baby.tracker.core.MasterTracker

class baby.tracker.core.MasterTracker(ctrack_args=None, btrack_args=None, min_bud_tps=3, isbud_thresh=0.5, **kwargs)

Bases: FeatureCalculator

Coordinates the data transmission from CellTracker to BudTracker to reduce number of calls to regionprops function.

input :ctrack_args: dict with arguments to pass on to CellTracker constructor

if None it passes all the features to use

Btrack_args

dict with arguments to pass on to BudTracker constructor if None it passes all the features to use

**kwargskwargs

additional arguments passed to FeatureCalculator constructor

Attributes

a_ind

ma_ind

x_ind

y_ind

Methods

calc_feats_from_mask(masks[, feats2use, ...])	Calculate feature ndarray from ndarray of cell masks
calc_trapfeats(basefeats)	Calculate trap-based features using basic ones. :basefeats: (n basic outfeats) 1-D array with features outputed by skimage.measure.regionprops_table.
scale_feats(feats, pixel_size)	input
step_trackers(masks, p_budneck, p_bud[, ...])	Calculate features and track cells and budassignments

get_outfeats
load_model
set_named_ids

__init__(ctrack_args=None, btrack_args=None, min_bud_tps=3, isbud_thresh=0.5, **kwargs)

Methods

__init__([ctrack_args, btrack_args, ...])
calc_feats_from_mask(masks[, feats2use, ...])	Calculate feature ndarray from ndarray of cell masks
calc_trapfeats(basefeats)	Calculate trap-based features using basic ones. :basefeats: (n basic outfeats) 1-D array with features outputed by skimage.measure.regionprops_table.
get_outfeats([feats2use])
load_model(path, fname)
scale_feats(feats, pixel_size)	input
set_named_ids()
step_trackers(masks, p_budneck, p_bud[, ...])	Calculate features and track cells and budassignments

Attributes

a_ind
ma_ind
x_ind
y_ind

calc_feats_from_mask(masks: ndarray, feats2use: Optional[Tuple[str]] = None, trapfeats: Optional[Tuple[str]] = None, scale: Optional[bool] = True, pixel_size: Optional[float] = None)

Calculate feature ndarray from ndarray of cell masks — input

Masks

ndarray (ncells, x_size, y_size), typically dtype bool

Feats2use

list of strings with the feature properties to extract. If it is None it uses the ones set in self.feats2use.

Trapfeats

List of str with additional features to use calculated immediately after basic features.

Scale

bool, if True scales mask to a defined pixel_size.

Pixel_size

float, used to rescale the object features.

returns

(ncells, nfeats) ndarray of features for input masks

calc_trapfeats(basefeats)

Calculate trap-based features using basic ones. :basefeats: (n basic outfeats) 1-D array with features outputed by

skimage.measure.regionprops_table

requires

self.aind self.aweights self.xind self.yind self.trapfeats

returns (ntrapfeats) 1-D array with

scale_feats(feats: ndarray, pixel_size: float)

input

Feats

np.ndarray (ncells * nfeatures)

Pixel_size

float Value used to normalise the images.

returns Rescaled list of feature values

step_trackers(masks, p_budneck, p_bud, state=None, assign_mothers=False, return_baprobs=False, keep_full_state=False)

Calculate features and track cells and budassignments

input

Masks

3d ndarray (ncells, size_x, size_y) containing cell masks

P_budneck

2d ndarray (size_x, size_y) giving the probability that a pixel corresponds to a bud neck

P_bud

2d ndarray (size_x, size_y) giving the probability that a pixel corresponds to a bud

State

running state for the tracker, or None for initialisation

Assign_mothers

whether to include mother assignments in the returned returns

Return_baprobs

whether to include bud assignment probability matrix in the returned output

returns a dict consisting of

Cell_label

list of int, the tracked global ID for each cell mask

State

the updated state to be used in a subsequent step

Mother_assign

(optional) list of int, specifying the assigned mother for each cell

P_bud_assign

(optional) matrix (list of lists of floats), bud assignment probability matrix from predict_mother_bud