def assert_img_properties(img: SimpleITK.Image, internal_image: SimpleITKImage): color_space = { 1: ColorSpace.GRAY, 3: ColorSpace.RGB, 4: ColorSpace.RGBA, } assert internal_image.color_space == color_space.get( img.GetNumberOfComponentsPerPixel()) if img.GetDimension() == 4: assert internal_image.timepoints == img.GetSize()[-1] else: assert internal_image.timepoints is None if img.GetDepth(): assert internal_image.depth == img.GetDepth() assert internal_image.voxel_depth_mm == img.GetSpacing()[2] else: assert internal_image.depth is None assert internal_image.voxel_depth_mm is None assert internal_image.width == img.GetWidth() assert internal_image.height == img.GetHeight() assert internal_image.voxel_width_mm == approx(img.GetSpacing()[0]) assert internal_image.voxel_height_mm == approx(img.GetSpacing()[1])
def verify_same_geometry(img_1: sitk.Image, img_2: sitk.Image): ori1, spacing1, direction1, size1 = img_1.GetOrigin(), img_1.GetSpacing( ), img_1.GetDirection(), img_1.GetSize() ori2, spacing2, direction2, size2 = img_2.GetOrigin(), img_2.GetSpacing( ), img_2.GetDirection(), img_2.GetSize() same_ori = np.all(np.isclose(ori1, ori2)) if not same_ori: print("the origin does not match between the images:") print(ori1) print(ori2) same_spac = np.all(np.isclose(spacing1, spacing2)) if not same_spac: print("the spacing does not match between the images") print(spacing1) print(spacing2) same_dir = np.all(np.isclose(direction1, direction2)) if not same_dir: print("the direction does not match between the images") print(direction1) print(direction2) same_size = np.all(np.isclose(size1, size2)) if not same_size: print("the size does not match between the images") print(size1) print(size2) if same_ori and same_spac and same_dir and same_size: return True else: return False
def assert_sitk_img_equivalence(img: SimpleITK.Image, img_ref: SimpleITK.Image): assert img.GetDimension() == img_ref.GetDimension() assert img.GetSize() == img_ref.GetSize() assert img.GetOrigin() == img_ref.GetOrigin() assert img.GetSpacing() == img_ref.GetSpacing() assert (img.GetNumberOfComponentsPerPixel() == img_ref.GetNumberOfComponentsPerPixel()) assert img.GetPixelIDValue() == img_ref.GetPixelIDValue() assert img.GetPixelIDTypeAsString() == img_ref.GetPixelIDTypeAsString()
def sitk_to_itk(image: sitk.Image) -> Any: r""" Function to convert an image object from SimpleITK to ITK. .. note:: Data is copied to the new object (deep copy). Parameters ---------- image : sitk.Image Input image. Returns ------- any Image in ITK format. """ if 'itk' not in sys.modules: raise Exception( 'sitk_to_itk: itk module is required to use this feature.') a = sitk.GetArrayViewFromImage(image) if len(a.shape) < 4: result = itk.GetImageFromArray(a) else: # NOTE: This workaround is implemented this way since it # seems that itk.GetImageFromArray() is not working properly # with vector images. region = itk.ImageRegion[3]() region.SetSize(image.GetSize()) region.SetIndex((0, 0, 0)) PixelType = itk.Vector[itk_float_type, 3] ImageType = itk.Image[PixelType, 3] # Create new image result = ImageType.New() result.SetRegions(region) result.Allocate() result.SetSpacing(image.GetSpacing()) # Copy image data b = itk.GetArrayViewFromImage(result) b[:] = a[:] result.SetSpacing(image.GetSpacing()) result.SetOrigin(image.GetOrigin()) return result
def compatible_metadata(image1: sitk.Image, image2: sitk.Image, check_size: bool = True, check_spacing: bool = True, check_origin: bool = True) -> bool: """ Compares the metadata of two images and determines if all checks are successful or not. Comparisons are carried out with a small tolerance (0.0001). @param image1: first image @param image2: second image @param check_size: if true, check if the sizes of the images are equal @param check_spacing: if true, check if the spacing of the images are equal @param check_origin: if true, check if the origin of the images are equal @return: true, if images are equal in all given checks, false if one of them failed """ all_parameters_equal = True tolerance = 1e-4 if check_size: size1 = image1.GetSize() size2 = image2.GetSize() if size1 != size2: all_parameters_equal = False print(f'Images do not have the same size ({size1} != {size2})') if check_spacing: spacing1 = image1.GetSpacing() spacing2 = image2.GetSpacing() if any( list( abs(s1 - s2) > tolerance for s1, s2 in zip(spacing1, spacing2))): all_parameters_equal = False print( f'Images do not have the same spacing ({spacing1} != {spacing2})' ) if check_origin: origin1 = image1.GetOrigin() origin2 = image2.GetOrigin() if any( list( abs(o1 - o2) > tolerance for o1, o2 in zip(origin1, origin2))): all_parameters_equal = False print( f'Images do not have the same origin ({origin1} != {origin2})') return all_parameters_equal
def _calculate_area(image: sitk.Image, slice_number: int=-1) -> float: """Calculates the area of a slice in a label image. Args: image (sitk.Image): The 3-D label image. slice_number (int): The slice number to calculate the area. Defaults to -1, which will calculate the area on the intermediate slice. """ img_arr = sitk.GetArrayFromImage(image) if slice_number == -1: slice_number = int(img_arr.shape[0] / 2) # use the intermediate slice return img_arr[slice_number, ...].sum() * image.GetSpacing()[0] * image.GetSpacing()[1]
def sitk_to_nib( image: sitk.Image, keepdim: bool = False, ) -> Tuple[np.ndarray, np.ndarray]: data = sitk.GetArrayFromImage(image).transpose() num_components = image.GetNumberOfComponentsPerPixel() if num_components == 1: data = data[np.newaxis] # add channels dimension input_spatial_dims = image.GetDimension() if not keepdim: data = ensure_4d(data, False, num_spatial_dims=input_spatial_dims) assert data.shape[0] == num_components assert data.shape[-input_spatial_dims:] == image.GetSize() spacing = np.array(image.GetSpacing()) direction = np.array(image.GetDirection()) origin = image.GetOrigin() if len(direction) == 9: rotation = direction.reshape(3, 3) elif len(direction) == 4: # ignore first dimension if 2D (1, 1, H, W) rotation_2d = direction.reshape(2, 2) rotation = np.eye(3) rotation[1:3, 1:3] = rotation_2d spacing = 1, *spacing origin = 0, *origin rotation = np.dot(FLIP_XY, rotation) rotation_zoom = rotation * spacing translation = np.dot(FLIP_XY, origin) affine = np.eye(4) affine[:3, :3] = rotation_zoom affine[:3, 3] = translation return data, affine
def query_extract_region(fixed_image: sitk.Image, moving_image: sitk.Image, transform: sitk.Transform, registration_method: sitk.ImageRegistrationMethod): do_extract = util.query_yes_no( 'Do you wish to extract a sub-region to register based on? [y/n] >> ') if do_extract: itkplt.plot_overlay(fixed_image, moving_image, transform=transform) size = util.query_int('Enter the region size >> ') origin = [] for dim in range(len(fixed_image.GetSpacing())): origin_in_dim = util.query_float( 'Enter the origin in dimension {0} >> '.format(dim)) origin.append(origin_in_dim) origin = np.array(origin) fixed_region = extract_region(fixed_image, size, origin) moving_region = extract_region(moving_image, size * 1.1, origin - 0.05 * size, transform) query_registration_sampling_change(registration_method) return fixed_region, moving_region, do_extract else: return fixed_image, moving_image, do_extract
def _calculate_volume(image: sitk.Image): """Calculates the volume of a label image.""" voxel_volume = np.prod(image.GetSpacing()) number_of_voxels = sitk.GetArrayFromImage(image).sum() return number_of_voxels * voxel_volume
def centre_of_mass(image: sitk.Image) -> np.ndarray: r""" Compute the centre of mass of the image. A real-valued image represents the distribution of mass, and its centre of mass is defined as :math:`\frac{1}{\sum_p I(p)} \sum_p p I(p)`. Parameters ---------- image : sitk.Image Input image. Returns ------- np.ndarray World coordinates (x, y, z) of the centre of mass. """ data = sitk.GetArrayViewFromImage(image) grid = np.meshgrid(*[range(i) for i in data.shape], indexing='ij') grid = np.vstack([a.flatten() for a in grid]).T cm = np.average(grid, axis=0, weights=data.flatten()) return np.multiply(np.flip(cm, axis=0), image.GetSpacing()) - image.GetOrigin()
def label_stat_results(labelled_img:sitk.Image, pet_img:sitk.Image) -> dict : """a function to gather stats about each ROI Args: labelled_img (sitk.Image): [3D segmentation sitk.Image with label] pet_img (sitk.Image): [3D pet sitk.Image] Returns: [type]: [description] """ results = {} stats = sitk.LabelIntensityStatisticsImageFilter() stats.Execute(labelled_img, pet_img) pet_spacing = pet_img.GetSpacing() number_of_label = stats.GetNumberOfLabels() results['number_of_label'] = number_of_label volume = 0 for i in range(1, number_of_label + 1) : subresult = {} subresult['max'] = stats.GetMaximum(i) subresult['mean'] = stats.GetMean(i) subresult['median'] = stats.GetMedian(i) subresult['variance'] = stats.GetVariance(i) subresult['sd'] = stats.GetStandardDeviation(i) subresult['number_of_pixel'] = stats.GetNumberOfPixels(i) volume_voxel = pet_spacing[0] * pet_spacing[1] * pet_spacing[2] * 10**(-3) #ml subresult['volume'] = stats.GetNumberOfPixels(i) * volume_voxel subresult['centroid'] = stats.GetCentroid(i) volume += stats.GetNumberOfPixels(i) * volume_voxel results[i] = subresult results['total_vol'] = volume return results
def resample_image_to_voxel_size(image: sitk.Image, new_spacing, interpolator, fill_value=0) -> sitk.Image: """ resample a 3d image to a given voxel size (dx, dy, dz) :param image: 3D sitk image :param new_spacing: voxel size (dx, dy, dz) :param interpolator: :param fill_value: pixel value when a transformed pixel is outside of the image. :return: """ # computing image shape based on the desired voxel size orig_size = np.array(image.GetSize()) orig_spacing = np.array(image.GetSpacing()) new_spacing = np.array(new_spacing) new_size = orig_size * (orig_spacing / new_spacing) # Image dimensions are in integers new_size = np.ceil(new_size).astype(np.int) # SimpleITK expects lists, not ndarrays new_size = [int(s) for s in new_size] return resample_sitk_image(image, new_size, interpolator, fill_value)
def sitk_to_nib( image: sitk.Image, keepdim: bool = False, ) -> Tuple[np.ndarray, np.ndarray]: data = sitk.GetArrayFromImage(image).transpose() num_components = image.GetNumberOfComponentsPerPixel() if num_components == 1: data = data[np.newaxis] # add channels dimension input_spatial_dims = image.GetDimension() if input_spatial_dims == 2: data = data[..., np.newaxis] if not keepdim: data = ensure_4d(data, num_spatial_dims=input_spatial_dims) assert data.shape[0] == num_components assert data.shape[1:1 + input_spatial_dims] == image.GetSize() spacing = np.array(image.GetSpacing()) direction = np.array(image.GetDirection()) origin = image.GetOrigin() if len(direction) == 9: rotation = direction.reshape(3, 3) elif len(direction) == 4: # ignore first dimension if 2D (1, W, H, 1) rotation_2d = direction.reshape(2, 2) rotation = np.eye(3) rotation[:2, :2] = rotation_2d spacing = *spacing, 1 origin = *origin, 0 else: raise RuntimeError(f'Direction not understood: {direction}') rotation = np.dot(FLIP_XY, rotation) rotation_zoom = rotation * spacing translation = np.dot(FLIP_XY, origin) affine = np.eye(4) affine[:3, :3] = rotation_zoom affine[:3, 3] = translation return data, affine
def split_4d_itk(img_itk: sitk.Image) -> List[sitk.Image]: """ Helper function to split 4d itk images into multiple 3 images Args: img_itk: 4D input image Returns: List[sitk.Image]: 3d output images """ img_npy = sitk.GetArrayFromImage(img_itk) spacing = img_itk.GetSpacing() origin = img_itk.GetOrigin() direction = np.array(img_itk.GetDirection()).reshape(4, 4) spacing = tuple(list(spacing[:-1])) assert len(spacing) == 3 origin = tuple(list(origin[:-1])) assert len(origin) == 3 direction = tuple(direction[:-1, :-1].reshape(-1)) assert len(direction) == 9 images_new = [] for i, t in enumerate(range(img_npy.shape[0])): img = img_npy[t] images_new.append( create_itk_image_spatial_props(img, spacing, origin, direction)) return images_new
def image_resample(image: sitk.Image): ''' image = sitk.ReadImage(image_path) 使用 SimpleITK 自带函数重新缩放图像 ''' origin_spacing = image.GetSpacing() # 获取源分辨率 origin_size = image.GetSize() new_spacing = [1, 1, 1] # 设置新分辨率 resample = sitk.ResampleImageFilter() resample.SetInterpolator(sitk.sitkLinear) resample.SetDefaultPixelValue(0) resample.SetOutputSpacing(new_spacing) resample.SetOutputOrigin(image.GetOrigin()) resample.SetOutputDirection(image.GetDirection()) # 计算新图像的大小 new_size = [ int(np.round(origin_size[0] * (origin_spacing[0] / new_spacing[0]))), int(np.round(origin_size[1] * (origin_spacing[1] / new_spacing[1]))), int(np.round(origin_size[2] * (origin_spacing[2] / new_spacing[2]))) ] resample.SetSize(new_size) new_image = resample.Execute(image) return new_image
def zoom(image: sitk.Image, scale_factor: Union[float, Sequence[float]], interpolation: str = "linear", anti_alias: bool = True, anti_alias_sigma: Optional[float] = None) -> sitk.Image: """Rescale image, preserving its spatial extent. The rescaled image will have the same spatial extent (size) but will be rescaled by `scale_factor` in each dimension. Alternatively, a separate scale factor for each dimension can be specified by passing a sequence of floats. Parameters ---------- image The image to rescale. scale_factor If float, each dimension will be scaled by that factor. If tuple, each dimension will be scaled by the corresponding element. interpolation, optional The interpolation method to use. Valid options are: - "linear" for bi/trilinear interpolation (default) - "nearest" for nearest neighbour interpolation - "bspline" for order-3 b-spline interpolation anti_alias, optional Whether to smooth the image with a Gaussian kernel before resampling. Only used when downsampling, i.e. when `size < image.GetSize()`. This should be used to avoid aliasing artifacts. anti_alias_sigma, optional The standard deviation of the Gaussian kernel used for anti-aliasing. Returns ------- sitk.Image The rescaled image. """ dimension = image.GetDimension() if isinstance(scale_factor, float): scale_factor = (scale_factor, ) * dimension centre_idx = np.array(image.GetSize()) / 2 centre = image.TransformContinuousIndexToPhysicalPoint(centre_idx) transform = sitk.ScaleTransform(dimension, scale_factor) transform.SetCenter(centre) return resample(image, spacing=image.GetSpacing(), interpolation=interpolation, anti_alias=anti_alias, anti_alias_sigma=anti_alias_sigma, transform=transform, output_size=image.GetSize())
def resample_sitk_image(sitk_image: sitk.Image, new_size, interpolator="gaussian", fill_value=0) -> sitk.Image: """ modified version from: https://github.com/jonasteuwen/SimpleITK-examples/blob/master/examples/resample_isotropically.py """ # if pass a path to image if isinstance(sitk_image, str): sitk_image = sitk.ReadImage(sitk_image) assert (interpolator in _SITK_INTERPOLATOR_DICT.keys() ), "`interpolator` should be one of {}".format( _SITK_INTERPOLATOR_DICT.keys()) if not interpolator: interpolator = "linear" pixelid = sitk_image.GetPixelIDValue() if pixelid not in [1, 2, 4]: raise NotImplementedError( "Set `interpolator` manually, " "can only infer for 8-bit unsigned or 16, 32-bit signed integers" ) # 8-bit unsigned int if sitk_image.GetPixelIDValue() == 1: # if binary mask interpolate it as nearest interpolator = "nearest" sitk_interpolator = _SITK_INTERPOLATOR_DICT[interpolator] orig_pixelid = sitk_image.GetPixelIDValue() orig_origin = sitk_image.GetOrigin() orig_direction = sitk_image.GetDirection() # new spacing based on the desired output shape new_spacing = tuple( np.array(sitk_image.GetSpacing()) * np.array(sitk_image.GetSize()) / np.array(new_size)) # setup image resampler - SimpleITK 2.0 resample_filter = sitk.ResampleImageFilter() resample_filter.SetOutputSpacing(new_spacing) resample_filter.SetSize(new_size) resample_filter.SetOutputDirection(orig_direction) resample_filter.SetOutputOrigin(orig_origin) resample_filter.SetTransform(sitk.Transform()) resample_filter.SetDefaultPixelValue(orig_pixelid) resample_filter.SetInterpolator(sitk_interpolator) resample_filter.SetDefaultPixelValue(fill_value) # run it resampled_sitk_image = resample_filter.Execute(sitk_image) return resampled_sitk_image
def slice_by_slice(image: sitk.Image, *args, **kwargs): dim = image.GetDimension() iter_dim = 2 if dim <= iter_dim: image = func(image, *args, **kwargs) return image extract_size = list(image.GetSize()) extract_size[iter_dim:] = itertools.repeat(0, dim - iter_dim) extract_index = [0] * dim paste_idx = [slice(None, None)] * dim extractor = sitk.ExtractImageFilter() extractor.SetSize(extract_size) if inplace: for high_idx in itertools.product( *[range(s) for s in image.GetSize()[iter_dim:]]): extract_index[iter_dim:] = high_idx extractor.SetIndex(extract_index) paste_idx[iter_dim:] = high_idx image[paste_idx] = func(extractor.Execute(image), *args, **kwargs) else: img_list = [] for high_idx in itertools.product( *[range(s) for s in image.GetSize()[iter_dim:]]): extract_index[iter_dim:] = high_idx extractor.SetIndex(extract_index) paste_idx[iter_dim:] = high_idx img_list.append( func(extractor.Execute(image), *args, **kwargs)) for d in range(iter_dim, dim): step = reduce((lambda x, y: x * y), image.GetSize()[d + 1:], 1) join_series_filter = sitk.JoinSeriesImageFilter() join_series_filter.SetSpacing(image.GetSpacing()[d]) join_series_filter.SetOrigin(image.GetOrigin()[d]) img_list = [ join_series_filter.Execute(img_list[i::step]) for i in range(step) ] assert len(img_list) == 1 image = img_list[0] return image
def match_world_info(source: sitk.Image, target: sitk.Image, spacing: Union[bool, Tuple[int], List[int]] = True, origin: Union[bool, Tuple[int], List[int]] = True, direction: Union[bool, Tuple[int], List[int]] = True): """Copy world information (eg spacing, origin, direction) from one image object to another. This matching is sometimes necessary for slight differences in metadata perhaps from founding that may prevent ITK filters from executing. Args: source (:obj:`sitk.Image`): Source object whose relevant metadata will be copied into ``target``. target (:obj:`sitk.Image`): Target object whose corresponding metadata will be overwritten by that of ``source``. spacing: True to copy the spacing from ``source`` to ``target``, or the spacing to set in ``target``; defaults to True. origin: True to copy the origin from ``source`` to ``target``, or the origin to set in ``target``; defaults to True. direction: True to copy the direction from ``source`` to ``target``, or the direction to set in ``target``; defaults to True. """ # get the world info from the source if not already set if spacing is True: spacing = source.GetSpacing() if origin is True: origin = source.GetOrigin() if direction is True: direction = source.GetDirection() # set the values in the target _logger.debug( "Adjusting spacing from %s to %s, origin from %s to %s, " "direction from %s to %s", target.GetSpacing(), spacing, target.GetOrigin(), origin, target.GetDirection(), direction) if spacing: target.SetSpacing(spacing) if origin: target.SetOrigin(origin) if direction: target.SetDirection(direction)
def display_info(img: sitk.Image) -> None: """display information about a sitk.Image Args: img (sitk.Image): [sitk image] """ print('img information :') print('\t Origin :', img.GetOrigin()) print('\t Size :', img.GetSize()) print('\t Spacing :', img.GetSpacing()) print('\t Direction :', img.GetDirection())
def sitk_to_nib(image: sitk.Image) -> Tuple[np.ndarray, np.ndarray]: data = sitk.GetArrayFromImage(image).transpose() spacing = np.array(image.GetSpacing()) rotation = np.array(image.GetDirection()).reshape(3, 3) rotation = np.dot(FLIP_XY, rotation) rotation_zoom = rotation * spacing translation = np.dot(FLIP_XY, image.GetOrigin()) affine = np.eye(4) affine[:3, :3] = rotation_zoom affine[:3, 3] = translation return data, affine
def resize(image: sitk.Image, size: Union[int, Sequence[int], np.ndarray], interpolation: str = "linear", anti_alias: bool = True, anti_alias_sigma: Optional[float] = None) -> sitk.Image: """Resize image to a given size by resampling coordinates. Parameters ---------- image The image to be resize. size The new image size. If float, assumes the same size in all directions. Alternatively, a sequence of floats can be passed to specify size along each dimension. Passing 0 at any position will keep the original size along that dimension. interpolation, optional The interpolation method to use. Valid options are: - "linear" for bi/trilinear interpolation (default) - "nearest" for nearest neighbour interpolation - "bspline" for order-3 b-spline interpolation anti_alias, optional Whether to smooth the image with a Gaussian kernel before resampling. Only used when downsampling, i.e. when `size < image.GetSize()`. This should be used to avoid aliasing artifacts. anti_alias_sigma, optional The standard deviation of the Gaussian kernel used for anti-aliasing. Returns ------- sitk.Image The resized image. """ original_size = np.array(image.GetSize()) original_spacing = np.array(image.GetSpacing()) if isinstance(size, (float, int)): new_size = np.repeat(size, len(original_size)).astype(np.float64) else: size = np.asarray(size) new_size = np.where(size == 0, original_size, size) new_spacing = original_spacing * original_size / new_size return resample(image, new_spacing, anti_alias=anti_alias, anti_alias_sigma=anti_alias_sigma, interpolation=interpolation)
def transaxis(img: sitk.Image, dtype: np.dtype) -> sitk.Image: spacing = img.GetSpacing() img_raw = sitk.GetArrayFromImage(img) img_raw = np.transpose(img_raw, axes=[2, 1, 0]) img_raw = img_raw[-1::-1, :, :] img_new = sitk.GetImageFromArray(img_raw.astype(dtype)) img_new.SetSpacing(tuple(reversed(spacing))) img_new.SetDirection((1, 0, 0, 0, 1, 0, 0, 0, 1)) return img_new
def set_origin_image(self, origin_img:sitk.Image) -> None : """method to set the origin sitk.Image on which we want to resample Args: origin_img (sitk.Image): [] """ self.origin_img = origin_img self.origin_size = origin_img.GetSize() self.origin_spacing = origin_img.GetSpacing() self.origin_direction = origin_img.GetDirection() self.origin_origin = origin_img.GetOrigin()
def _assert_3d(self, image: sitk.Image, is_vector=False): self.assertEqual(self.properties_3d.size, image.GetSize()) if is_vector: self.assertEqual(self.no_vector_components, image.GetNumberOfComponentsPerPixel()) else: self.assertEqual(1, image.GetNumberOfComponentsPerPixel()) self.assertEqual(self.origin_spacing_3d, image.GetOrigin()) self.assertEqual(self.origin_spacing_3d, image.GetSpacing()) self.assertEqual(self.direction_3d, image.GetDirection())
def __init__(self, image: sitk.Image): """Initializes a new instance of the ImageInformation class. Args: image (sitk.Image): The image whose properties to hold. """ self.size = image.GetSize() self.origin = image.GetOrigin() self.spacing = image.GetSpacing() self.direction = image.GetDirection() self.dimensions = image.GetDimension() self.number_of_components_per_pixel = image.GetNumberOfComponentsPerPixel() self.pixel_id = image.GetPixelID()
def rgb_to_grayscale_img(image: sitk.Image, white_light_filter_value=0.9): """Convert an RGB to grayscale image by extracting the average intensity, filtering out white light >0.9 max""" array = sitk.GetArrayFromImage(image) dimension = image.GetDimension() grayscale_array = np.average(array, 2) grayscale_array[grayscale_array > white_light_filter_value * np.max(array)] = 0 grayscale_image = sitk.GetImageFromArray(grayscale_array) grayscale_image.SetSpacing(image.GetSpacing()) grayscale_image.SetOrigin(image.GetOrigin()) return grayscale_image
def create_circle_mask_itk( image_itk: sitk.Image, world_centers: Sequence[Sequence[float]], world_rads: Sequence[float], ndim: int = 3, ) -> sitk.Image: """ Creates an itk image with circles defined by center points and radii Args: image_itk: original image (used for the coordinate frame) world_centers: Sequence of center points in world coordiantes (x, y, z) world_rads: Sequence of radii to use ndim: number of spatial dimensions Returns: sitk.Image: mask with circles """ image_np = sitk.GetArrayFromImage(image_itk) min_spacing = min(image_itk.GetSpacing()) if image_np.ndim > ndim: image_np = image_np[0] mask_np = np.zeros_like(image_np).astype(np.uint8) for _id, (world_center, world_rad) in enumerate(zip(world_centers, world_rads), start=1): check_rad = (world_rad / min_spacing) * 1.5 # add some buffer to it bounds = [] center = image_itk.TransformPhysicalPointToContinuousIndex( world_center)[::-1] for ax, c in enumerate(center): bounds.append(( max(0, int(c - check_rad)), min(mask_np.shape[ax], int(c + check_rad)), )) coord_box = product(*[list(range(b[0], b[1])) for b in bounds]) # loop over every pixel position for coord in coord_box: world_coord = image_itk.TransformIndexToPhysicalPoint( tuple(reversed(coord))) # reverse order to x, y, z for sitk dist = np.linalg.norm( np.array(world_coord) - np.array(world_center)) if dist <= world_rad: mask_np[tuple(coord)] = _id assert mask_np.max() == _id mask_itk = sitk.GetImageFromArray(mask_np) return copy_meta_data_itk(image_itk, mask_itk)
def get_mask(ground_truth: sitk.Image, ground_truth_labels: list, label_percentages: list, background_mask: sitk.Image = None) -> sitk.Image: """Gets a training mask. Args: ground_truth (sitk.Image): The ground truth image. ground_truth_labels (list of int): The ground truth labels, where 0=background, 1=label1, 2=label2, ..., e.g. [0, 1] label_percentages (list of float): The percentage of voxels of a corresponding label to extract as mask, e.g. [0.2, 0.2]. background_mask (sitk.Image): A mask, where intensity 0 indicates voxels to exclude independent of the label. Returns: sitk.Image: The training mask. """ # initialize mask ground_truth_array = sitk.GetArrayFromImage(ground_truth) mask_array = np.zeros(ground_truth_array.shape, dtype=np.uint8) # exclude background if background_mask is not None: background_mask_array = sitk.GetArrayFromImage(background_mask) background_mask_array = np.logical_not(background_mask_array) ground_truth_array = ground_truth_array.astype( float) # convert to float because of np.nan ground_truth_array[background_mask_array] = np.nan for label_idx, label in enumerate(ground_truth_labels): indices = np.transpose(np.where(ground_truth_array == label)) np.random.shuffle(indices) no_mask_items = int(indices.shape[0] * label_percentages[label_idx]) for no in range(no_mask_items): x = indices[no][0] y = indices[no][1] z = indices[no][2] mask_array[x, y, z] = 1 # this is a masked item mask = sitk.GetImageFromArray(mask_array) mask.SetOrigin(ground_truth.GetOrigin()) mask.SetDirection(ground_truth.GetDirection()) mask.SetSpacing(ground_truth.GetSpacing()) return mask
def get_cuboid_image(radii_world, reference: sitk.Image, center_ras): r, a, s = center_ras center_lps = -r, -a, s center_voxel = reference.TransformPhysicalPointToIndex(center_lps) spacing = np.array(reference.GetSpacing()) radii_voxel = np.array(radii_world) / spacing radii_voxel = radii_voxel.round().astype(np.uint16) axes_voxel = 2 * radii_voxel cuboid = sitk.Image(*axes_voxel.tolist(), sitk.sitkUInt8) + 1 result = reference * 0 destination = (center_voxel - radii_voxel).tolist() paste = sitk.PasteImageFilter() paste.SetDestinationIndex(destination) paste.SetSourceSize(cuboid.GetSize()) result = paste.Execute(result, cuboid) return result