Abstract
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.
Highlights
The use of digital pathology (DP) as a companion diagnostic is growing rapidly, with several reports of pathology departments transitioning towards signing out cases using either partial or completely digital workflows [1,2,3,4]
A more holistic approach is required that combines intensity and colour recognition with more sophisticated features that can quantify the context of any object, and include this context in the classification in order to successfully analyse samples of lung fibrosis or other challenging tissues
We describe the development of the Orbit Image Analysis tool and its application in three realworld scenarios
Summary
The use of digital pathology (DP) as a companion diagnostic is growing rapidly, with several reports of pathology departments transitioning towards signing out cases using either partial or (in some cases) completely digital workflows [1,2,3,4]. The purpose of acquiring WSI digital data is not just to have a digital, computer-aided display of pathology specimens, but to make it possible to apply advanced computer vision and machine learning tools This will accelerate the processing of slides and cases in research, drug development, clinical trials and patient diagnosis—across all the domains where pathology makes a critical contribution to our understanding of the effects of experimental perturbation or disease. For example, normal structural collagen has the same staining colour as newly-deposited fibrotic collagen These earlier algorithms were not able to detect such differences, whereas for pathologists these tasks were relatively straightforward. The emergence of deep learning methods has facilitated the quantification of even more complex scenarios [10,11,12,13,14]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
