Deep learning for NeuroImaging in Python.

Note

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

surfify.utils.sampling.find_neighbors(start_node, order, neighbors)[source]¶

Recursively find neighbors from a starting node up to a certain order.

Parameters:

start_node : int

node index to start search from.

order : int

order up to which to look for neighbors.

neighbors : dict

neighbors for each node as generated by the ‘neighbors’ or ‘neighbors_rec’ functions.

Returns:

indices : list of int

the n-ring neighbors indices.

See also

neighbors, neighbors_rec

Examples

>>> from surfify.utils import icosahedron, neighbors_rec, find_neighbors
>>> import matplotlib.pyplot as plt
>>> from surfify.plotting import plot_trisurf
>>> ico2_verts, ico2_tris = icosahedron(order=2)
>>> neighs = neighbors_rec(ico2_verts, ico2_tris, size=3, zoom=3)[0]
>>> neighs = neighs.reshape(len(neighs), -1)
>>> neighs = neighbors(ico2_verts, ico2_tris, depth=1,
                       direct_neighbor=True)
>>> node = 0
>>> node_neighs = find_neighbors(node, order=3, neighbors=neighs)
>>> fig, ax = plt.subplots(1, 1, subplot_kw={
        "projection": "3d", "aspect": "auto"}, figsize=(10, 10))
>>> plot_trisurf(ico2_verts, triangles=ico2_tris, colorbar=False, fig=fig,
                 ax=ax)
>>> center = ico2_verts[node]
>>> for cnt, idx in enumerate(node_neighs):
>>>     point = ico2_verts[idx]
>>>     ax.scatter(point[0], point[1], point[2], marker="o", c="red",
                   s=100)
>>> ax.scatter(center[0], center[1], center[2], marker="o", c="blue",
               s=100)
>>> plt.show()