def save_multilabel_img_as_multiple_files_endings_OLD(Config,
img,
affine,
path,
multilabel=True):
'''
multilabel True: save as 1 and 2 without fourth dimension
multilabel False: save with beginnings and endings combined
'''
# bundles = exp_utils.get_bundle_names("20")[1:]
bundles = exp_utils.get_bundle_names(Config.CLASSES)[1:]
for idx, bundle in enumerate(bundles):
data = img[:, :, :, (idx * 2):(idx * 2) + 2] > 0
multilabel_img = np.zeros(data.shape[:3])
if multilabel:
multilabel_img[data[:, :, :, 0]] = 1
multilabel_img[data[:, :, :, 1]] = 2
else:
multilabel_img[data[:, :, :, 0]] = 1
multilabel_img[data[:, :, :, 1]] = 1
img_seg = nib.Nifti1Image(multilabel_img, affine)
exp_utils.make_dir(join(path, "endings"))
nib.save(img_seg, join(path, "endings", bundle + ".nii.gz"))
def save_multilabel_img_as_multiple_files_endings(classes, img, affine, path):
bundles = dataset_specific_utils.get_bundle_names(classes)[1:]
for idx, bundle in enumerate(bundles):
img_seg = nib.Nifti1Image(img[:, :, :, idx], affine)
exp_utils.make_dir(join(path, "endings_segmentations"))
nib.save(img_seg,
join(path, "endings_segmentations", bundle + ".nii.gz"))
def create_preprocessed_files(subject):
# Estimate bounding box from this file and then apply it to all other files
bb_file = "12g_125mm_peaks"
# todo: adapt
# filenames_data = ["12g_125mm_peaks", "90g_125mm_peaks", "270g_125mm_peaks",
# "12g_125mm_bedpostx_peaks_scaled", "90g_125mm_bedpostx_peaks_scaled",
# "270g_125mm_bedpostx_peaks_scaled"]
# filenames_seg = ["bundle_masks_72", "bundle_masks_dm", "endpoints_72_ordered",
# "bundle_peaks_Part1", "bundle_peaks_Part2", "bundle_peaks_Part3", "bundle_peaks_Part4",
# "bundle_masks_autoPTX_dm", "bundle_masks_autoPTX_thr001"]
filenames_data = ["bundle_uncertainties"]
filenames_seg = []
print("idx: {}".format(subjects.index(subject)))
exp_utils.make_dir(join(C.DATA_PATH, DATASET_FOLDER_PREPROC, subject))
# Get bounding box
data = nib.load(
join(C.NETWORK_DRIVE, DATASET_FOLDER, subject,
bb_file + ".nii.gz")).get_data()
_, _, bbox, _ = data_utils.crop_to_nonzero(np.nan_to_num(data))
for idx, filename in enumerate(filenames_data):
path = join(C.NETWORK_DRIVE, DATASET_FOLDER, subject,
filename + ".nii.gz")
if os.path.exists(path):
img = nib.load(path)
data = img.get_data()
affine = img.affine
data = np.nan_to_num(data)
# Add channel dimension if does not exist yet
if len(data.shape) == 3:
data = data[..., None]
data, _, _, _ = data_utils.crop_to_nonzero(data, bbox=bbox)
# np.save(join(C.DATA_PATH, DATASET_FOLDER_PREPROC, subject, filename + ".npy"), data)
nib.save(
nib.Nifti1Image(data, affine),
join(C.DATA_PATH, DATASET_FOLDER_PREPROC, subject,
filename + ".nii.gz"))
else:
print("skipping file: {}-{}".format(subject, idx))
raise IOError("File missing")
for filename in filenames_seg:
img = nib.load(
join(C.NETWORK_DRIVE, DATASET_FOLDER, subject,
filename + ".nii.gz"))
data = img.get_data()
data, _, _, _ = data_utils.crop_to_nonzero(data, bbox=bbox)
# np.save(join(C.DATA_PATH, DATASET_FOLDER_PREPROC, subject, filename + ".npy"), data)
nib.save(
nib.Nifti1Image(data, img.affine),
join(C.DATA_PATH, DATASET_FOLDER_PREPROC, subject,
filename + ".nii.gz"))
def main():
args = sys.argv[1:]
out_dir = args[0]
exp_utils.make_dir(join(out_dir, "endings_segmentations"))
exp_utils.make_dir(join(out_dir, "TOM_trackings"))
affine = np.array([[-1., 0., 0., 90], [0., 1., 0., 126], [0., 0., 1., -72],
[0., 0., 0., 1.]])
offset = np.array([90, 126, -72])
spacing = abs(affine[0, 0])
data = [
[[0.9, 0.5, 0.9], [0.5, 0.9, 0.5], [0.9, 0.5, 0.9]],
[[0.5, 0.9, 0.5], [0.9, 0.5, 0.9], [0.5, 0.9, 0.5]],
[[0.9, 0.5, 0.9], [0.5, 0.9, 0.5], [0.9, 0.5, 0.9]],
]
data = np.array(data)
data[0, 0, 0] = 0.1
data[2, 2, 2] = 0.3
data[0, 2, 2] = 0.4
img = nib.Nifti1Image(data, affine)
nib.save(img, join(out_dir, "toy_FA.nii.gz"))
mask = np.zeros((3, 3, 3))
mask[0, 0, 0] = 1
img = nib.Nifti1Image(mask, affine)
nib.save(img, join(out_dir, "endings_segmentations", "toy_b.nii.gz"))
# sl1 = np.array([[0., 0., 0.], [2., 2., 2.]])
sl2 = np.array([[0., 2., 2.], [0., 0., 0.]])
streamlines = [sl2]
# Have to substract 0.5 to move from convention "0mm is in voxel corner" to convention "0mm is in voxel center"
# We have to do this because nifti uses convention "0mm is in voxel center" (streamlines are in world space,
# but edge of first voxel of nifti is not at 0,0,0 but at -0.5,-0.5,-0.5). If we do not apply this results
# will be displayed incorrectly in image viewers (e.g. MITK) and dipy functions (e.g. near_roi) will give wrong results.
streamlines = fiber_utils.add_to_each_streamline(streamlines, -0.5)
streamlines = list(transform_streamlines(streamlines, affine))
streamlines = fiber_utils.invert_streamlines(streamlines,
data,
affine,
axis="y")
# This is equivalent to doing -0.5 before transforms
# -> Have to change sign of each axis where there is minus in affine or invert
# streamlines = fiber_utils.add_to_each_streamline_axis(streamlines, 0.5 * spacing, axis="x")
# streamlines = fiber_utils.add_to_each_streamline_axis(streamlines, 0.5 * spacing, axis="y")
# streamlines = fiber_utils.add_to_each_streamline_axis(streamlines, -0.5 * spacing, axis="z")
fiber_utils.save_streamlines_as_trk_legacy(
join(out_dir, "TOM_trackings", "toy.trk"), streamlines, affine,
data.shape)
def save_multilabel_img_as_multiple_files(Config,
img,
affine,
path,
name="bundle_segmentations"):
bundles = exp_utils.get_bundle_names(Config.CLASSES)[1:]
for idx, bundle in enumerate(bundles):
img_seg = nib.Nifti1Image(img[:, :, :, idx], affine)
exp_utils.make_dir(join(path, name))
nib.save(img_seg, join(path, name, bundle + ".nii.gz"))
def create_preprocessed_files(subject):
# todo: adapt
# filenames_data = ["12g_125mm_peaks", "90g_125mm_peaks", "270g_125mm_peaks", "125mm_bedpostx_tensor"]
# filenames_seg = ["bundle_masks_72", "bundle_peaks_Part1", "bundle_masks_dm",
# "bundle_masks_autoPTX_dm", "bundle_masks_autoPTX_thr001"]
# filenames_data = ["270g_125mm_peaks", "90g_125mm_peaks", "12g_125mm_peaks",
# "12g_125mm_bedpostx_peaks_scaled", "90g_125mm_bedpostx_peaks_scaled",
# "270g_125mm_bedpostx_peaks_scaled"]
# filenames_data = ["270g_125mm_bedpostx_peaks_scaled", "32g_125mm_bedpostx_peaks_scaled"]
# filenames_seg = ["bundle_masks_autoPTX_dm", "bundle_masks_autoPTX_thr001"]
filenames_data = [
"270g_125mm_bedpostx_peaks_scaled", "32g_125mm_bedpostx_peaks_scaled"
]
filenames_seg = []
print("idx: {}".format(subjects.index(subject)))
exp_utils.make_dir(join(C.DATA_PATH, DATASET_FOLDER_PREPROC, subject))
for idx, filename in enumerate(filenames_data):
path = join(C.NETWORK_DRIVE, DATASET_FOLDER, subject,
filename + ".nii.gz")
if os.path.exists(path):
img = nib.load(path)
data = img.get_data()
affine = img.get_affine()
data = np.nan_to_num(data)
if idx == 0:
data, _, bbox, _ = dataset_utils.crop_to_nonzero(data)
else:
data, _, _, _ = dataset_utils.crop_to_nonzero(data, bbox=bbox)
# if idx > 0:
# np.save(join(C.DATA_PATH, DATASET_FOLDER_PREPROC, subject, filename + ".npy"), data)
nib.save(
nib.Nifti1Image(data, affine),
join(C.DATA_PATH, DATASET_FOLDER_PREPROC, subject,
filename + ".nii.gz"))
else:
print("skipping file: {}-{}".format(subject, idx))
raise IOError("File missing")
for filename in filenames_seg:
data = nib.load(
join(C.NETWORK_DRIVE, DATASET_FOLDER, subject,
filename + ".nii.gz")).get_data()
data, _, _, _ = dataset_utils.crop_to_nonzero(data, bbox=bbox)
# np.save(join(C.DATA_PATH, DATASET_FOLDER_PREPROC, subject, filename + ".npy"), data)
nib.save(
nib.Nifti1Image(data, affine),
join(C.DATA_PATH, DATASET_FOLDER_PREPROC, subject,
filename + ".nii.gz"))
def save_multilabel_img_as_multiple_files_peaks(Config, img, affine, path, name="TOM"):
bundles = exp_utils.get_bundle_names(Config.CLASSES)[1:]
for idx, bundle in enumerate(bundles):
data = img[:, :, :, (idx*3):(idx*3)+3]
if Config.FLIP_OUTPUT_PEAKS:
data[:, :, :, 2] *= -1 # flip z Axis for correct view in MITK
filename = bundle + "_f.nii.gz"
else:
filename = bundle + ".nii.gz"
img_seg = nib.Nifti1Image(data, affine)
exp_utils.make_dir(join(path, name))
nib.save(img_seg, join(path, name, filename))
def save_fusion_nifti_as_npy():
#Can leave this always the same (for 270g and 32g)
class Config:
DATASET = "HCP"
RESOLUTION = "1.25mm"
FEATURES_FILENAME = "270g_125mm_peaks"
LABELS_TYPE = np.int16
LABELS_FILENAME = "bundle_masks"
DATASET_FOLDER = "HCP"
DIFFUSION_FOLDER = "32g_25mm"
subjects = get_all_subjects()
print("\n\nProcessing Data...")
for s in subjects:
print("processing data subject {}".format(s))
start_time = time.time()
data = nib.load(
join(C.NETWORK_DRIVE, "HCP_fusion_" + DIFFUSION_FOLDER,
s + "_probmap.nii.gz")).get_data()
print("Done Loading")
data = np.nan_to_num(data)
data = dataset_utils.scale_input_to_unet_shape(data, Config.DATASET,
Config.RESOLUTION)
# cut one pixel at the end, because in scale_input_to_world_shape we ouputted 146 -> one too much at the end
data = data[:-1, :, :-1, :]
exp_utils.make_dir(
join(C.NETWORK_DRIVE, "HCP_fusion_npy_" + DIFFUSION_FOLDER, s))
np.save(
join(C.NETWORK_DRIVE, "HCP_fusion_npy_" + DIFFUSION_FOLDER, s,
DIFFUSION_FOLDER + "_xyz.npy"), data)
print("Took {}s".format(time.time() - start_time))
print("processing seg subject {}".format(s))
start_time = time.time()
# seg = ImgUtils.create_multilabel_mask(Config, s, labels_type=Config.LABELS_TYPE)
seg = nib.load(
join(C.NETWORK_DRIVE, "HCP_for_training_COPY", s,
Config.LABELS_FILENAME + ".nii.gz")).get_data()
if Config.RESOLUTION == "2.5mm":
seg = img_utils.resize_first_three_dims(seg, order=0, zoom=0.5)
seg = dataset_utils.scale_input_to_unet_shape(seg, Config.DATASET,
Config.RESOLUTION)
np.save(
join(C.NETWORK_DRIVE, "HCP_fusion_npy_" + DIFFUSION_FOLDER, s,
"bundle_masks.npy"), seg)
print("Took {}s".format(time.time() - start_time))
def save_multilabel_img_as_multiple_files_peaks(flip_output_peaks,
classes,
img,
affine,
path,
name="TOM"):
bundles = dataset_specific_utils.get_bundle_names(classes)[1:]
for idx, bundle in enumerate(bundles):
data = img[:, :, :, (idx * 3):(idx * 3) + 3]
if flip_output_peaks:
data[:, :, :, 2] *= -1 # flip z Axis for correct view in MITK
filename = bundle + "_f.nii.gz"
else:
filename = bundle + ".nii.gz"
img_seg = nib.Nifti1Image(data, affine)
exp_utils.make_dir(join(path, name))
nib.save(img_seg, join(path, name, filename))
def peaks2fixel(peaks_file_in, fixel_dir_out):
"""
Transform TOM peak file to mrtrix fixels format. That can then be transformed to spherical harmonics using
fixel2sh.
Args:
peaks_file_in: (x,y,z,3) (only 1 peak allowed per voxel)
fixel_dir_out:
Returns:
Void
"""
exp_utils.make_dir(fixel_dir_out)
peaks_img = nib.load(peaks_file_in)
peaks = peaks_img.get_data()
s = peaks.shape
directions = []
index = np.zeros(list(s[:3]) + [2])
amplitudes = []
idx_ctr = 0
for x in range(s[0]):
for y in range(s[1]):
for z in range(s[2]):
peak = peaks[x, y, z]
peak_len = np.linalg.norm(peak)
if peak_len > 0:
peak_normalized = peak / (peak_len + 1e-20)
directions.append(peak_normalized)
amplitudes.append(peak_len)
index[x, y, z] = [1, idx_ctr]
idx_ctr += 1
nib.save(nib.Nifti2Image(np.array(directions), np.eye(4)),
join(fixel_dir_out, "directions.nii.gz"))
nib.save(nib.Nifti2Image(index, peaks_img.affine),
join(fixel_dir_out, "index.nii.gz"))
nib.save(nib.Nifti2Image(np.array(amplitudes), np.eye(4)),
join(fixel_dir_out, "amplitudes.nii.gz"))
def main():
args = sys.argv[1:]
out_dir = args[0]
exp_utils.make_dir(join(out_dir, "endings_segmentations"))
exp_utils.make_dir(join(out_dir, "TOM_trackings"))
affine = np.eye(4)
data = [
[[0.9, 0.5, 0.9], [0.5, 0.9, 0.5], [0.9, 0.5, 0.9]],
[[0.5, 0.9, 0.5], [0.9, 0.5, 0.9], [0.5, 0.9, 0.5]],
[[0.9, 0.5, 0.9], [0.5, 0.9, 0.5], [0.9, 0.5, 0.9]],
]
data = np.array(data)
data[0, 0, 0] = 0.1
data[2, 2, 2] = 0.3
data[0, 2, 2] = 0.4
img = nib.Nifti1Image(data, affine)
nib.save(img, join(out_dir, "toy_FA.nii.gz"))
mask = np.zeros((3, 3, 3))
mask[0, 0, 0] = 1
img = nib.Nifti1Image(mask, affine)
nib.save(img, join(out_dir, "endings_segmentations", "toy_b.nii.gz"))
sl1 = np.array([[0., 0., 0.], [2., 2., 2.]])
sl2 = np.array([[0., 2., 2.], [0., 0., 0.]])
streamlines = [sl1, sl2]
# Have to substract 0.5 to move from convention "0mm is in voxel corner" to convention "0mm is in voxel center"
# We have to do this because nifti uses convention "0mm is in voxel center" (streamlines are in world space,
# but edge of first voxel of nifti is not at 0,0,0 but at -0.5,-0.5,-0.5). If we do not apply this results
# will be displayed incorrectly in image viewers (e.g. MITK) and dipy functions (e.g. near_roi) will give wrong results.
streamlines = fiber_utils.add_to_each_streamline(streamlines, -0.5)
fiber_utils.save_streamlines_as_trk_legacy(
join(out_dir, "TOM_trackings", "toy.trk"), streamlines, affine,
data.shape)
def precompute_batches(custom_type=None):
'''
9000 slices per epoch -> 200 batches (batchsize=44) per epoch
=> 200-1000 batches needed
'''
class Config:
NORMALIZE_DATA = True
DATA_AUGMENTATION = False
CV_FOLD = 0
INPUT_DIM = (144, 144)
BATCH_SIZE = 44
DATASET_FOLDER = "HCP"
TYPE = "single_direction"
EXP_PATH = "~"
LABELS_FILENAME = "bundle_peaks"
FEATURES_FILENAME = "270g_125mm_peaks"
DATASET = "HCP"
RESOLUTION = "1.25mm"
LABELS_TYPE = np.float32
Config.TRAIN_SUBJECTS, Config.VALIDATE_SUBJECTS, Config.TEST_SUBJECTS = exp_utils.get_cv_fold(
Config.CV_FOLD)
num_batches_base = 5000
num_batches = {
"train": num_batches_base,
"validate": int(num_batches_base / 3.),
"test": int(num_batches_base / 3.),
}
if custom_type is None:
types = ["train", "validate", "test"]
else:
types = [custom_type]
for type in types:
data_loader = DataLoaderTraining(Config)
batch_gen = data_loader.get_batch_generator(
batch_size=Config.BATCH_SIZE,
type=type,
subjects=getattr(Config,
type.upper() + "_SUBJECTS"))
num_batches = num_batches[type]
for idx in range(num_batches):
print("Processing: {}".format(idx))
batch = next(batch_gen)
DATASET_DIR = "HCP_batches/270g_125mm_bundle_peaks_XYZ"
exp_utils.make_dir(join(C.HOME, DATASET_DIR, type))
data = nib.Nifti1Image(
batch["data"],
img_utils.get_dwi_affine(Config.DATASET, Config.RESOLUTION))
nib.save(
data,
join(C.HOME, DATASET_DIR, type,
"batch_" + str(idx) + "_data.nii.gz"))
seg = nib.Nifti1Image(
batch["seg"],
img_utils.get_dwi_affine(Config.DATASET, Config.RESOLUTION))
nib.save(
seg,
join(C.HOME, DATASET_DIR, type,
"batch_" + str(idx) + "_seg.nii.gz"))
