sklearn

dbdicom.extensions.sklearn.kmeans(features, mask=None, n_clusters=2, multiple_series=False, normalize=True, return_features=False)

Labels structures in an image

Wrapper for sklearn.cluster.KMeans function.

Parameters:

• input (list of dbdicom series (one for each feature))

• mask (optional mask for clustering)

Returns:

clusters

Return type:

list of dbdicom series, with labels per cluster.

dbdicom.extensions.sklearn.kmeans_4d(features, mask=None, n_clusters=2, multiple_series=False, normalize=True, return_features=False)

dbdicom.extensions.sklearn.masks_to_label(masks)

Convert a list of masks into a single label series

dbdicom.extensions.sklearn.sequential_kmeans(features, mask=None, n_clusters=2, multiple_series=False)

Labels structures in an image using sequential k-means clustering

Sequential here means that the clustering is always performed on a single feature using the output of the previous iteration as a mask for the next.

Parameters:

• input (list of dbdicom series (one for each feature))

• mask (optional mask for clustering)

Returns:

clusters

Return type:

list of dbdicom series, with labels per cluster.