def main():
parser = argparse.ArgumentParser()
parser.add_argument(
'input',
metavar='input',
type=path,
help='Path to the input image, can be a folder for dicoms')
parser.add_argument('output',
metavar='output',
type=str,
help='Filepath for output lungmask')
parser.add_argument('--modeltype',
help='Default: unet',
type=str,
choices=['unet', 'resunet'],
default='unet')
parser.add_argument('--modelname',
help="spcifies the trained model, Default: R231",
type=str,
choices=['R231', 'LTRCLobes', 'R231CovidWeb'],
default='R231')
parser.add_argument(
'--cpu',
help=
"Force using the CPU even when a GPU is available, will override batchsize to 1",
action='store_true')
parser.add_argument(
'--nopostprocess',
help=
"Deactivates postprocessing (removal of unconnected components and hole filling",
action='store_true')
parser.add_argument(
'--batchsize',
type=int,
help=
"Number of slices processed simultaneously. Lower number requires less memory but may be slower.",
default=20)
argsin = sys.argv[1:]
args = parser.parse_args(argsin)
batchsize = args.batchsize
if args.cpu:
batchsize = 1
logging.info(f'Load model')
model = mask.get_model(args.modeltype, args.modelname)
input_image = utils.get_input_image(args.input)
logging.info(f'Infer lungmask')
result = mask.apply(input_image,
model,
force_cpu=args.cpu,
batch_size=batchsize,
volume_postprocessing=not (args.nopostprocess))
result_out = sitk.GetImageFromArray(result)
result_out.CopyInformation(input_image)
logging.info(f'Save result to: {args.output}')
sys.exit(sitk.WriteImage(result_out, args.output))
def segmenter():
from lungmask import lungmask, utils
import SimpleITK as sitk
from pathlib import Path
import os
import logging
import numpy as np
# import pdb
images_path = Path("./Data/COVID")
segmentation_path = Path("./Data/Segmentations")
dict_path = Path("./Data/Dictionaries")
images = [
f for f in os.listdir(images_path)
if os.path.isdir(os.path.join(images_path, f))
]
# pdb.set_trace()
logging.info(f'Load model')
model = lungmask.get_model('unet', 'R231')
for input in images:
input_image = utils.get_input_image(os.path.join(images_path, input))
logging.info(f'Infer lungmask')
result = lungmask.apply(input_image,
model,
batch_size=1,
volume_postprocessing=False)
result_dict = np.zeros((np.shape(result)[0], 2))
for i in range(np.shape(result)[0]):
slice = result[i, :, :]
area = np.size(np.where(slice > 0))
result_dict[i, :] = [i + 1, area]
result_dict = np.flip(result_dict[result_dict[:, 1].argsort()], axis=0)
with open(os.path.join(dict_path, '{}.csv'.format(input)),
"w") as outfile:
np.savetxt(outfile, result_dict, delimiter=",")
result_out = sitk.GetImageFromArray(result)
result_out.CopyInformation(input_image)
logging.info(f' %s results saved', input)
sitk.WriteImage(
result_out, os.path.join(segmentation_path,
'{}.dcm'.format(input)))
def __host_segment(self, source_dir, model_name):
from lungmask import lungmask
from lungmask import utils
import SimpleITK as sitk
model = lungmask.get_model('unet', model_name)
input_image = utils.get_input_image(source_dir)
input_nda = sitk.GetArrayFromImage(input_image)
print(input_nda.shape)
segmentation = lungmask.apply(input_image,
model,
force_cpu=False,
batch_size=20,
volume_postprocessing=False)
return segmentation, input_nda
def run_lungmask_absolute(abs_source_dir, model_name='R231CovidWeb'):
data_share = os.environ["DATA_SHARE_PATH"]
model = lungmask.get_model('unet', model_name)
if not os.path.exists(abs_source_dir):
log_debug("Input image source dir doesn't exist", abs_source_dir)
return {}, False
input_image = utils.get_input_image(abs_source_dir)
segmentation = lungmask.apply(input_image,
model,
force_cpu=False,
batch_size=20,
volume_postprocessing=False)
log_debug("Got result")
log_debug(segmentation)
result_dict = {}
lungmask_dir = "lungmask_output"
os.makedirs(os.path.join(data_share, lungmask_dir), exist_ok=True)
unique_id = cutils.get_unique_id()
hostname = os.environ["LUNGMASK_HOSTNAME"]
rel_seg_save_path = os.path.join(
lungmask_dir, f"{hostname}-segmentation-{unique_id}.nii.gz")
abs_seg_save_path = os.path.join(data_share, rel_seg_save_path)
segmentation_nifti = sitk.GetImageFromArray(segmentation)
segmentation_nifti.SetSpacing(input_image.GetSpacing())
sitk.WriteImage(segmentation_nifti, abs_seg_save_path)
result_dict["segmentation"] = rel_seg_save_path
return result_dict, True
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--in-folder', type=str, default=in_folder)
parser.add_argument('--out-folder', type=str, default=out_mask_folder)
parser.add_argument('--file-list-txt', type=str, default=file_list_txt)
parser.add_argument('--failed-list-txt', type=str)
parser.add_argument('--modeltype',
help='Default: unet',
type=str,
choices=['unet'],
default='unet')
parser.add_argument(
'--modelname',
help="spcifies the trained model, Default: R231",
type=str,
choices=['R231', 'LTRCLobes', 'LTRCLobes_R231', 'R231CovidWeb'],
default='R231')
parser.add_argument(
'--cpu',
help=
"Force using the CPU even when a GPU is available, will override batchsize to 1",
action='store_true')
parser.add_argument(
'--nopostprocess',
help=
"Deactivates postprocessing (removal of unconnected components and hole filling",
action='store_true')
parser.add_argument(
'--noHU',
help=
"For processing of images that are not encoded in hounsfield units (HU). E.g. png or jpg images from the web. Be aware, results may be substantially worse on these images",
action='store_true')
parser.add_argument(
'--batchsize',
type=int,
help=
"Number of slices processed simultaneously. Lower number requires less memory but may be slower.",
default=20)
argsin = sys.argv[1:]
args = parser.parse_args(argsin)
batchsize = args.batchsize
if args.cpu:
batchsize = 1
logging.info(f'Load model')
file_list = read_file_contents_list(args.file_list_txt)
failed_case_list = []
for file_idx in range(len(file_list)):
file_name = file_list[file_idx]
logging.info(f'Process {file_name}, {file_idx} / {len(file_list)}')
try:
in_nii = os.path.join(args.in_folder, file_name)
out_nii_mask = os.path.join(args.out_folder, file_name)
input_image = utils.get_input_image(in_nii)
logging.info(f'Infer lungmask')
if args.modelname == 'LTRCLobes_R231':
result = mask.apply_fused(
input_image,
force_cpu=args.cpu,
batch_size=batchsize,
volume_postprocessing=not (args.nopostprocess),
noHU=args.noHU)
else:
model = mask.get_model(args.modeltype, args.modelname)
result = mask.apply(
input_image,
model,
force_cpu=args.cpu,
batch_size=batchsize,
volume_postprocessing=not (args.nopostprocess),
noHU=args.noHU)
result_out = sitk.GetImageFromArray(result)
result_out.CopyInformation(input_image)
logging.info(f'Save result to: {out_nii_mask}')
# sys.exit(sitk.WriteImage(result_out, out_nii_mask))
sitk.WriteImage(result_out, out_nii_mask)
except:
print(f'Something wrong with {file_name}')
failed_case_list.append(file_name)
save_file_contents_list(args.failed_list_txt, failed_case_list)
if st.button('download and analyse'):
latest_iteration = st.empty()
bar = st.progress(0)
dir_ = os.path.join('/tmp/', subject_name)
scan.download_dir(dir_, verbose=True)
download_dir = ''
for path in Path(dir_).rglob('*.dcm'):
download_dir, file = os.path.split(str(path.resolve()))
break
bar.progress(100)
st.text('Analysis progress...')
bar2 = st.progress(0)
model = lungmask.get_model('unet', 'R231CovidWeb')
input_image = utils.get_input_image(download_dir)
input_nda = sitk.GetArrayFromImage(input_image)
print(input_nda.shape)
zd, yd, xd = input_nda.shape
spx, spy, spz = input_image.GetSpacing()
result = lungmask.apply(input_image,
model,
bar2,
force_cpu=False,
batch_size=20,
volume_postprocessing=False)
result_out = sitk.GetImageFromArray(result)
result_out.CopyInformation(input_image)
sitk.WriteImage(result_out,