def stat_slide_info(gt_type, eva_type):
stat_cfg = init.stat_config()
path_info = init.path_info()
outs_path = os.path.join(path_info.outs, stat_cfg.info_file)
vs_file = gname.get_VS_file_path()
files = open(vs_file, "r")
fd_outs = open(outs_path, "ab+")
#print "type: %d %d "%(gt_type,eva_type)
if stat_cfg.gt_itc_mode == 0:
GtStr = stat_cfg.GT_str16
else:
GtStr = stat_cfg.GT_str17
match_cnt = 0
match_id_str = ""
for line in files:
st = line.split(",")
#print "[%s %s] [%s %s]" %(st[0],GtStr[gt_type],st[1],stat_cfg.eva_str[eva_type])
if str(st[0]) == str(GtStr[gt_type]):
if str(st[1]) == str(stat_cfg.eva_str[eva_type]):
match_cnt += 1
match_id_str = "%s,%d" % (match_id_str, int(st[2]))
context = "%s,%s,%d,%s\n" % (GtStr[gt_type], stat_cfg.eva_str[eva_type],
match_cnt, match_id_str)
fd_outs.write(context)
fd_outs.close()
files.close()
return match_cnt
def loop_patient(bar_img, gate):
slide_info = init.slide()
path_info = init.path_info()
cfg = init.config()
patient_info = ["", "", "", "", ""]
init.set_positive_gate(gate)
## patients loop
for patient_id in range(slide_info.start_id, slide_info.end_id):
print(
"################### Patient:%d Gate:%1.4lf ###################"
% (patient_id, gate))
for node_id in range(slide_info.node_num):
print(">>>Patient:%d Node:%d" % (patient_id, node_id))
#get score
slide_score = slide_run.gen_slide_score(patient_id, node_id)
#generate heatmap
draw_heatmap_img(slide_score, patient_id, node_id, cfg.step)
#positive check
if bar_img == 1:
gate_cnt = positive_check.section_stat(slide_score)
positive_check.section_bar_img(gate_cnt, (patient_id, node_id))
positive_flag, mask_dat = positive_check.positive_find(
slide_score, gate)
if positive_flag:
mask_dat = positive_check.transfer_find(slide_score, mask_dat)
if cfg.gen_slide_info_xml_mode == 1:
positive_xml.gen_xml(mask_dat, patient_id, node_id, gate)
print("patient:" + str(patient_id) + " node:" + str(node_id) +
" is Positive!")
#mask_dat = positive_check.slide_mask(slide_score,cfg.positive_gate)
#metastasis_check.get_positive_count(mask_dat)
slide_type_str = metastasis_check.get_slide_type(
patient_id, node_id, mask_dat)
patient_info[node_id] = slide_type_str
else:
patient_info[node_id] = cfg.slide_type[0]
if (slide_score.shape[0] != 100) & (slide_score.shape[1] !=
100):
metastasis_check.save_slide_info(patient_id, node_id, 0, 0,
patient_info[node_id])
#pnstage_file_name = "%s_%1.3lf.csv" %(cfg.result_csv_file,init.get_positive_gate())
#result_path = os.path.join(path_info.pns_info,pnstage_file_name)
result_path = gname.get_pnstage_file_path()
#print "patient :%d "%(patient_id)
print patient_info
result.result(patient_info, result_path, patient_id)
if cfg.eva_mode == 1:
val_kappa = eva.evaluate_main()
statinfo.write_stat_info(val_kappa)
print "Threshold:%1.3lf Kappa:%1.5lf" % (cfg.positive_gate, val_kappa)
stat_cfg = init.stat_config()
if stat_cfg.pnstage_kappa_mode == 1:
statinfo.write_pn_stage_kappa()
def write_pn_stage_kappa():
path_info = init.path_info()
stat_cfg = init.stat_config()
gate = init.get_positive_gate()
c17_gt_path = os.path.join(path_info.config, stat_cfg.c17_pnstage)
c17_eva_path = gname.get_pnstage_file_path()
kappa_score = eva.pnstage_kappa(c17_eva_path, c17_gt_path)
file_path = gname.get_pnstage_kappa_file_path()
result_pnstage_kappa = open(file_path, "ab+")
context_str = "%lf,%lf\n" % (gate, kappa_score)
result_pnstage_kappa.write(context_str)
result_pnstage_kappa.close()
def write_stat_info(kappa):
stat_cfg = init.stat_config()
vs_file = gname.get_VS_file_path()
cnt = [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
if os.path.exists(vs_file):
#files = open(vs_file,"r")
if stat_cfg.gt_itc_mode == 0:
cnt[0] = stat_slide_info(0, 0) # negative #negative
cnt[1] = stat_slide_info(1, 2) # micro #micro
cnt[2] = stat_slide_info(2, 3) # macro #macro
cnt[3] = stat_slide_info(0, 1) # negative #itc
cnt[4] = stat_slide_info(0, 2) # negative #micro
cnt[5] = stat_slide_info(0, 3) # negative #macro
cnt[6] = stat_slide_info(1, 3) # micro #macro
cnt[7] = stat_slide_info(2, 2) # macro #micro
cnt[8] = stat_slide_info(2, 1) # macro #itc
cnt[9] = stat_slide_info(2, 0) # macro #negative
cnt[10] = stat_slide_info(1, 1) # micro #itc
cnt[11] = stat_slide_info(1, 0) # micro #negative
#files.close()
elif stat_cfg.gt_itc_mode == 1:
cnt[0] = stat_slide_info(0, 0) # negative #negative
cnt[1] = stat_slide_info(1, 1) # itc #itc
cnt[2] = stat_slide_info(2, 2) # micro #micro
cnt[3] = stat_slide_info(3, 3) # macro #macro
cnt[4] = stat_slide_info(0, 1) # negative #itc
cnt[5] = stat_slide_info(0, 2) # negative #micro
cnt[6] = stat_slide_info(0, 3) # negative #macro
cnt[7] = stat_slide_info(1, 0) # itc #negative
cnt[8] = stat_slide_info(1, 2) # itc #micro
cnt[9] = stat_slide_info(1, 3) # itc #macro
cnt[10] = stat_slide_info(2, 0) # micro #negative
cnt[11] = stat_slide_info(2, 1) # micro #itc
cnt[12] = stat_slide_info(2, 3) # micro #macro
cnt[13] = stat_slide_info(3, 0) # macro #negative
cnt[14] = stat_slide_info(3, 1) # macro #itc
cnt[15] = stat_slide_info(3, 2) # macro #micro
rate = write_stat_sum(cnt)
write_kappa_score(rate, kappa)
else:
print "cannot find file :%s " % (vs_file)
def write_kappa_score(rate, kappa):
stat_cfg = init.stat_config()
#path_info = init.path_info()
#outs_path = os.path.join(path_info.outs,stat_cfg.info_file)
outs_path = gname.get_result_info_path()
fd_outs = open(outs_path, "ab+")
gate = init.get_positive_gate()
context = "Threshold:,%lf\n" % (gate)
context = context + "Kappa:,%1.5lf\n" % (kappa)
context = context + "\n\n"
context = context + "#,#,#,#,#,#,#,#,#,#,#,#,#,#\n"
fd_outs.write(context)
fd_outs.close()
outs_path = gname.get_kappa_file_path()
fd_outs = open(outs_path, "ab+")
context = "%1.4lf,%lf,%lf\n" % (gate, kappa, rate)
fd_outs.write(context)
fd_outs.close()
def calculate_kappa(ground_truth_map, result_map):
stage_list = ['itc', 'micro', 'macro', 'negative']
stat_cfg = init.stat_config()
ground_truth_stage_list = []
result_stage_list = []
for patient_id, result_stage in result_map.iteritems():
if stat_cfg.gt_itc_mode == 0:
result_stage = result_stage.replace('itc', 'negative')
result_stage_list.append(result_stage)
ground_truth_stage_list.append(ground_truth_map[patient_id])
#print ground_truth_stage_list, result_stage_list
# Return the Kappa score.
cohen_kappa_score = sklearn.metrics.cohen_kappa_score(
y1=ground_truth_stage_list,
y2=result_stage_list,
labels=stage_list,
weights='quadratic')
#print cohen_kappa_score
return cohen_kappa_score
def get_result_info_path():
path_info = init.path_info()
stat_cfg = init.stat_config()
path_file = os.path.join(path_info.outs, stat_cfg.info_file)
return path_file
def get_VS_file_path():
path_info = init.path_info()
stat_cfg = init.stat_config()
file_name = "%s_%1.3lf.csv" % (stat_cfg.vs_file, init.get_positive_gate())
path_file = os.path.join(path_info.outs, file_name)
return path_file
def get_GT_C17_path():
#cfg = init.config()
path_info = init.path_info()
stat_cfg = init.stat_config()
path_file = os.path.join(path_info.config, stat_cfg.GT_file_C17)
return path_file
def get_pnstage_kappa_file_path():
path_info = init.path_info()
stat_cfg = init.stat_config()
path_file = os.path.join(path_info.outs, stat_cfg.patient_kappa_file)
return path_file