News |  Sitemap |  Contact
PDF Export  | 

Integrating ImageJ into KNIME for High-throughput Image Analysis


The balooning use of high-throughput microscopy in recent years has resulted in much richer data being available for image analysis. This calls for software solutions that are able to handle the huge amounts of image data produced in a high-throughput environment. Such a software must provide access to a wide range of functionality (e.g. image analysis, machine learning, statistics and visualisation), and yet still be easy to use by non-experts.

KNIME is a user-friendly and comprehensive open-source data integration, processing, analysis, and exploration platform designed to handle large amounts of heterogeneous data. It therefore satisfies the aforementioned requirements. As an integration platform, KNIME directly combines functionality from several different domains.

More recently the image processing extension of KNIME has been dramatically enhanced. It is designed to extend KNIME by providing algorithms and data structures that can easily process and analyse images and videos on a large scale. The addition of image processing capabilites to KNIME means that complex domain comprehensive workflows can be designed without difficulty, enabling for instance the analysis of images with machine learning algorithms or the integration of image data with chemical information. Further advantages directly inherited from KNIME, amongst many others, are the handling of large amounts of data and fast prototyping of understandable workflows.

Avoiding redundant and benefitting from ongoing, high quality development, the KNIME image processing extension in turn uses and integrates state-of-the-art libraries like Bioformats, OMERO, and ImgLib2. A key element is an additional extension which allows to execute suitable ImageJ1 macros and tightly integrates with ImageJ2 as well. Headless executable ImageJ2 modules are automatically recovered and can therefore be provided as KNIME nodes (the functional entities of a KNIME workflow). Hence, it is easy to compose complex image processing and analysis workflows.

As a consequence the functionality of KNIME is made available for ImageJ users (e.g. the visual composition of workflows, storage and exchange of workflows, easy connection to other application domains, …). With the marriage of these two powerful tools, new possibilities to process and analyse image data arise.

Currently the KNIME image processing extension is used to solve several segmentation, classification and tracking problems in different areas of science, such as biology, chemistry and physics.


High-throughput analysis, image processing, image analysis, screening, imagej, imagej2, KNIME

Short CV

Christian Dietz

with the Nycomed Chair for Bioinformatics and Information Mining, University of Konstanz

since 2011:
Research assistant at the University of Konstanz, Department of Computer and Information Science

2008 - 2011:
Study of Computer Science, University of Konstanz

2005 - 2008:
Study of Business Informatics, Verwaltungs- und Wirtschaftsakademie Stuttgart

Research interests and work domain:
Biomedical image processing and analysis with the focus on active classification and tracking.

Martin Horn

with the Nycomed Chair for Bioinformatics and Information Mining, University of Konstanz

since 2010:
Member of the Graduate School Chemical Biology at the University of Konstanz.

2003 - 2009:
Study of Bioinformatics at the University of Leipzig.

Research interests and work domain:
Biomedical image processing and analysis with the focus on supervised (active) image segmentation.

Administrative data

Presenting author: Martin Horn
Organisation: University of Konstanz

co-authors: Christian Dietz, Michael Zinsmaier, Michael R. Berthold

Type: Workshop

Workshop Materials

© Luxembourg Institute of Science and Technology | Legal Notice