mridc.collections.quantitative.parts package

Submodules

mridc.collections.quantitative.parts.transforms module

class mridc.collections.quantitative.parts.transforms.qMRIDataTransforms(TEs: Optional[List[float]], precompute_quantitative_maps: bool = True, apply_prewhitening: bool = False, prewhitening_scale_factor: float = 1.0, prewhitening_patch_start: int = 10, prewhitening_patch_length: int = 30, apply_gcc: bool = False, gcc_virtual_coils: int = 10, gcc_calib_lines: int = 24, gcc_align_data: bool = True, coil_combination_method: str = 'SENSE', dimensionality: int = 2, mask_func: Optional[List[MaskFunc]] = None, shift_mask: bool = False, mask_center_scale: Optional[float] = 0.02, half_scan_percentage: float = 0.0, remask: bool = False, crop_size: Optional[Tuple[int, int]] = None, kspace_crop: bool = False, crop_before_masking: bool = True, kspace_zero_filling_size: Optional[Tuple] = None, normalize_inputs: bool = False, fft_centered: bool = True, fft_normalization: str = 'ortho', max_norm: bool = True, spatial_dims: Optional[Sequence[int]] = None, coil_dim: int = 0, shift_B0_input: bool = False, use_seed: bool = True)[source]

Bases: object

qMRI preprocessing data transforms.

__call__(kspace: ndarray, sensitivity_map: ndarray, qmaps: ndarray, mask: ndarray, eta: ndarray, target: ndarray, attrs: Dict, fname: str, slice_idx: int) → Tuple[Union[Tensor, List[Any], List[Tensor]], Union[Tensor, Any], Union[Tensor, List[Any], List[Tensor]], Union[Tensor, Any], Union[Tensor, List[Any], List[Tensor]], Union[Tensor, Any], Union[Tensor, List[Any], List[Tensor]], Union[Tensor, Any], Tensor, Tensor, Union[Tensor, List[Union[float, Tensor, Any]], float, Any], Union[Tensor, None, Any], Union[List[Union[Tensor, Any]], Tensor, List[Tensor], Any], Union[Tensor, Any], Union[Tensor, None, Any], Union[Tensor, Any], str, int, Union[List[int], int, Tensor]][source]

Apply the data transform.

Parameters

  • kspace (The kspace.) –

  • sensitivity_map (The sensitivity map.) –

  • qmaps (The quantitative maps.) –

  • mask (List, sampling mask if exists and brain mask and head mask.) –

  • eta (The initial estimation.) –

  • target (The target.) –

  • attrs (The attributes.) –

  • fname (The file name.) –

  • slice_idx (The slice number.) –

Return type

The transformed data.

Module contents