Orbit Image Analysis


Whole Slide Image Analysis

Sophisticated Image Analysis Algorithms

Orbit has many build-in image analysis algorithms. Tissue quantification using machine learning techniques, object / cell segmentation, and object classification are the basic ones. Region of interest (ROI) can be defined by manual annotations or via a trainable exclusion map. Everything can be combined.


All algorithms are build to work on really big images, up to gigapixel images, especially whole slide scans.
This is possible due to a tile-based processing pipeline and combination with the use of different resolutions of the image.

Connectivity: OMERO & Spark connectors

You can use your existing image server, e.g. it has been designed to work great with Omero.
Orbit can also run in stand-alone mode and open whole slide images like SVS, NDPI, SCN, ….

A Spark infrastructure can be used as scaleout infrastructure to distribute computation intensive tasks.

Scripting & Extentions & Connectors

Orbit provides a versatile API for developers to create scripts or extentions. For instance, you can easily iterate over all tiles within a defined ROI and apply any algorithm or ImageJ plugin. You write s.th. which works for small in-memory images, Orbit takes care that is works for really big images.

Individual image server and scaleout connectors can also be created by implementing clear interfaces.

New version 2.43 available!
CZI files with JPEG-XR compression support, multi image series (e.g. VSI files) support. Many speed optimizations!

What it is

A very versatile image analysis software
It's completely free, really!
And it will stay for free.
No demo, it's a full version.

Orbit Image Analysis is a free open source software with the focus to quantify big images like whole slide scans.

It can connect to image servers, e.g. Omero.
Analysis can be done on your local computer or via scaleout functionality in a distrubuted computing environment like a Spark cluster.

Sophisticated image analysis algorithms incl. tissue quantification using machine learning, object segmentation and classification are build in. In addition a versatile API allows you to enhance Orbit and to run your own scripts.

  • Sophisticated Algorithms
  • Connectivity
  • Scaleout
  • Programming API

Image Analysis

Sophisticated image analysis features
Uploaded image

Tissue Quantification

Compute the ratio of different tissue classes, e.g. percentage of collagen in a tissue.
Machine learning based tissue quantification allows the domain expert to train the system specific (e.g stained) tissue classes and to quantify it.
Uploaded image

Object segmentation

Segment objects like cells or nerves.
Object detection based on trainable foreground / background classes. Overlapping object, e.g. cell clusters can be devided afterwards. Features of objects (shape factors, area, intensities, …) can be computed and reported or used for object classification.
Uploaded image

Object Classification

Assign classes to objects based on their features.
Segmented objects can be classified based on their features like size, shape factors or intensities. For instance, it can be distinguished between stained and not stained cells or between round and edgy objects. This classification is based on machine learning; the user can specify classes by selecting examples.
Uploaded image

Annotations & ROI

Annotations and trainable exclusion maps for ROI definition.
The ROI (region of interest) can be defined by manuel annotations or a trainable exclusion map which defines “the good” area of your tissue. Both methods can be combined.

Latest news