FastSurferCNN.reduce_to_aseg

FastSurferCNN.reduce_to_aseg.create_mask(aseg_data, dnum, enum)

Create dilated mask.

Parameters:

aseg_datanpt.NDArray[int]

The input segmentation data.

dnumint

The number of iterations for the dilation operation.

enumint

The number of iterations for the erosion operation.

Returns:

• Returns aseg_data.

FastSurferCNN.reduce_to_aseg.flip_wm_islands(aseg_data)

Flip labels of disconnected white matter islands to the other hemisphere.

Parameters:

aseg_datanumpy.ndarray

The input segmentation data.

Returns:

flip_datanumpy.ndarray

The segmentation data with flipped WM labels.

FastSurferCNN.reduce_to_aseg.options_parse()

Command line option parser.

Returns:

options

Object holding options.

FastSurferCNN.reduce_to_aseg.reduce_to_aseg(data_inseg)

Reduce the input segmentation to a simpler segmentation.

Parameters:

data_insegnp.ndarray, torch.Tensor

The input segmentation. This should be a 3D array where the value at each position represents the segmentation label for that position.

Returns:

data_insegnp.ndarray, torch.Tensor

The reduced segmentation.