petebankhead

/**
 * Script to import binary masks & create annotations, adding them to the current object hierarchy.
 *
 * It is assumed that each mask is stored in a PNG file in a project subdirectory called 'masks'.
 * Each file name should be of the form:
 *   [Short original image name]_[Classification name]_([downsample],[x],[y],[width],[height])-mask.png
 *
 * Note: It's assumed that the classification is a simple name without underscores, i.e. not a 'derived' classification
 * (so 'Tumor' is ok, but 'Tumor: Positive' is not)
 *

petebankhead

/**
 * Script to export pixels & annotations for whole slide images.
 *
 * The image can optionally be tiled during export, so that even large images can be exported at high resolution.
 * (Note: In this case 'tiled' means as separate, non-overlapping images... not a single, tiled pyramidal image.)
 *
 * The downsample value and coordinates are encoded in each image file name.
 *
 * The annotations are exported as 8-bit labelled images.
 * These labels depend upon annotation classifications; a text file giving the key is written for reference.

petebankhead

/**
 * Script to export pixels & annotations for TMA images.
 *
 * The downsample value and coordinates are encoded in each image file name.
 *
 * The annotations are exported as 8-bit labelled images.
 * These labels depend upon annotation classifications; a text file giving the key is written for reference.
 *
 * The labelled image can also optionally use indexed colors to depict the colors of the
 * original classifications within QuPath for easier visualization & comparison.

petebankhead

/**
 * Count the annotations for each classification, for all images in a project.
 *
 * This works by looping through all the images in a project, and checking for the existence of a data file.
 *
 * If a data file is found, read the hierarchy (no need to open the whole image), and print the number of objects,
 * the total number of annotations & the number of annotations split by classification.
 *
 * @author Pete Bankhead
 */

petebankhead

/**
 * Update paths within a QuPath project to handle images that have been moved.
 *
 * This works by first finding image paths that don't point to any existing files,
 * and then prompting the user to select a base directory below which the script
 * will search for image files with the same names.
 *
 * The process is a bit cumbersome, partly because there is no easy way to set
 * the path for an existing ProjectImageEntry.
 *

petebankhead

/**
 * Create a QuPath classifier by scripting, rather than the 'standard' way with annotations.
 *
 * This selects training regions according to a specified criterion based on staining,
 * and then creates a classifier that uses other features.
 *
 * The main aim is to show the general idea of creating a classifier by scripting.
 *
 * @author Pete Bankhead
 */

petebankhead

/**
 * Export ROIs made in QuPath as .zip files that can be imported into ImageJ.
 *
 * This makes several assumptions:
 *  - the rois apply to the whole image, without offsets or downsampling
 *  - only the outer ROI for cells is export (rather than the outer ROI + nucleus)
 *  - the image is 2D (i.e. it doesn't attempt to set z-slice properties)
 *
 * The ROIs will be put into a 'rois' subdirectory of the QuPath project directory.
 *

petebankhead

/**
 * Try to extract the label from an image and show this with enhanced contrast using ImageJ as the viewer.
 *
 * This is mostly intended for .czi files, where currently the label seems to be 16-bit
 * and displays as entirely black in QuPath.
 *
 * It assumes that the label exists as an 'associated image' within the server.
 * 
 * This has been tested with QuPath v0.2 - it may not work with other versions.
 *

petebankhead

/**
 * Replace (selected) annotations with ROIs containing holes with filled-in versions.
 * 
 * @author Pete Bankhead
 */

import qupath.lib.objects.PathAnnotationObject
import qupath.lib.roi.AreaROI
import qupath.lib.roi.PathROIToolsAwt
import qupath.lib.scripting.QPEx

petebankhead

/**
 * Proof-of-concept script showing one whole slide image as an overlay on top
 * of another within QuPath.
 *
 * Note that this script simply overlays the *same* image that is currently open;
 * therefore it may not be immediately obvious that anything has happened.
 *
 * Uncomment the line
 *   g2d.translate(1000, 1000)
 * if you want to convince yourself that something *has* actually happened,