Get dict of slide idx, indexed by name.

Perform stain unmixing using the method of choice (wrapper). Parameters ---------- im_rgb : array_like An RGB image (m x n x 3) t

Threshold a multi-channel image (eg. HSI image) to get tissue. The relies on the fact that oftentimes some slide elements (eg blood or whites

Placeholder.

Calculated FSDs from boundary points X,Y. Boundaries are resampled to have K equally spaced points (arclength) around the shape. The curvatur

Returns bounds of object in global label image. Parameters ---------- bbox : tuple Bounding box (min_row, min_col, max_row,

Resamples boundary points [X, Y] at L total equal arc-length locations. Parameters ---------- X : array_like x points of bou

Detect whitespace, saliency, etc in one tissue piece (Internal). Arguments: --------- cdt : object Cellularity_de

Detect cellularity in one tissue piece (Internal). Arguments: --------- cd : object Cellularity_detector_superpix

Add single contour to dataframe (Internal).

Add a single element to the final dataframe. Note that we wrap this into a method so that when (if) we split an annotation element into multi

Add merged polygons to self.merged_contours df (Internal).

Add merged polygons to self.new_contours df (Internal).

Add roi offset to coordinates of polygons (Internal).

Add single contour to self.new_contours (Internal).

Placeholder.

Internal support for compute_global_cell_graph_features that returns its result in a nested nametuple structure instead of a pandas DataFrame.

Create a local dsa docker and connect to it

Wrap around color_deconvolution_routine (compatibility).

Drop edge contours that have already been merged (Internal).

Flatten the result of _compute_global_cell_graph_features to the DataFrame returned by compute_global_cell_graph_features.

Calculate the fractal dimension of an object (boundary complexity). Source: https://gist.github.com/rougier/e5eafc276a4e54f516ed5559df4242c0

Merge polygons using shapely (Internal). Given a a list of clusters from _get_merge_clusters_from_df(). Creates and merges polygons i

Get element coords and mask and add to ROI (Internal).

Take a 2xN matrix of vectors and return a length-N array of an. ... angle-like quantity. Since this is an internal function, we assume that t

Parse shapely polygon coordinates into string form (Internal).

Parse shapely polygon coordinates into string form (Internal).

Get dictionary of mask offsets (top and left) (Internal). The pattern _left-123_ and _top-123_ is assumed to encode the x and y offse

Assign each nest to one cluster (Internal). That is, such that all nests that are connected to each other are in the same cluster. Us

Get merge dataframe (pairs along shared edges) (Internal).

Get nest dfs and indices of which ones to merge (Internal).

Merge polygons using shapely (Internal). Given a single cluster from _get_merge_clusters_from_df(), This creates and merges polygons

Get a visualization of rgb and annotations for rapid review. Parameters ---------- rgb : np.array mxnx3 rgb image vis : np.ar

Get unique roi pairs (Internal).

Get a zoomed out visualization of ROI RGB and annotation overlay. Parameters ---------- gc : girder_client.Girder_Client authenti

Placeholder.

Crop bounds to desired area using shapely polygons.

Download special ROI regions as-is, even if they are very large.

Download special ROI regions in a tiled fashion.

Scores the angles produced by cutting line (cx1, cy1)->(cx2, cy2) given the convex hull segments (ax1, ay1)->(bx1, by1) and (ax2, ay2)->(bx2, by2)

Calculate index in arr of element nearest the pth percentile.

Assign cellularity scores to spixel clusters.

Assign RGB color string to cellularity clusters.

Get components by thresholding in HSI and LAB spaces.

Sample the background of the slide identified by slide_path to compute the background intensities in the RGB channels. Arguments are as in hi

SCale-adaptive Multiscale Difference-of-Gaussian (DoG) filter for nuclei/blob detection. Computes the maximal DoG response over a series of s

Constrained Laplacian of Gaussian filter. Takes as input a grayscale nuclear image and binary mask of cell nuclei, and uses the distance tran

Perform Color Convolution. Reconstructs a color image from the stain matrix `w` and the individual images stored as channels in `im_stains` a

Perform color deconvolution. The given RGB Image `I` is first first transformed into optical density space, and then projected onto the stain

Color normalize "true" tissue components.

r""" Calculates 26 Haralick texture features for each object in the given label mask. These features are derived from gray-level co-occur

Process contours to get and object segmentation labeled mask. Parameters ---------- contours : DataFrame contours corresponding t

Convert a column matrix of pixels to a 3D image given by shape. The number of channels is taken from m, not shape. If shape has length 2, the

Convert nuclei segmentation data from polygon format to bounding box format. Parameters ---------- nuclei_list (list): A list of dic

Count positive pixels, computing a label mask and summary statistics. Parameters ---------- image : array-like NxMx3 array of

Besides the inputs described by the specification, this also can take opts.callback, which is a function that takes (step_name: str, step

Placeholder.

Create a shapely Polygon from a list of points. Args: ---- points (list): A list containing tuples representing the points of th

Create and or post review galleries for rapid review. Parameters ---------- tilepath_base : str directory where combined visualiz

Add contour bounding boxes to R-tree.

Placeholder.

Performs a cut across a binary mask, zeroing pixels that round to positions on the line (x1, y1)->(x2, y2). Returns ------- Cut : arr