Note

This page is a reference documentation. It only explains the function signature, and not how to use it. Please refer to the user guide for the big picture.

fmralign.embeddings.whole_brain.get_laplacian_embedding¶

fmralign.embeddings.whole_brain.get_laplacian_embedding(mask_img, k, sigma=1e-08)[source]¶

Computes the Laplacian embedding of a given mask image or surface mesh.

Given a mask image (Nifti1Image) or a surface mesh (InMemoryMesh), this function computes the Laplace-Beltrami eigenmodes on the vertices defined by the mask or mesh. It solves a generalized eigenvalue problem to return the first k eigenmodes.

Note: The zero-order eigenmode is skipped.

Parameters:

mask_imgNifti1Image or InMemoryMesh: Input mask image or surface mesh.
kint: Number of eigenmodes to compute.
sigmafloat, optional: Stability parameter passed to the sparse solver, by default 1e-8.

Returns:

evecsndarray of shape (k, n_vertices): The computed Laplacian eigenmodes.