segmetrics.detection

class segmetrics.detection.FalseMerge(aggregation: Literal['sum', 'mean', 'geometric-mean', 'object-mean'] = 'mean')

Bases: Measure

Counts falsely merged objects.

References:

• L. Coelho, A. Shariff, and R. Murphy, “Nuclear segmentation in microscope cell images: A hand-segmented dataset and comparison of algorithms,” in Proc. Int. Symp. Biomed. Imag., 2009, pp. 518–521.

compute(actual: None) → List[float]

Computes the values of the performance measure (or an intermediate representation thereof) for the given segmentation results based on the previously set expected result.

Intermediate representations are useful, for example, if the measure must take multiple images of a dataset into account and cannot be computed by a mean value across those images. If an intermediate representation is returned, the final performance values can be obtained by feeding the list of intermediate representations obtained for all images into the postprocess() method.

Parameters:

actual – An image containing uniquely labeled object masks corresponding to the segmentation results.

Returns:

A list of float values representing the performance measure or an intermediate representation thereof (arbitrary data type).

default_name() → str

Returns the default name of this measure.

class segmetrics.detection.FalseNegative(**kwargs)

Bases: Measure

Counts missing objects.

References:

• L. Coelho, A. Shariff, and R. Murphy, “Nuclear segmentation in microscope cell images: A hand-segmented dataset and comparison of algorithms,” in Proc. Int. Symp. Biomed. Imag., 2009, pp. 518–521.

compute(actual: None) → List[float]

Computes the values of the performance measure (or an intermediate representation thereof) for the given segmentation results based on the previously set expected result.

Intermediate representations are useful, for example, if the measure must take multiple images of a dataset into account and cannot be computed by a mean value across those images. If an intermediate representation is returned, the final performance values can be obtained by feeding the list of intermediate representations obtained for all images into the postprocess() method.

Parameters:

actual – An image containing uniquely labeled object masks corresponding to the segmentation results.

Returns:

A list of float values representing the performance measure or an intermediate representation thereof (arbitrary data type).

default_name() → str

Returns the default name of this measure.

class segmetrics.detection.FalsePositive(**kwargs)

Bases: Measure

Counts spurious objects.

References:

• L. Coelho, A. Shariff, and R. Murphy, “Nuclear segmentation in microscope cell images: A hand-segmented dataset and comparison of algorithms,” in Proc. Int. Symp. Biomed. Imag., 2009, pp. 518–521.

compute(actual: None) → List[float]

Computes the values of the performance measure (or an intermediate representation thereof) for the given segmentation results based on the previously set expected result.

Intermediate representations are useful, for example, if the measure must take multiple images of a dataset into account and cannot be computed by a mean value across those images. If an intermediate representation is returned, the final performance values can be obtained by feeding the list of intermediate representations obtained for all images into the postprocess() method.

Parameters:

actual – An image containing uniquely labeled object masks corresponding to the segmentation results.

Returns:

A list of float values representing the performance measure or an intermediate representation thereof (arbitrary data type).

default_name() → str

Returns the default name of this measure.

class segmetrics.detection.FalseSplit(aggregation: Literal['sum', 'mean', 'geometric-mean', 'object-mean'] = 'mean')

Bases: Measure

Counts falsely split objects.

References:

• L. Coelho, A. Shariff, and R. Murphy, “Nuclear segmentation in microscope cell images: A hand-segmented dataset and comparison of algorithms,” in Proc. Int. Symp. Biomed. Imag., 2009, pp. 518–521.

compute(actual: None) → List[float]

Computes the values of the performance measure (or an intermediate representation thereof) for the given segmentation results based on the previously set expected result.

Intermediate representations are useful, for example, if the measure must take multiple images of a dataset into account and cannot be computed by a mean value across those images. If an intermediate representation is returned, the final performance values can be obtained by feeding the list of intermediate representations obtained for all images into the postprocess() method.

Parameters:

actual – An image containing uniquely labeled object masks corresponding to the segmentation results.

Returns:

A list of float values representing the performance measure or an intermediate representation thereof (arbitrary data type).

default_name() → str

Returns the default name of this measure.