Task062_NIHPancreas.py

[vincentochs]

Hello!

I tried to replicate the Task06_NIHPancreas.py

I tried to run it but get the following error:

`python3 Task062_NIHPancreas.py

Please cite the following paper when using nnUNet:

Isensee, F., Jaeger, P.F., Kohl, S.A.A. et al. "nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation." Nat Methods (2020). https://doi.org/10.1038/s41592-020-01008-z

If you have questions or suggestions, feel free to open an issue at https://github.com/MIC-DKFZ/nnUNet

nnUNet_raw_data_base is not defined and nnU-Net can only be used on data for which preprocessed files are already present on your system. nnU-Net cannot be used for experiment planning and preprocessing like this. If this is not intended, please read documentation/setting_up_paths.md for information on how to set this up properly.
nnUNet_preprocessed is not defined and nnU-Net can not be used for preprocessing or training. If this is not intended, please read documentation/setting_up_paths.md for information on how to set this up.
RESULTS_FOLDER is not defined and nnU-Net cannot be used for training or inference. If this is not intended behavior, please read documentation/setting_up_paths.md for information on how to set this up.
Traceback (most recent call last):
File "/home/vincent.ochs/nn_unet/nnUnetFrame/nnUNet/nnunet/dataset_conversion/Task062_NIHPancreas.py", line 49, in
out_base = join(nnUNet_raw_data, foldername)
File "/home/vincent.ochs/miniconda3/envs/nn_UNet/lib/python3.10/posixpath.py", line 76, in join
a = os.fspath(a)
TypeError: expected str, bytes or os.PathLike object, not NoneType
`

I have this setup of the json:

`from collections import OrderedDict
from nnunet.paths import nnUNet_raw_data
from batchgenerators.utilities.file_and_folder_operations import *
import shutil
from multiprocessing import Pool
import nibabel

def reorient(filename):
img = nibabel.load(filename)
img = nibabel.as_closest_canonical(img)
nibabel.save(img, filename)

if name == "main":
base = "/home/vincent.ochs/nn_unet/Pancreas-CT"
# reorient
p = Pool(8)
results = []

for f in subfiles(join(base, "data"), suffix=".nii.gz"):
    results.append(p.map_async(reorient, (f, )))
_ = [i.get() for i in results]

for f in subfiles(join(base, "TCIA_pancreas_labels-02-05-2017"), suffix=".nii.gz"):
    results.append(p.map_async(reorient, (f, )))
_ = [i.get() for i in results]

task_id = 62
task_name = "NIHPancreas"

foldername = "Task%03.0d_%s" % (task_id, task_name)

out_base = join(nnUNet_raw_data, foldername)
imagestr = join(out_base, "imagesTr")
imagests = join(out_base, "imagesTs")
labelstr = join(out_base, "labelsTr")
maybe_mkdir_p(imagestr)
maybe_mkdir_p(imagests)
maybe_mkdir_p(labelstr)

train_patient_names = []
test_patient_names = []
cases = list(range(1, 83))
folder_data = join(base, "data")
folder_labels = join(base, "TCIA_pancreas_labels-02-05-2017")
for c in cases:
    casename = "pancreas_%04.0d" % c
    shutil.copy(join(folder_data, "PANCREAS_%04.0d.nii.gz" % c), join(imagestr, casename + "_0000.nii.gz"))
    shutil.copy(join(folder_labels, "label%04.0d.nii.gz" % c), join(labelstr, casename + ".nii.gz"))
    train_patient_names.append(casename)

json_dict = OrderedDict()
json_dict['name'] = task_name
json_dict['description'] = task_name
json_dict['tensorImageSize'] = "4D"
json_dict['reference'] = "see website"
json_dict['licence'] = "see website"
json_dict['release'] = "0.0"
json_dict['modality'] = {
    "0": "CT",
}
json_dict['labels'] = {
    "0": "background",
    "1": "Pancreas",
}
json_dict['numTraining'] = len(train_patient_names)
json_dict['numTest'] = len(test_patient_names)
json_dict['training'] = [{'image': "./imagesTr/%s.nii.gz" % i.split("/")[-1], "label": "./labelsTr/%s.nii.gz" % i.split("/")[-1]} for i in
                         train_patient_names]
json_dict['test'] = ["./imagesTs/%s.nii.gz" % i.split("/")[-1] for i in test_patient_names]

save_json(json_dict, os.path.join(out_base, "dataset.json"))`

So the only thing I have changed was the "base" path.
Other than that I have donwloaded the dataset with the folder "Pancreas-CT" with the subfolders "data" and "TCIA_pancreas_labels-02-05-2017"

any idea what else I need to specify or what is going wrong?

Thank you very much!

[vincentochs]

already fund the answer, thanks anyway !