This project aims to analyse imaging flow cytometry data with advanced computational techniques. Imaging flow cytometry is a novel technology which allows making photographs of millions of individual cells in a high-throughput fashion, capturing their size and shape as well as information about protein expression. These measurements can be used to study and understand complex biological systems, such as the immune system, made up of dozens of cell types, each with particular functions. However, extracting relevant insights from this large amount of measurements is not trivial. We will develop "machine learning" algorithms, which will learn from the patterns in the data itself rather than using previously defined rules. We will explore two approaches: first, we will use algorithms which take derived properties of the cells into account (e.g. the cell area or the maximal cross-section length). Additionally, we will also explore "deep learning" approaches, which take the original images as input. We will apply these techniques both to predict the cell type, given a set of example images for different possible cell types, as a more unbiased approach, where we will let the algorithms look for patterns. In the end, this will lead to detailed descriptions of the cells that can be used to describe the cells from patient samples (e.g. from a blood draw) and could provide detailed insights in the patient's immune state. This will be very helpful for clinical diagnosis and prognosis.