def convert_labels_to_nnunet(source_nifti: str, target_nifti: str):
img = sitk.ReadImage(source_nifti)
img_npy = sitk.GetArrayFromImage(img)
nnunet_seg = np.zeros(img_npy.shape, dtype=np.uint8)
# why are they not using normal labels and instead use random numbers???
nnunet_seg[img_npy == 500] = 1 # left ventricular (LV) blood pool (500)
nnunet_seg[img_npy == 600] = 2 # right ventricular blood pool (600)
nnunet_seg[img_npy == 200] = 3 # LV normal myocardium (200)
nnunet_seg[img_npy == 1220] = 4 # LV myocardial edema (1220)
nnunet_seg[img_npy == 2221] = 5 # LV myocardial scars (2221)
nnunet_seg_itk = sitk.GetImageFromArray(nnunet_seg)
nnunet_seg_itk = copy_geometry(nnunet_seg_itk, img)
sitk.WriteImage(nnunet_seg_itk, target_nifti)
def convert_labels_back_to_myops(source_nifti: str, target_nifti: str):
nnunet_itk = sitk.ReadImage(source_nifti)
nnunet_npy = sitk.GetArrayFromImage(nnunet_itk)
myops_seg = np.zeros(nnunet_npy.shape, dtype=np.uint8)
# why are they not using normal labels and instead use random numbers???
myops_seg[nnunet_npy == 1] = 500 # left ventricular (LV) blood pool (500)
myops_seg[nnunet_npy == 2] = 600 # right ventricular blood pool (600)
myops_seg[nnunet_npy == 3] = 200 # LV normal myocardium (200)
myops_seg[nnunet_npy == 4] = 1220 # LV myocardial edema (1220)
myops_seg[nnunet_npy == 5] = 2221 # LV myocardial scars (2221)
myops_seg_itk = sitk.GetImageFromArray(myops_seg)
myops_seg_itk = copy_geometry(myops_seg_itk, nnunet_itk)
sitk.WriteImage(myops_seg_itk, target_nifti)
def load_remove_save(input_file: str, output_file: str, for_which_classes: list,
minimum_valid_object_size: dict = None):
# Only objects larger than minimum_valid_object_size will be removed. Keys in minimum_valid_object_size must
# match entries in for_which_classes
img_in = sitk.ReadImage(input_file)
img_npy = sitk.GetArrayFromImage(img_in)
volume_per_voxel = float(np.prod(img_in.GetSpacing(), dtype=np.float64))
image, largest_removed, kept_size = remove_all_but_the_largest_connected_component(img_npy, for_which_classes,
volume_per_voxel,
minimum_valid_object_size)
# print(input_file, "kept:", kept_size)
img_out_itk = sitk.GetImageFromArray(image)
img_out_itk = copy_geometry(img_out_itk, img_in)
sitk.WriteImage(img_out_itk, output_file)
return largest_removed, kept_size
seg = convert_MR_seg(load_png_stack(gt_dir)[::-1])
img_dir = join(d, p, "T1DUAL", "DICOM_anon", "InPhase")
img_outfile = join(output_images, patient_name + "_0000.nii.gz")
_ = dicom2nifti.convert_dicom.dicom_series_to_nifti(
img_dir, img_outfile, reorient_nifti=False)
img_dir = join(d, p, "T1DUAL", "DICOM_anon", "OutPhase")
img_outfile = join(output_images, patient_name + "_0001.nii.gz")
_ = dicom2nifti.convert_dicom.dicom_series_to_nifti(
img_dir, img_outfile, reorient_nifti=False)
img_sitk = sitk.ReadImage(img_outfile)
img_sitk_npy = sitk.GetArrayFromImage(img_sitk)
seg_itk = sitk.GetImageFromArray(seg.astype(np.uint8))
seg_itk = copy_geometry(seg_itk, img_sitk)
sitk.WriteImage(seg_itk, join(output_labels, patient_name + ".nii.gz"))
patient_ids.append(patient_name)
# Process T1 test
d = join(root_test, "MR")
patients = subdirs(d, join=False)
for p in patients:
patient_name = "T1_" + p
img_dir = join(d, p, "T1DUAL", "DICOM_anon", "InPhase")
img_outfile = join(output_imagesTs, patient_name + "_0000.nii.gz")
_ = dicom2nifti.convert_dicom.dicom_series_to_nifti(
img_dir, img_outfile, reorient_nifti=False)
img_dir = join(d, p, "T1DUAL", "DICOM_anon", "OutPhase")
