We describe Orbit Image Analysis, an open-source whole slide image analysis tool. The tool consists of a generic tile-processing engine which allows the execution of various image analysis algorithms provided by either Orbit itself or from other open-source platforms using a tile-based map-reduce execution framework. Orbit Image Analysis is capable of sophisticated whole slide imaging analyses due to several key features. First, Orbit has machine-learning capabilities. This deep learning segmentation can be integrated with complex object detection for analysis of intricate tissues. In addition, Orbit can run locally as standalone or connect to the open-source image server OMERO. Another important characteristic is its scale-out functionality, using the Apache Spark framework for distributed computing. In this paper, we describe the use of Orbit in three different real-world applications: quantification of idiopathic lung fibrosis, nerve fibre density quantification, and glomeruli detection in the kidney.

This is a whole slide image (WSI) dataset for glomeruli segmentation on kidney tissue, in total 88 images.
The train-set (58 images) and test-set (32 images) has been used in the Orbit publication (1) to train and test the
glomeruli segmentation model (2).

The images are pyramidal tiff images (tiled, jpeg-compression) and can be displayed with Orbit Image Analysis (3).

The file orbit.db is a sqllite database which contains the manual drawn glomeruli annotations for all images, in total 21037 annotations.
It can be placed in the user-home folder, then Orbit Image Analysis (3) will detect the database and show the glomeruli annotations in the annotation tab when opening an image.
(Orbit will use the md5 hashes of the images for identification.)

For more information on how to train a CNN model or to use the existing model (2) please visit the Orbit deep learning page (4).

(1) Manuel Stritt, Anna K. Stalder, Enrico Vezzali; Orbit Image Analysis: An open-source whole slide image analysis tool; Plos Computational Biology
(2) http://www.orbit.bio/deep-learning-models/
(3) http://www.orbit.bio
(4) http://www.orbit.bio/deep-learning-object-segmentation/
(5) https://creativecommons.org/share-your-work/public-domain/cc0

Groups:
H&DAB Rat G1: 5483162,5482449,5483170,5482455,5483190,5482452,5482458,5483139,5483117,5482411,5483132           
H&DAB Rat G2: 4737452,4737489,4737509,4737522,4730025,4730043,4730080,4758050,4758056,4758065,4758073           
H&DAB Rat G3: 6139966,6139967,6139977,6139983,6140227,6140234,6140254,6140232,6140251,6140179,6140168,6140176   
FastRed Mouse: 6533664,6533666,6533668,6533679,6533672,6533678,6533683,6533680,6533682,6533691,6533687,6533688  
PAS Rat: 6609616,6609615,6609629,6609617,6609626,6609628,6625497,6625501,6625506,6625505,6609613,6609634,6609605
H&E Mouse G1: 6654562,6654559,6654566,6654568,6654582,6654586,6654587,6654588,6654517                           
H&E Mouse G2: 6479221,6479222,6479223,6479224,6479183,6479186,6479191,6479195,6479196,6479203                   
H&E Mouse G3: 6666707,6666708,6666709,6666710,6666711,6666712,6666713,6666714,6666717,6666718