mridc.collections.reconstruction.models.crossdomain package
Submodules
mridc.collections.reconstruction.models.crossdomain.crossdomain module
- class mridc.collections.reconstruction.models.crossdomain.crossdomain.CrossDomainNetwork(image_model_list: Module, kspace_model_list: Optional[Module] = None, domain_sequence: str = 'KIKI', image_buffer_size: int = 1, kspace_buffer_size: int = 1, normalize_image: bool = False, fft_centered: bool = True, fft_normalization: str = 'ortho', spatial_dims: Optional[Tuple[int, int]] = None, coil_dim: int = 1, **kwargs)[source]
Bases:
Module
This performs optimisation in both, k-space (“K”) and image (“I”) domains according to domain_sequence.
- forward(masked_kspace: Tensor, sensitivity_map: Tensor, sampling_mask: Tensor) Tensor [source]
Computes the forward pass of CrossDomainNetwork.
- Parameters
masked_kspace (Subsampled k-space data.) – torch.tenor, shape [batch_size, n_coil, height, width, 2]
sensitivity_map (Sensitivity map.) – torch.tenor, shape [batch_size, n_coil, height, width, 2]
sampling_mask (Sampling mask.) – torch.tenor, shape [batch_size, 1, height, width, 1]
- Returns
torch.tenor, shape [batch_size, height, width, 2]
- Return type
Output image.
- image_correction(block_idx, image_buffer, kspace_buffer, sampling_mask, sensitivity_map)[source]
Performs image correction.
- kspace_correction(block_idx, image_buffer, kspace_buffer, sampling_mask, sensitivity_map, masked_kspace)[source]
Performs k-space correction.
- training: bool
mridc.collections.reconstruction.models.crossdomain.multicoil module
- class mridc.collections.reconstruction.models.crossdomain.multicoil.MultiCoil(model: Module, coil_dim: int = 1, coil_to_batch: bool = False)[source]
Bases:
Module
This makes the forward pass of multi-coil data of shape (N, N_coils, H, W, C) to a model. If coil_to_batch is set to True, coil dimension is moved to the batch dimension. Otherwise, it passes to the model each coil-data individually.
- forward(x: Tensor) Tensor [source]
Performs the forward pass of MultiCoil.
- Parameters
x (Multi-coil input.) – torch.Tensor, shape (N, N_coils, H, W, C)
- Returns
torch.Tensor, shape (N, N_coils, H, W, C)
- Return type
Multi-coil output.
- training: bool