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
def retain_loops(g, output_file):
#loop is defined: if an edge is broken and the connected graph breaks into 2 components, that edge is not part of a loop
while graph_analysis.prune_leaves(g) > 0:
pass
N = number_of_connected_components(g)
edge2remove = [] #edge not part of a loop
ne = 0
h = copy.deepcopy(g)
for e in g.edge_list():
properties = g.edge_properties(e)
h.remove_edge(e)
if number_of_connected_components(h) > N:
edge2remove.append(e)
if number_of_connected_components(h) != N:
ne += 1
h.add_edge(e, properties)
print ne, " ", len(edge2remove)
h = copy.deepcopy(g)
for e in edge2remove:
h.remove_edge(e)
graph_analysis.output_graph(output_file, h)
return h
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']
graph_analysis.output_graph(output_file, g, history, attributes)
cmd = ("graph2cylinder.py --use_label %s" % (output_file))
os.system(cmd)
cmd = ("graph2obj.py %s %s %s " %
(output_file, output_file[:-3] + "obj", options.clobber))
os.system(cmd)
e, 'cyl_label', int(np.mean(label_vals[l]))
) #"No label \0" #add label dataset to edge properties and initialize it to None with null-terminted character '\0'
ref_graph.set_edge_property(
e, 'estimated_label', [l, np.mean(label_vals[l])]
) #"No label \0" #add label dataset to edge properties and initialize it to None with null-terminted character '\0'
else:
ref_graph.set_edge_property(e, 'cyl_label', int(0))
ref_graph.set_edge_property(
e, 'estimated_label', [l, 0]
) #"No label \0" #add label dataset to edge properties and initialize it to None with null-terminted character '\0'
history = '>>> %s: %s' % (time.ctime(time.time()), string.join(argv)
) ##argv = ['code.py', 'input.db', 'output']
if attributes.has_key("history"):
history = attributes["history"] + "\n" + history
del attributes['history']
graph_analysis.output_graph(output_file[:-2] + "db", ref_graph, history,
attributes)
#graph_analysis.output_graph("simplifiedgraph.db", h, history, attributes)
print("Succefully wrote the %s\n" % output_file[:-2] + "db")
## save the final cylinder file into h5 file for the Brainview
#output_final=output_file.replace(".db", ".h5")
cmd = ("graph2graph.py %s %s --clobber " %
(output_file[:-2] + "db", output_file[:-2] + "h5")
) #python /micehome/jgsled/bin/
print(cmd)
os.system(cmd)
print len(g.edge_list()), " ", len(g.vertices)
sys.stdout.flush()
#for e in g.edge_list():
#print e, " ",g.edge_property(e, 'intermediaries')
#print " "
this_estimate_edge_diameters(g)
this_estimate_edge_lengths(g)
history = '\n>>> %s: %s' % (time.ctime(
time.time()), string.join(argv) + "\nmodified_simplify_graph"
) ##argv = ['code.py', 'input.db', 'output']
if attributes.has_key("history"):
history = attributes["history"] + "\n" + history
del attributes['history']
graph_analysis.output_graph(output_file[:-3] + "_nofeature_simplified.db",
g, history, attributes)
print("Succefully wrote the %s\n" % output_file[:-3] +
"_nofeature_simplified.db")
sys.stdout.flush()
#output_file = output_file[:-3]+"_simp.db"
#redo feature extraction
cmnd = (
"python /projects/souris/sghanavati/src/scripts/cerebrovascular_analysis/feature_extraction.py %s %s %s %s %s"
%
(output_file[:-3] + "_nofeature_simplified.db", mr_atlas_file,
mr_centroids_file, reference_file, output_file[:-3] + "_featured.db")
) #--new_edges
print "\n", cmnd, "\n"
sys.stdout.flush()
# read in the labeled CT : used to make labling training dataset
#labeled_ct=py_minc.ArrayVolume(labeled_CT_file,dim_names=py_minc.FILE_ORDER_DIMENSION_NAMES) #which is in [x,y,z]
labeled_ct = py_minc.ArrayVolume(
labeled_CT_file
) # without this always [z,y,x], with this :dim_names=py_minc.FILE_ORDER_DIMENSION_NAMES order as the image
#
g = edge_labeling(g, labeled_ct)
#history = history + '\n>>> %s: %s' % (time.ctime(time.time()), "edge_labeling") ##argv = ['code.py', 'input.db', 'output']
history = '\n>>> %s: %s' % (time.ctime(time.time()), string.join(argv)
) ##argv = ['code.py', 'input.db', 'output']
if attributes.has_key("history"):
history = attributes["history"] + "\n" + history
del attributes['history']
graph_analysis.output_graph(output_file, g, history, attributes)
print("Succefully wrote the %s\n" % output_file)
g = label_propagate(g, 0)
#history = history + '\n>>> %s: %s' % (time.ctime(time.time()), "edge_labeling") ##argv = ['code.py', 'input.db', 'output']
history += '\n>>> %s: %s' % (time.ctime(time.time()), "label_propagate"
) ##argv = ['code.py', 'input.db', 'output']
if attributes.has_key("history"):
#history = attributes["history"] + "\n" + history
del attributes['history']
graph_analysis.output_graph(output_file[:-3] + "_propagate.db", g, history,
attributes)
print("Succefully wrote the %s\n" % output_file[:-3] + "_propagate.db")
#####
###if not os.path.exists(input_file[:-3]+"_dt.mnc"):
#h = copy.deepcopy(ref)
keep_edges = []
for input_file in input_files:
print ">>> ", input_file
if os.path.exists(input_file):
g, attributes = graph_analysis.input_graph(
input_file, ["history", "vertex_offsets"])
for e in g.edge_list():
keep_edges.append(e)
for e in ref.edge_list():
if e not in keep_edges:
if ref.edge_property(e,
'cyl_label') not in [9, 200
]: #don't remove pcommAs
ref.remove_edge(e)
if ref_attributes.has_key("history"):
#history = attributes["history"] + "\n>>>Main labels retained." + "\n" + history
history = "\n>>>Anatomical length calculations." + "\n" + ref_attributes[
"history"]
del ref_attributes['history']
graph_analysis.output_graph(options.output_name, ref, history,
ref_attributes)
cmd = ("graph2cylinder.py --clobber --use_label %s" % (options.output_name)
) #python /micehome/jgsled/bin/
os.system(cmd)
for j in range(len(e_radius)):
e_volume += cyl_volume_calculation(e_radius[j], e_height[j])
total_volume += e_volume
#if int(ref.edge_property(e,'label')) != int(g.edge_property(e,'estimated_label')):
if int(ref.edge_property(e, 'cyl_label')) != int(
g.edge_property(e, 'cyl_label')):
h.set_edge_property(e, 'error_label', 2) #error labelling
error_volume += e_volume
error_num += 1
else:
h.set_edge_property(e, 'error_label', 1) #correct labelling
else:
h.set_edge_property(
e, 'error_label',
2) #error labelling (new edge in g that does not exist in ref
graph_analysis.output_graph(output_file, h)
cmd = (
"\npython /projects/souris/sghanavati/src/scripts/cerebrovascular_analysis/graph2cylinder.py %s %s --use_error_label --clobber "
% (output_file, output_file[:-3] + "_error_cyl.h5")
) #python /micehome/jgsled/bin/
print(cmd)
os.system(cmd)
if (labeled_num > 0) and (total_volume >
0): #otherwise test set was not labeled
print(
"Out of %d edges that were labeled, %d were labelled correctly with second round of manual labelling. The error is %f%% (volumetric error %f%%). Recognition Rate is %f%% (volumetric RR %f%%)."
% (labeled_num, labeled_num - error_num,
100 * float(error_num) / float(labeled_num),
100 * float(error_volume) / float(total_volume),
