ParallelProjectorFunction#

class diffct.ParallelProjectorFunction(*args, **kwargs)[source]#

Bases: Function

Summary#

PyTorch autograd function for differentiable 2D parallel beam forward projection.

Notes

Provides a differentiable interface to the CUDA-accelerated Siddon ray-tracing method with a cell-constant image basis for parallel beam CT geometry. The forward pass computes the sinogram from a 2D image using parallel beam geometry. The backward pass computes gradients using the adjoint backprojection operation. Requires NVIDIA CUDA hardware. Geometry tensors are moved to the image’s device; execution uses float32.

Examples

>>> import torch
>>> from diffct import ParallelProjectorFunction, circular_trajectory_2d_parallel
>>>
>>> image = torch.randn(128, 128, device='cuda', requires_grad=True)
>>> ray_dir, det_origin, det_u_vec = circular_trajectory_2d_parallel(180, device='cuda')
>>> sinogram = ParallelProjectorFunction.apply(image, ray_dir, det_origin, det_u_vec, 192, 1.0)
>>> sinogram.sum().backward()
>>> image.grad.shape
torch.Size([128, 128])
static backward(ctx, grad_sinogram)[source]#
static forward(ctx, image, ray_dir, det_origin, det_u_vec, num_detectors, detector_spacing=1.0, voxel_spacing=1.0)[source]#

Compute the 2D parallel beam forward projection with arbitrary trajectories using CUDA acceleration.

Parameters:

  • image (torch.Tensor) – Floating-point CUDA image of shape (H, W), converted to float32 for execution.

  • ray_dir (torch.Tensor) – Ray direction unit vectors for each view, shape (n_views, 2).

  • det_origin (torch.Tensor) – Detector origin positions for each view, shape (n_views, 2), in physical units.

  • det_u_vec (torch.Tensor) – Detector u-direction unit vectors for each view, shape (n_views, 2).

  • num_detectors (int) – Number of detector elements in the sinogram (columns).

  • detector_spacing (float, optional) – Physical spacing between detector elements (default: 1.0).

  • voxel_spacing (float, optional) – Physical size of one voxel (in same units as detector_spacing, default: 1.0).

Returns:

sinogram – 2D tensor of shape (n_views, num_detectors) containing the forward projection (sinogram) on the same device as image.

Return type:

torch.Tensor

Notes

  • Geometry tensors are moved to the image’s CUDA device and converted to float32.

  • Data derivatives support higher orders; geometry derivatives are first-order only.

  • Supports arbitrary parallel beam geometries.

  • Uses cell-constant Siddon ray tracing.

Examples

>>> image = torch.randn(128, 128, device='cuda', requires_grad=True)
>>> ray_dir, det_origin, det_u_vec = circular_trajectory_2d_parallel(180, device='cuda')
>>> sinogram = ParallelProjectorFunction.apply(
...     image, ray_dir, det_origin, det_u_vec, 128, 1.0
... )
Parameters:

  • args (Any)

  • kwargs (Any)

Return type:

Any