File size: 4,324 Bytes
ecf08bc |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 |
# Copyright 2020 Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import numpy as np
import subprocess
from collections import OrderedDict
from nnunet.paths import nnUNet_raw_data
from batchgenerators.utilities.file_and_folder_operations import *
import shutil
from skimage import io
import SimpleITK as sitk
import shutil
if __name__ == "__main__":
# download from here https://www.epfl.ch/labs/cvlab/data/data-em/
base = "/media/fabian/My Book/datasets/EPFL_MITO_SEG"
# the orientation of VerSe is all fing over the place. run fslreorient2std to correct that (hopefully!)
# THIS CAN HAVE CONSEQUENCES FOR THE TEST SET SUBMISSION! CAREFUL!
train_volume = io.imread(join(base, "training.tif"))
train_labels = io.imread(join(base, "training_groundtruth.tif"))
train_labels[train_labels == 255] = 1
test_volume = io.imread(join(base, "testing.tif"))
test_labels = io.imread(join(base, "testing_groundtruth.tif"))
test_labels[test_labels == 255] = 1
task_id = 59
task_name = "EPFL_EM_MITO_SEG"
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")
labelste = join(out_base, "labelsTs")
maybe_mkdir_p(imagestr)
maybe_mkdir_p(imagests)
maybe_mkdir_p(labelstr)
maybe_mkdir_p(labelste)
img_tr_itk = sitk.GetImageFromArray(train_volume.astype(np.float32))
lab_tr_itk = sitk.GetImageFromArray(train_labels.astype(np.uint8))
img_te_itk = sitk.GetImageFromArray(test_volume.astype(np.float32))
lab_te_itk = sitk.GetImageFromArray(test_labels.astype(np.uint8))
img_tr_itk.SetSpacing((5, 5, 5))
lab_tr_itk.SetSpacing((5, 5, 5))
img_te_itk.SetSpacing((5, 5, 5))
lab_te_itk.SetSpacing((5, 5, 5))
# 5 copies, otherwise we cannot run nnunet (5 fold cv needs that)
sitk.WriteImage(img_tr_itk, join(imagestr, "training0_0000.nii.gz"))
shutil.copy(join(imagestr, "training0_0000.nii.gz"), join(imagestr, "training1_0000.nii.gz"))
shutil.copy(join(imagestr, "training0_0000.nii.gz"), join(imagestr, "training2_0000.nii.gz"))
shutil.copy(join(imagestr, "training0_0000.nii.gz"), join(imagestr, "training3_0000.nii.gz"))
shutil.copy(join(imagestr, "training0_0000.nii.gz"), join(imagestr, "training4_0000.nii.gz"))
sitk.WriteImage(lab_tr_itk, join(labelstr, "training0.nii.gz"))
shutil.copy(join(labelstr, "training0.nii.gz"), join(labelstr, "training1.nii.gz"))
shutil.copy(join(labelstr, "training0.nii.gz"), join(labelstr, "training2.nii.gz"))
shutil.copy(join(labelstr, "training0.nii.gz"), join(labelstr, "training3.nii.gz"))
shutil.copy(join(labelstr, "training0.nii.gz"), join(labelstr, "training4.nii.gz"))
sitk.WriteImage(img_te_itk, join(imagests, "testing.nii.gz"))
sitk.WriteImage(lab_te_itk, join(labelste, "testing.nii.gz"))
json_dict = OrderedDict()
json_dict['name'] = task_name
json_dict['description'] = task_name
json_dict['tensorImageSize'] = "4D"
json_dict['reference'] = "see challenge website"
json_dict['licence'] = "see challenge website"
json_dict['release'] = "0.0"
json_dict['modality'] = {
"0": "EM",
}
json_dict['labels'] = {i: str(i) for i in range(2)}
json_dict['numTraining'] = 5
json_dict['numTest'] = 1
json_dict['training'] = [{'image': "./imagesTr/training%d.nii.gz" % i, "label": "./labelsTr/training%d.nii.gz" % i} for i in
range(5)]
json_dict['test'] = ["./imagesTs/testing.nii.gz"]
save_json(json_dict, os.path.join(out_base, "dataset.json")) |