Ilastik_organoid_segmentation

<p>This repository holds two Ilastik projects and respective training data used for the organoid segmentation of the initial organoid screen in the publication &quot;A semi-automated intestinal organoid screening method demonstrates epigenetic control of epithelial differentiation&quot; (<a href="https://doi.org/10.3389/fcell.2020.618552">Ostrop et al. 2020</a>).</p> <p>The image pre-processing was carried out with the ImageJ script available on GitHub: <a href="https://github.com/jennyostrop/Fiji_organoid_brightfield_processing">https://github.com/jennyostrop/Fiji_organoid_brightfield_processing</a>, archived on Zenodo as <a href="https://doi.org/10.5281/zenodo.3951125">https://doi.org/10.5281/zenodo.3951125</a></p> <p>For training, 1 well treated with DMSO vehicle control of 4 biological replicates and 5 timepoints were used (total 20 images). Training data was excluded from further analysis.</p> <p>The raw images were deposited to the Image Data Resource (<a href="https://idr.openmicroscopy.org">https://idr.openmicroscopy.org</a>) under accession number idr0092.<br> Training data corresponds to Well A01 in plate 1-plate 4.</p> <p>&nbsp;</p> <p><strong>Project 1: Ilastik1_PixelClass_Edges</strong></p> <p>Pixel classification, created with Ilastik 1.3.2</p> <p>Input Raw Data: Summary projection of Sobel edge detection for each z-layer (Output 2d from ImageJ script)</p> <p>Training classes:<br> Background: lines over background and debris (size 7) and inside of organoids (size 3)<br> Object: exact lines following the outer border of organoids (size 1)</p> <p>&nbsp;</p> <p><strong>Project 2: Ilastik2_ObjectClass_Projection</strong></p> <p>Object classification [Inputs: Raw Data, Pixel Prediction Map], created with Ilastik 1.3.2</p> <p>Input Raw Data: Minimum intensity projections of each Zstack (Output 1b from ImageJ script)<br> Input Prediction Maps: Pixel Prediction Maps generated in project Ilastik1_PixelClass_Edges</p> <p>Threshold and Size Filter: Method - Simple, Input - 0 (Background), Smooth &ndash; 1.0, 1.0, Threshold&nbsp; - 0.55, Size Filter &ndash; Min 10, Max 1000000<br> <br> Object classes:<br> Mislabelled: Patch of background enclosed by objects, light<br> Organoid: Typical organoid, medium dark<br> Sphere_big: Sphere, almost round, light, size of organoids or bigger<br> Sphere_small: Sphere, almost round, light to medium dark, small<br> Cluster: Cluster of several organoids/spheres and organoids segmented as single object<br> Debris: Debris in Matrigel, irregular borders and structure, mostly small, medium dark<br> AirBubble: Air bubbles in Matrigel at early timepoints, round, dark with light centre<br> Edges: Edges of well plate (empty class, included for consistency)</p>