Function extreme_points_to_image

monai/transforms/utils.py:1638–1681

Please refer to :py:class:`monai.transforms.AddExtremePointsChannel` for the usage. Applies a gaussian filter to the extreme points image. Then the pixel values in points image are rescaled to range [rescale_min, rescale_max]. Args: points: Extreme points of the object/org

(
    points: list[tuple[int, ...]],
    label: NdarrayOrTensor,
    sigma: Sequence[float] | float | Sequence[torch.Tensor] | torch.Tensor = 0.0,
    rescale_min: float = -1.0,
    rescale_max: float = 1.0,
)

def extreme_points_to_image(
    points: list[tuple[int, ...]],
    label: NdarrayOrTensor,
    sigma: Sequence[float] | float | Sequence[torch.Tensor] | torch.Tensor = 0.0,
    rescale_min: float = -1.0,
    rescale_max: float = 1.0,
) -> torch.Tensor:
    """
    Please refer to :py:class:`monai.transforms.AddExtremePointsChannel` for the usage.

    Applies a gaussian filter to the extreme points image. Then the pixel values in points image are rescaled
    to range [rescale_min, rescale_max].

    Args:
        points: Extreme points of the object/organ.
        label: label image to get extreme points from. Shape must be
            (1, spatial_dim1, [, spatial_dim2, ...]). Doesn't support one-hot labels.
        sigma: if a list of values, must match the count of spatial dimensions of input data,
            and apply every value in the list to 1 spatial dimension. if only 1 value provided,
            use it for all spatial dimensions.
        rescale_min: minimum value of output data.
        rescale_max: maximum value of output data.
    """
    # points to image
    # points_image = torch.zeros(label.shape[1:], dtype=torch.float)
    points_image = torch.zeros_like(torch.as_tensor(label[0]), dtype=torch.float)
    for p in points:
        points_image[p] = 1.0

    if isinstance(sigma, Sequence):
        sigma = [torch.as_tensor(s, device=points_image.device) for s in sigma]
    else:
        sigma = torch.as_tensor(sigma, device=points_image.device)

    # add channel and add batch
    points_image = points_image.unsqueeze(0).unsqueeze(0)
    gaussian_filter = GaussianFilter(label.ndim - 1, sigma=sigma)
    points_image = gaussian_filter(points_image).squeeze(0).detach()

    # rescale the points image to [rescale_min, rescale_max]
    min_intensity = points_image.min()
    max_intensity = points_image.max()
    points_image = (points_image - min_intensity) / (max_intensity - min_intensity)
    return points_image * (rescale_max - rescale_min) + rescale_min


def map_spatial_axes(