STAPLE

Class: NodeMaskStaple

Node Icon

The STAPLE filter implements the Simultaneous Truth And Performance Level Estimation algorithm for generating ground truth volumes from a set of binary expert segmentations. The STAPLE algorithm treats segmentation as a pixelwise classification, which leads to an averaging scheme that accounts for systematic biases in the behavior of experts in order to generate a fuzzy ground truth volume and simultaneous accuracy assessment of each expert. The ground truth volumes produced by this filter are floating point volumes of values between zero and one that indicate the probability of each pixel being in the object targeted by the segmentation.

Example Workflows

STAPLE and voting workflow

Inputs

Masks

At least two binary masks of the same size.

Type: Image4DBool, Required, Multiple (Minimum = 2)

Outputs

Probability

An image with the same spatial properties as the input mask, with values between zero and one that indicate the probability of each pixel is a part of the object targeted by the segmentation.

Type: Image4DFloat

Fraction

A Data Table that summarizes the Sensitivity and Specificity of each mask.

Type: DataCollection

Settings

Confidence Weight Number

The Confidence Weight parameter is a modifier for the prior probability that any pixel would be classified as inside the target object. This implementation of the STAPLE algorithm automatically calculates prior positive classification probability as the average fraction of the image volume filled by the target object in each input segmentation. The Confidence Weight parameter allows for scaling the of this default prior probability: if \(g_t\) is the prior probability that a pixel would be classified inside the target object, then \(g_t\) is set to \(g_t \times \textrm{ConfidenceWeight}\) before iterating on the solution. In general ConfidenceWeight should be left to the default of 1.0.

Maximum Iterations Integer

Set the maximum number of iterations. The STAPLE algorithm is an iterative E-M algorithm and will converge on a solution after some number of iterations that cannot be known a priori. If the maximum number of iterations is reached, the algorithm will stop iterating regardless of whether or not it has converged. This implementation of the STAPLE algorithm will find the solution to within seven digits of precision unless it is stopped early.