petebankhead

/**
 * Script to convert all polyline annotations to polygons in QuPath.
 * Written for QuPath v0.5 (may work in other versions).
 */

def lineObjects = getAnnotationObjects().findAll {it.getROI().isLine()}
def polygonObjects = []
def selectedObjects = getSelectedObjects() as List
for (lineObject in lineObjects) {
    def line = lineObject.getROI()

petebankhead

/**
 * QuPath script to calculate areas (e.g. of tumor) based upon classified cells only.
 *
 * It works by using a distance transform applied to binary images generated from the
 * objects of each class, and then assigns each pixel to the closest object.
 *
 * Having done this, new annotations are generated for these regions.
 *
 * WARNINGS!
 * - This will remove *all* previous annotations & replace them with new annotations

petebankhead

/**
 * Convert TIFF fields of view to a pyramidal OME-TIFF.
 *
 * Locations are parsed from the baseline TIFF tags, therefore these need to be set.
 *
 * One application of this script is to combine spectrally-unmixed images.
 * Be sure to read the script and see where default settings could be changed, e.g.
 *   - Prompting the user to select files (or using the one currently open the viewer)
 *   - Using lossy or lossless compression
 *

petebankhead

/**
 * Demonstration of how to use ImageJ + QuPath to detect stained regions in
 * a brightfield image.
 *
 * @author Pete Bankhead
 */


import ij.CompositeImage
import ij.IJ

petebankhead

/**
 * Add pixel classifier measurements to all cells in an image.
 * 
 * This is intended to overcome the fact that measurements can be quite slow because they aren't parallelized.
 * 
 * Written for QuPath v0.3.2.
 * See https://forum.image.sc/t/qupath-measure-pixel-classifier-area-per-cell-detection-for-wsis/72701
 * 
 * Warning! This hasn't been extensively tested - please report any problems on the forum.
 *

petebankhead

/**
 * Add a 'small' image overlay to the image currently open in the QuPath viewer.
 * Here, 'small' indicates something that ImageIO can handle, and which isn't pyramidal.
 *
 * @author Pete Bankhead
 * 
 * Updated 1/2023 to be compatible with QuPath v0.4.x
 */

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

/**
 * Create fixed-sized square annotations around the points of a selected 
 * point annotation.
 * 
 * Written for QuPath v0.4 and v0.5.
 * See https://forum.image.sc/t/is-it-possible-to-create-annotations-on-click/79270
 * 
 * Edited 12/2023 to support multiple selected point annotations (not just one).
 *
 * @author Pete Bankhead

petebankhead

/**
 * Groovy script to generate a batch script to launch QuPath while setting the PATH 
 * from a conda environment.
 * 
 * This is useful to add GPU support with Deep Java Library (DJL) without needing to install 
 * CUDA system-wide.
 * 
 * This script was written for QuPath v0.5.
 * You should read the top part and change the variables to match what you need.
 */

petebankhead

/**
 * QuPath v0.4.3 script to threshold probability outputs from a pixel classifier.
 *
 * By default, converting the pixel classifier output to probabilities will always
 * apply a softmax operation and take the class with the highest probability.
 *
 * This script provides an alternative, whereby you can specify a probability threshold
 * for one or more channels, and threshold to create objects from that.
 * Using a higher threshold can then restrict the object creation of more confident predictions.
 *