FanProjectorFunction#

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

Bases: Function

Summary#

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

Notes

Provides a differentiable interface to the CUDA-accelerated Siddon ray-tracing method with a cell-constant image basis for fan beam geometry, where rays diverge from a point X-ray source to a linear detector array. The forward pass computes sinograms using divergent beam geometry, and the backward pass computes gradients via adjoint backprojection.

Examples

>>> import torch
>>> from diffct import FanProjectorFunction, circular_trajectory_2d_fan
>>>
>>> image = torch.randn(256, 256, device='cuda', requires_grad=True)
>>> src_pos, det_center, det_u_vec = circular_trajectory_2d_fan(360, sid=1000.0, sdd=1500.0, device='cuda')
>>> sinogram = FanProjectorFunction.apply(image, src_pos, det_center, det_u_vec, 512, 1.0)
>>> sinogram.sum().backward()
>>> image.grad.shape
torch.Size([256, 256])
static backward(ctx, grad_sinogram)[source]#
static forward(ctx, image, src_pos, det_center, det_u_vec, num_detectors, detector_spacing, voxel_spacing=1.0)[source]#

Compute the 2D fan 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.

  • src_pos (torch.Tensor) – Source positions for each view, shape (n_views, 2), in physical units.

  • det_center (torch.Tensor) – Detector center 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) – Physical spacing between detector elements.

  • 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 fan beam 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 fan beam geometries.

  • Uses cell-constant Siddon ray tracing.

Examples

>>> image = torch.randn(256, 256, device='cuda', requires_grad=True)
>>> src_pos, det_center, det_u_vec = circular_trajectory_2d_fan(360, 1000.0, 1500.0, device='cuda')
>>> sinogram = FanProjectorFunction.apply(
...     image, src_pos, det_center, det_u_vec, 512, 1.0
... )
Parameters:

  • args (Any)

  • kwargs (Any)

Return type:

Any