FastSurferCNN.data_loader.conform¶

class FastSurferCNN.data_loader.conform.Criteria(value)[source]¶: An enumeration.

FastSurferCNN.data_loader.conform.check_affine_in_nifti(img, logger=None)[source]¶

Check the affine in nifti Image.

Sets affine with qform, if it exists and differs from sform. If qform does not exist, voxel sizes between header information and information in affine are compared. In case these do not match, the function returns False (otherwise True).

Parameters:

imgUnion[nib.Nifti1Image, nib.Nifti2Image]: Loaded nifti-image.
loggerOptional[logging.Logger]: Logger object or None (default) to log or print an info message to stdout (for None).

Returns:

bool: False, if voxel sizes in affine and header differ.

FastSurferCNN.data_loader.conform.find_img_size_by_fov(img, vox_size, min_dim=256)[source]¶

Find the cube dimension (>= 256) to cover the field of view of img.

If vox_size is one, the img_size MUST always be min_dim (the FreeSurfer standard).

Parameters:

imgnib.analyze.SpatialImage: Loaded source image.
vox_sizefloat: The target voxel size in mm.
min_dimint: Minimal image dimension in voxels (default 256).

Returns:

int: The number of voxels needed to cover field of view.

Notes

This function only needs the header (not the data).

FastSurferCNN.data_loader.conform.find_min_size(img, max_size=1)[source]¶

Find minimal voxel size <= 1mm.

Parameters:

imgnib.analyze.SpatialImage: Loaded source image.
max_sizefloat: Maximal voxel size in mm (default: 1.0).

Returns:

float: Rounded minimal voxel size.

Notes

This function only needs the header (not the data).

FastSurferCNN.data_loader.conform.get_conformed_vox_img_size(img, conform_vox_size, conform_to_1mm_threshold=None)[source]¶

Extract the voxel size and the image size.

This function only needs the header (not the data).

Parameters:

imgnib.analyze.SpatialImage: Loaded source image.
conform_vox_sizefloat, “min”: The voxel size parameter to use: either a voxel size as float, or the string “min” to automatically find a suitable voxel size (smallest per-dimension voxel size).
conform_to_1mm_thresholdfloat, optional: The threshold for which image voxel size should be conformed to 1mm instead of conformed to the smallest voxel size (default: None, never apply).

Returns:

conformed_vox_sizefloat: The determined voxel size to conform the image to.
conformed_img_sizeint: The size of the image adjusted to the conformed voxel size.

FastSurferCNN.data_loader.conform.getscale(data, dst_min, dst_max, f_low=0.0, f_high=0.999)[source]¶

Get offset and scale of image intensities to robustly rescale to dst_min..dst_max.

Equivalent to how mri_convert conforms images.

Parameters:

datanp.ndarray: Image data (intensity values).
dst_minfloat: Future minimal intensity value.
dst_maxfloat: Future maximal intensity value.
f_lowfloat, default=0.0: Robust cropping at low end (0.0=no cropping).
f_highfloat, default=0.999: Robust cropping at higher end (0.999=crop one thousandth of highest intensity).

Returns:

float src_min: (adjusted) offset.
float: Scale factor.

FastSurferCNN.data_loader.conform.is_lia(affine, strict=True, eps=1e-06)[source]¶

Checks whether the affine is LIA-oriented.

Parameters:

affinenp.ndarray: The affine to check.
strictbool, default=True: Whether the orientation should be “exactly” LIA or just similar to LIA (i.e. it is more LIA than other directions).
epsfloat, default=1e-6: The threshold in strict mode.

Returns:

bool: Whether the affine is LIA-oriented.

FastSurferCNN.data_loader.conform.is_resampling_vox2vox(vox2vox, eps=1e-06)[source]¶

Check whether the affine is resampling or just reordering.

Parameters:

vox2voxnp.ndarray: The affine matrix.
epsfloat, default=1e-6: The epsilon for the affine check.

Returns:

bool: The result.

FastSurferCNN.data_loader.conform.map_image(img, out_affine, out_shape, ras2ras=None, order=1, dtype=None)[source]¶

Map image to new voxel space (RAS orientation).

Parameters:

imgnib.analyze.SpatialImage: The src 3D image with data and affine set.
out_affinenp.ndarray: Trg image affine.
out_shapetuple[int, …], np.ndarray: The trg shape information.
ras2rasnp.ndarray, optional: An additional mapping that should be applied (default=id to just reslice).
orderint, default=1: Order of interpolation (0=nearest,1=linear,2=quadratic,3=cubic).
dtypeType, optional: Target dtype of the resulting image (relevant for reorientation, default=keep dtype of img).

Returns:

np.ndarray: Mapped image data array.

FastSurferCNN.data_loader.conform.options_parse()[source]¶

Command line option parser.

Returns:

options: Object holding options.

FastSurferCNN.data_loader.conform.rescale(data, dst_min, dst_max, f_low=0.0, f_high=0.999)[source]¶

Rescale image intensity values (0-255).

Parameters:

datanp.ndarray: Image data (intensity values).
dst_minfloat: Future minimal intensity value.
dst_maxfloat: Future maximal intensity value.
f_lowfloat, default=0.0: Robust cropping at low end (0.0=no cropping).
f_highfloat, default=0.999: Robust cropping at higher end (0.999=crop one thousandth of highest intensity).

Returns:

np.ndarray: Scaled image data.

FastSurferCNN.data_loader.conform.scalecrop(data, dst_min, dst_max, src_min, scale)[source]¶

Crop the intensity ranges to specific min and max values.

Parameters:

datanp.ndarray: Image data (intensity values).
dst_minfloat: Future minimal intensity value.
dst_maxfloat: Future maximal intensity value.
src_minfloat: Minimal value to consider from source (crops below).
scalefloat: Scale value by which source will be shifted.

Returns:

np.ndarray: Scaled image data.