mask_blur_delleaves.db")
print("Succefully read in the %s\n" % output_file[:-3] +
"_nofeature.db")
sys.stdout.flush()
except:
print("Error reading in the %s\n" % output_file[:-3] + "_nofeature.db")
sys.stdout.flush()
#redo the simplified graph and feature extraction for new edges!
print len(g.edge_list()), " ", len(g.vertices), "\nsimplifying edges:"
sys.stdout.flush()
#for e in g.edge_list():
#print e, " ",
#print " "
def graph2featureVect(training_files,featureNames):
graphs=[]
for training_file in training_files:
try:
graphs.append( graph_analysis.input_graph(training_file)) # open graph data and copy contents to memory
print ("Succefully read in %s\n" %training_file)
except:
print("Error reading in %s\n" %training_file)
#### initialize the feature_vector to be zeros(#datapoints=sum(len(g.edge_list()) w label!=0 , len(featureNames))
## initialize the target_vector to be zeros(#datapoints=sum(len(g.edge_list()) w label!=0 , 1)
MRI_labels=[]
if 'mri_label_dist' in featureNames:
MRI_labels=[l[0] for l in graphs[0].edge_property(graphs[0].edge_list()[0],'mri_label_dist')]
feature_vector = Matlib.empty((0,len(featureNames)+len(MRI_labels)-1),float)
else:
feature_vector = Matlib.empty((0,len(featureNames)),float)
target_vector = [] #Matlib.empty((0,1),float)
labelNumerics = []
edge_w_indx = {}
g_cnt=-1
e_cnt = 0
for g in graphs:
g_cnt =g_cnt+1
for e in g.edge_list():
if 'label' not in g.edge_properties(e).keys():
print ("ERROR! The edge (%d,%d) in graph %s doesn't have label property.\nAborted!\n" %(e[0],e[1],training_files[g_cnt]))
exit (0)
#else:
if g.edge_property(e,'label')>-1: #including the edges with label 0
#target_vector= numpy.vstack([target_vector, array(g.edge_property(e,'label'))])
target_vector.append(int(g.edge_property(e,'label')))
if g.edge_property(e,'label') not in labelNumerics and g.edge_property(e,'label')>0:
labelNumerics.append(int(g.edge_property(e,'label')))
features=[]
for f in featureNames:
if f not in g.edge_properties(e).keys():
print ("ERROR! The edge (%d,%d) in graph %s doesn't have feature %s property.\nAborted!\n" %(e[0],e[1],training_files[g_cnt],f))
exit (0)
if not f== 'mri_label_dist' and not f=='rel_dir' and not f=='rel_diameter':
features.append(g.edge_property(e,f))
elif f== 'mri_label_dist':
for mr_l in MRI_labels:
#if type(g.edge_property(e,'mri_label_dist'))==list:
#print mr_l,":",e, " list ", training_files[g_cnt]
#ind=[l[0] for l in g.edge_property(e,'mri_label_dist')].index(mr_l)
#else:
#print mr_l,":",e, ", ", training_files[g_cnt]
#ind=[l[0] for l in g.edge_property(e,'mri_label_dist').tolist()].index(mr_l)
mri_label_dist_list = [int(l[0]) for l in g.edge_property(e,'mri_label_dist')]
if mr_l in mri_label_dist_list:
ind = mri_label_dist_list.index(mr_l)
features.append(g.edge_property(e,'mri_label_dist')[ind][1])
elif f=='rel_dir' or f=='rel_diameter':
rel_f = 1.0
for rel_i in range(min(len(g.edge_property(e,f)),4)): #we only consider up to 4 adjacent edges, if there are less 1.0 will be used
rel_f = rel_f * g.edge_property(e,f)[rel_i]
features.append(rel_f)
feature_vector = numpy.vstack([feature_vector, array(features)]) #hstack #a = matrix([[10,20,30]]); a=append(a,[[1,2,3]],axis=0); a=append(a,[[15],[15]],axis=1)
edge_w_indx[e_cnt]= e
e_cnt = e_cnt+1
#### !!find neighbouring edges and in iterations find their
adjacency_matrix = (1.0/len(labelNumerics))*Matlib.ones((len(labelNumerics),len(labelNumerics)+1),float) #### smoothing (for 0s in the adj_matrix)! to be minimum of 1 occurance for the nieghbourhood!
edge_neighboring_indx = {}
g_cnt=-1
e_cnt = 0
for g in graphs:
g_cnt =g_cnt+1
for e in g.edge_list():
#if 'label' not in g.edge_properties(e).keys():
#print ("ERROR! The edge (%d,%d) in graph %s doesn't have label property.\nAborted!\n" %(e[0],e[1],training_files[g_cnt]))
#exit (0)
#else:
if g.edge_property(e,'label')>0:
indx0= labelNumerics.index(g.edge_property(e,'label'))
e1_neighbours= g.vertices[e[0]].edges
#e1_neighbours.remove(e2)
for v in e1_neighbours:
if v!=e[1]:
neighbor_edge=tuple((min(e[0],v),max(e[0],v)))
if g.edge_property(neighbor_edge,'label')>0:
indx1= labelNumerics.index(g.edge_property(neighbor_edge,'label'))
adjacency_matrix[indx0,indx1]= adjacency_matrix[indx0,indx1]+1
e2_neighbours= g.vertices[e[1]].edges
#e2_neighbours.remove(e1)
for v in e2_neighbours:
if v!=e[0]:
neighbor_edge=tuple((min(e[1],v),max(e[1],v)))
if g.edge_property(neighbor_edge,'label')>0:
indx1= labelNumerics.index(g.edge_property(neighbor_edge,'label'))
adjacency_matrix[indx0,indx1]= adjacency_matrix[indx0,indx1]+1
if len(g.vertices[e[0]].edges)==1: #end point
adjacency_matrix[indx0,len(labelNumerics)] +=1
if len(g.vertices[e[1]].edges)==1: #end point
adjacency_matrix[indx0,len(labelNumerics)] +=1
#find edge neighbouring indeces
neighbor_indx=[]
e1_neighbours= g.vertices[e[0]].edges
for v in e1_neighbours:
if v!=e[1]:
neighbor_edge=tuple((min(e[0],v),max(e[0],v)))
neighbor_indx.append(find_key(edge_w_indx, neighbor_edge, e_cnt))
e2_neighbours= g.vertices[e[1]].edges
for v in e2_neighbours:
if v!=e[0]:
neighbor_edge=tuple((min(e[1],v),max(e[1],v)))
neighbor_indx.append(find_key(edge_w_indx, neighbor_edge, e_cnt))
#if (len(neighbor_indx)!=2 and len(neighbor_indx)!=4):
#print ("\n\nERROR! edge (%d,%d) has %d neighbouring vertices!" %(e[0],e[1],len(neighbor_indx)))
#if (len(neighbor_indx)!=0):
#print "Aborted!\n"
#exit(0)
edge_neighboring_indx[e_cnt]=neighbor_indx
e_cnt = e_cnt+1
#### adjacency matrix normalization
for i in range(adjacency_matrix.shape[0]):
adjacency_matrix[i,:]= adjacency_matrix[i,:]/sum(adjacency_matrix[i,:])
print_adj_mat (adjacency_matrix,labelNumerics)
return labelNumerics, feature_vector, target_vector, adjacency_matrix, edge_w_indx, edge_neighboring_indx #featureVect
sys.stdout.flush()
tic = time.time()
#groundturht_file, test_file, ref_graph, mr_atlas_file, mr_centroids_file, reference_file, output_file = args
groundturht_file, test_file, output_file = args
#cmnd = ("python /projects/souris/sghanavati/src/scripts/cerebrovascular_analysis/cylinder2graph.py %s %s %s %s %s %s --use_cyl_label --clobber" %(groundturht_file,ref_graph, mr_atlas_file, mr_centroids_file, reference_file,groundturht_file[:-2]+"db"))
#print "\n", cmnd
#os.system(cmnd)
#cmnd = ("python /projects/souris/sghanavati/src/scripts/cerebrovascular_analysis/cylinder2graph.py %s %s %s %s %s %s --use_cyl_label --clobber" %(test_file,ref_graph, mr_atlas_file, mr_centroids_file, reference_file,test_file[:-2]+"db"))
#print "\n", cmnd
#os.system(cmnd)
ref = graph_analysis.input_graph(groundturht_file[:-2] + "db")
g = graph_analysis.input_graph(test_file[:-2] + "db")
h = copy.deepcopy(g)
labeled_num = 0
error_num = 0
total_volume = 0
error_volume = 0
availabel_labels = []
for e in g.edge_list():
if e in ref.edge_list():
if int(ref.edge_property(e, 'cyl_label')) not in availabel_labels:
availabel_labels.append(int(ref.edge_property(e, 'cyl_label')))
labeled_num += 1
e_radius = ref.edge_property(e, 'cyl_radius')
if len(args) != 5:
parser.error("incorrect number of arguments")
graph_file, mr_atlas_file, mr_centroids_file, dir_reference_file, output_file = args
#### mri_distance feature:
cmd=("feature_MRI_labels.py %s %s %s --clobber" %(graph_file,mr_atlas_file, output_file))
print(cmd)
sys.stdout.flush()
check_call(cmd, shell=True)
try:
g, attributes = graph_analysis.input_graph(output_file, ["history", "vertex_offsets"]) # open graph data and copy contents to memory
print ("Successfully read in the %s\n" %graph_file)
sys.stdout.flush()
except:
print("Error reading in the %s \n" %graph_file)
sys.stdout.flush()
mr = shelve.open(mr_centroids_file, "r")
mr_centroids = mr['mr_centroids']
mr.close()
#### find curvature and midpoint and turtoisity of each edge
i1=l[i0+1:].index(';')+i0+1
labelNumeric2Name[int(l[0:i0])]=l[i0+1:i1]
f.close()
if options.labels:
ls = options.labels.split(',')
ls = [int(l) for l in ls]
else:
ls = []
ls_name = []
for l in labelNumeric2Name.keys():
if labelNumeric2Name[l] not in ls_name:
ls.append(l)
ls_name.append(labelNumeric2Name[l])
#ls = labelNumeric2Name.keys()
f = open(options.output_name,'w')
f.write( "strain,sample, label, label_Name, initial_RR,GD_RR,SA_RR, initialvol_RR,GDvol_RR,SAvol_RR")
ls = [int(l) for l in ls]
for input_file in input_files:
if os.path.exists(input_file) and os.path.exists(input_file[:-3]+"_autolabel_initial_cyl.db") and os.path.exists(input_file[:-3]+"_autolabel_GD_cyl.db") and os.path.exists(input_file[:-3]+"_autolabel_S_cyl.db"):
g = graph_analysis.input_graph(input_file)
ginit = graph_analysis.input_graph(input_file[:-3]+"_autolabel_initial_cyl.db")
ggd = graph_analysis.input_graph(input_file[:-3]+"_autolabel_GD_cyl.db")
gsa = graph_analysis.input_graph(input_file[:-3]+"_autolabel_S_cyl.db")
f.write( "\n"+os.path.basename(input_file)[:3]+ ","+os.path.basename(input_file)[:14]+ ",0,total,"+ str(totallabelcomparison(g,ginit,labelNumeric2Name,'cyl_label')[0])+","+str(totallabelcomparison(g,ggd,labelNumeric2Name,'cyl_label')[0]) +","+ str(totallabelcomparison(g,gsa,labelNumeric2Name,'cyl_label')[0]) +"," + str(totallabelcomparison(g,ginit,labelNumeric2Name,'cyl_label')[1])+","+str(totallabelcomparison(g,ggd,labelNumeric2Name,'cyl_label')[1]) +","+ str(totallabelcomparison(g,gsa,labelNumeric2Name,'cyl_label')[1]))
for l in ls:
f.write( "\n"+os.path.basename(input_file)[:3]+ ","+os.path.basename(input_file)[:14]+ ","+ str(l)+ ","+ labelNumeric2Name[l]+ ","+ str(labelcomparison(g,ginit,l,labelNumeric2Name,'cyl_label')[0])+","+str(labelcomparison(g,ggd,l,labelNumeric2Name,'cyl_label')[0]) +","+ str(labelcomparison(g,gsa,l,labelNumeric2Name,'cyl_label')[0]) + ","+ str(labelcomparison(g,ginit,l,labelNumeric2Name,'cyl_label')[1])+","+str(labelcomparison(g,ggd,l,labelNumeric2Name,'cyl_label')[1]) +","+ str(labelcomparison(g,gsa,l,labelNumeric2Name,'cyl_label')[1]) )
f.close()
