`trw.transforms.spatial_info`¶

Module Contents¶

Classes¶

SpatialInfo

Represent a the geometric space of a n-dimensional (2D or 3D) volume.

Functions¶

`make_aligned_patient_scale_transform`(origin: trw.basic_typing.Length, spacing: trw.basic_typing.Length) → torch.Tensor	Make a patient scale transform from (origin, spacing, without rotation or shear component)
`patient_scale_transform_get_spacing`(pst: torch.Tensor) → torch.Tensor	Return the spacing (expansion factor) of the transformation per dimension ZYX
`patient_scale_transform_get_origin`(pst: torch.Tensor) → torch.Tensor	Return the origin of the transformation per dimension ZYX

trw.transforms.spatial_info.make_aligned_patient_scale_transform(origin: trw.basic_typing.Length, spacing: trw.basic_typing.Length) → torch.Tensor¶

Make a patient scale transform from (origin, spacing, without rotation or shear component)

Parameters

origin – (Z)YX origin of the geometric space (millimeter)
spacing – (Z)YX spacing of the geometric space (millimeter)

Returns

a patient scale transform, mapping a (Z)YX voxel to a position in (Z)YX defined in millimeter

trw.transforms.spatial_info.patient_scale_transform_get_spacing(pst: torch.Tensor) → torch.Tensor¶

Return the spacing (expansion factor) of the transformation per dimension ZYX

Parameters: pst – a 3x3 or 4x4 transformation matrix
Returns: [Z]YX spacing

trw.transforms.spatial_info.patient_scale_transform_get_origin(pst: torch.Tensor) → torch.Tensor¶

Return the origin of the transformation per dimension ZYX

Parameters: pst – a 3x3 or 4x4 transformation matrix
Returns: [Z]YX spacing

class trw.transforms.spatial_info.SpatialInfo(shape: trw.basic_typing.ShapeX, patient_scale_transform: Optional[torch.Tensor] = None, origin: Optional[trw.basic_typing.Length] = None, spacing: Optional[trw.basic_typing.Length] = None)¶

Represent a the geometric space of a n-dimensional (2D or 3D) volume.

Concepts: patient scale transform

we often need to work with data in a given geometric space. This can be achieved by mapping voxel indices of a tensor to given geometric space by applying a linear transform on the location of the voxel to express.

This patient transform can be decomposed as multiple linear transforms such as translation, rotation, zoom and shearing. SpatialInfo will encode its geometric space as PST = Translation * (RotationZ *) RotationY * RotationZ * Spacing

The matrix is a homogeneous transformation matrix:

```: RXx RYx RZx Tx |
PST = | RXy RYy RZy Ty |: RXz RYz RZz Tz |

0 0 0 1 |

```

with (RX, RY, RZ) the basis of the geometric space. The spacing is defined as (||RX||^2, ||RY||^2, ||RZ||^2).

Notes

function will require calls argument names (*), since the xyz / zyx is cumbersome and probably both conventions will need to be supported in the future

We use arbitrary unit millimeter unit for all the attributes.

set_patient_scale_transform(self, patient_scale_transform: torch.Tensor) → None¶

property spacing(self) → numpy.ndarray¶: Calculate the spacing of the PST. Return the components as ZYX order.

property origin(self) → numpy.ndarray¶: Return the origin expressed in world space (expressed as ZYX order).

property center(self) → numpy.ndarray¶: Return the center in world space (expressed as ZYX order).

index_to_position(self, *, index_zyx: torch.Tensor) → torch.Tensor¶

Map an index to world space

Parameters: index_zyx – coordinate in index space
Returns: position in world space (Z)YX

position_to_index(self, *, position_zyx: torch.Tensor) → torch.Tensor¶

Map world space coordinate to an index

Parameters: position_zyx – position in world space
Returns: coordinate in index space (Z)YX

sub_geometry(self, *, start_index_zyx: torch.Tensor, end_index_zyx_inclusive: torch.Tensor)¶

Create a sub-geometry from min and max indices