def get_pathology_filelists(datasetidx=''):
root_name = 'root_dir'
if datasetidx is not None: root_name += str(datasetidx)
if hasattr(opt, root_name) and getattr(opt, root_name) is not None:
#filelists, folddict = lt.filelist_training(opt.root_dir, remove_uncertain=opt.remove_uncertain, shuffle = opt.filelist_shuffle, cross_fold = opt.num_cross_folds, val_fold = opt.val_fold, test_fold = opt.test_fold)
file_root = getattr(opt, root_name)
if os.path.isfile(file_root):
filelist = bt.filelist_load(file_root)
else:
filelist = glob.glob(
os.path.join(getattr(opt, root_name), "npy", "*.npy"))
#mt.sample_statistics(filelist, True)
if 'lidc' in getattr(opt, root_name) and hasattr(
opt, 'remove_uncertain') and opt.remove_uncertain:
filelist = lt.filelist_remove_uncertain(filelist)
if opt.filelist_shuffle:
random.shuffle(filelist)
filelists, folddict = bt.foldlist(
filelist, opt.num_cross_folds, {
'val': getattr(opt, 'val_fold' + str(datasetidx)),
'test': getattr(opt, 'test_fold' + str(datasetidx))
})
if 'train' in filelists.keys():
bt.filelist_store(
filelists['train'], save_path + '/filelist' + str(datasetidx) +
'_train_fold' + str(folddict['train']) + '.log')
if 'val' in filelists.keys():
bt.filelist_store(
filelists['val'], save_path + '/filelist' + str(datasetidx) +
'_val_fold' + str(folddict['val']) + '.log')
if 'test' in filelists.keys():
bt.filelist_store(
filelists['test'], save_path + '/filelist' + str(datasetidx) +
'_test_fold' + str(folddict['test']) + '.log')
#vis.log("trainfold:{} valfold:{} testfold:{}" .format(folddict['train'], folddict['val'], folddict['test']))
print("filelist generated")
else:
filelists = {}
filelists['train'] = bt.filelist_load(
getattr(opt, 'filelists' + str(datasetidx))['train'])
filelists['val'] = bt.filelist_load(
getattr(opt, 'filelists' + str(datasetidx))['val'])
bt.filelist_store(filelists['train'],
save_path + '/filelist_train.log')
bt.filelist_store(filelists['val'], save_path + '/filelist_val.log')
if 'test' in getattr(opt, 'filelists' + str(datasetidx)).keys():
filelists['test'] = bt.filelist_load(
getattr(opt, 'filelists' + str(datasetidx))['test'])
bt.filelist_store(filelists['test'],
save_path + '/filelist_test.log')
print("filelist loaded")
return filelists
def get_detection_filelists(patient_uids=None,
filepaths=None,
easy_eliminate_filelist=None,
config={}):
save_path = config['model_root'] + '/' + config['env']
if easy_eliminate_filelist is not None:
easy_eliminate_filelist = bt.filelist_load(easy_eliminate_filelist)
if filepaths is None:
filelists = {}
filelists['train'] = bt.filelist_load(config['filelists']['train'])
filelists['val'] = bt.filelist_load(config['filelists']['val'])
if easy_eliminate_filelist is not None:
filelists['train'] = bt.filelist_eliminate(
filelists['train'], easy_eliminate_filelist)
filelists['val'] = bt.filelist_eliminate(filelists['val'],
easy_eliminate_filelist)
bt.filelist_store(filelists['train'],
save_path + '/filelist_train.log')
bt.filelist_store(filelists['val'], save_path + '/filelist_val.log')
print("filelist loaded")
else:
#filepaths=["/home/fyl/datasets/luna_64/train", "/home/fyl/datasets/luna_64/test", "/home/fyl/datasets/npy_non_set"]
#filelist = []
if patient_uids is None:
patient_uids = []
for filepath in filepaths:
files = glob.glob(filepath + '/*.npy')
#filelist.extend(files)
for file in files:
filename = os.path.basename(file)
filenamenoext = os.path.splitext(filename)[0]
fileinfos = filenamenoext.split('_')
annolabel = fileinfos[-1]
patient_uid = fileinfos[0]
if patient_uid not in patient_uids:
patient_uids.append(patient_uid)
elif type(patient_uids) == str:
patient_uids = bt.filelist_load(patient_uids)
#patient_temp = patient_uids[int(len(patient_uids)/10.0+0.5)*3:]
#random.shuffle(patient_temp)
#patient_uids[int(len(patient_uids)/10.0+0.5)*3:] = patient_temp
if config['filelist_shuffle']: random.shuffle(patient_uids)
bt.filelist_store(patient_uids, save_path + '/patientlist.log')
patient_folds, folddict = bt.foldlist(patient_uids,
config['num_cross_folds'], {
'val': config['val_fold'],
'test': config['test_fold']
})
filelist_overall = []
filelists = {}
for setname in patient_folds.keys():
filelists[setname] = []
for filelist in filepaths:
if os.path.isfile(filelist):
files = bt.filelist_load(filelist)
else:
files = os.listdir(filelist)
for f in range(len(files)):
files[f] = filelist + '/' + files[f]
#files = glob.glob(filelist+'/*.%s' %(fileext))
filelist_overall.extend(files)
if 'lidc' in filelist and 'remove_uncertain' in config.keys(
) and config['remove_uncertain']:
filelist_overall = lt.filelist_remove_uncertain(
filelist_overall)
if easy_eliminate_filelist is not None:
filelist_overall = bt.filelist_eliminate(filelist_overall,
easy_eliminate_filelist)
if config['filelist_shuffle']: random.shuffle(filelist_overall)
for file in filelist_overall:
filename_split = os.path.splitext(
os.path.basename(file))[0].split('_')
#if 'label_choice' in config.keys() and filename_split[-1]=='annotation' and config['label_choice']!=filename_split[2]: continue
patient_uid = filename_split[0]
for setname in patient_folds.keys():
if patient_uid in patient_folds[setname]:
filelists[setname].append(file)
for setname in patient_folds.keys():
bt.filelist_store(
filelists[setname], save_path + '/filelist_' + setname +
'_fold' + str(folddict[setname]) + '.log')
bt.filelist_store(filelist_overall, save_path + '/filelist.log')
print("filelist generated")
'''
filelists = get_filelists_patientwise(patient_uids, filepaths, fileext='npy', config=config)
for setname in filelists.keys():
if easy_eliminate_filelist is not None:
filelists[setname] = bt.filelist_eliminate(filelists[setname], easy_eliminate_filelist)
'''
return filelists
def get_filelists_patientwise(patient_uids=None,
filelists=None,
fileext='npy',
datasetidx='',
config={}):
save_path = config['model_root'] + '/' + config['env']
if filelists is None:
filelistdict = {}
filelistdict['train'] = bt.filelist_load(
config['filelists' + str(datasetidx)]['train'])
filelistdict['val'] = bt.filelist_load(config['filelists' +
str(datasetidx)]['val'])
bt.filelist_store(filelistdict['train'],
save_path + '/filelist_train.log')
bt.filelist_store(filelistdict['val'], save_path + '/filelist_val.log')
if 'test' in config['filelists' + str(datasetidx)].keys():
filelistdict['test'] = bt.filelist_load(
config['filelists' + str(datasetidx)]['test'])
bt.filelist_store(filelistdict['test'],
save_path + '/filelist_test.log')
print("filelist loaded")
else:
#filelists=["/home/fyl/datasets/luna_64/train", "/home/fyl/datasets/luna_64/test", "/home/fyl/datasets/npy_non_set"]
#filelist = []
if patient_uids is None:
patient_uids = []
for filelist in filelists:
files = glob.glob(filelist + '/*.' + fileext)
#filelist.extend(files)
for file in files:
filename = os.path.basename(file)
filenamenoext = os.path.splitext(filename)[0]
fileinfos = filenamenoext.split('_')
patient_uid = fileinfos[0]
if patient_uid not in patient_uids:
patient_uids.append(patient_uid)
elif type(patient_uids) == str:
patient_uids = bt.filelist_load(patient_uids)
if config['filelist_shuffle']: random.shuffle(patient_uids)
bt.filelist_store(
patient_uids,
save_path + '/patientlist' + str(datasetidx) + '.log')
#bt.filelist_store('luna16samplelist.log', filelist)
patient_folds, folddict = bt.foldlist(
patient_uids, config['num_cross_folds'], {
'val': config['val_fold' + str(datasetidx)],
'test': config['test_fold' + str(datasetidx)]
})
filelist_overall = []
filelistdict = {}
for setname in patient_folds.keys():
filelistdict[setname] = []
'''
print("filelist {} generating" .format(setname))
for patient_uid in tqdm(patient_folds[setname]):
for filelist in filelists:
if os.path.isfile(filelist):
files = bt.filelist_load(filelist)
else:
files = glob.glob(filelist+'/%s*.%s' %(patient_uid, fileext))
if 'lidc' in filelist and hasattr(opt, 'remove_uncertain') and opt.remove_uncertain:
files = lt.filelist_remove_uncertain(files)
filelist_overall.extend(files)
filelistdict[setname].extend(files)
bt.filelist_store(filelistdict[setname], save_path+'/filelist'+str(datasetidx)+'_'+setname+'_fold'+str(folddict[setname])+'.log')
'''
for filelist in filelists:
if os.path.isfile(filelist):
files = bt.filelist_load(filelist)
else:
files = glob.glob(filelist + '/*.%s' % (fileext))
filelist_overall.extend(files)
if 'lidc' in filelist and 'remove_uncertain' in config.keys(
) and config['remove_uncertain']:
filelist_overall = lt.filelist_remove_uncertain(
filelist_overall)
if config['filelist_shuffle']: random.shuffle(filelist_overall)
for file in filelist_overall:
patient_uid = os.path.basename(file).split('_')[0]
for setname in patient_folds.keys():
if patient_uid in patient_folds[setname]:
filelistdict[setname].append(file)
for setname in patient_folds.keys():
bt.filelist_store(
filelistdict[setname],
save_path + '/filelist' + str(datasetidx) + '_' + setname +
'_fold' + str(folddict[setname]) + '.log')
bt.filelist_store(filelist_overall,
save_path + '/filelist' + str(datasetidx) + '.log')
print("filelist generated")
return filelistdict
