Introduction to image analysis with ilastik

This event is part of a series of four workshops, made possible thanks to support from the Crick and University Partnership Networking Fund. Each workshop is delivered as a mix of lectures and hands-on practical exercises and focuses on a different open-source software tool. 

The four sessions are intended to be independent of one another; it is not expected that a single attendee will participate in all four, unless they wish to do so.

The dates and topics of the workshops are:

• 31 July 2026 – Introduction to image analysis with FIJI
• 12 October 2026 – Introduction to image analysis with QuPath
• 10 February 2027 – Introduction to image analysis using Python and Jupyter notebooks
• 19 March 2027 – Introduction to image analysis with ilastik

Some guidance on which applications are most suited for each software tool is provided below:

• FIJI is the most commonly used image analysis software in scientific research. It is easy to use, and its capabilities are enhanced by additional plugins developed by the community for specific tasks. It tends to perform well for traditional image analysis workflows (segmentation, morphological analysis, signal quantification and tracking) on light microscopy data.
   
• QuPath was developed for digital pathology images and is best suited for large fields of view for various modalities (eg hematoxylin, eosin and multiplex immunofluorescence). Segmentation, classification and colocalisation analyses are common tasks that QuPath performs well, both with traditional and machine-learning approaches.
   
• ilastik is a user-friendly image analysis tool that can help leverage machine learning algorithms to easily segment, classify, track, and count cells or other experimental data. It works well with light and electron microscopy data and other acquisition modalities where traditional algorithms perform poorly.
   
• Python is an open-source programming language used in many different applications beyond science. It provides some dedicated libraries for image analysis and allows for easy integration with other workflows due to its wide application base. Jupyter notebooks provide an accessible distribution that makes it straightforward to interact with and share code. Most types of image data can be analysed with custom-made Python pipelines.