Figure 1: Microscopy provides imagery to the algorithm that then delineates the cellular structures, making the segmentation clearer.

Figure 1: Microscopy provides imagery to the algorithm that then delineates the cellular structures, making the segmentation clearer.

The Kreshuk group develops machine-learning-based methods and tools for automatic segmentation, classification and analysis of biological images.

Previous and current research

Machine learning is advancing the state of the art in image analysis more rapidly than ever before: for many problems in natural image analysis, automated methods are now approaching parity with humans. One of the major advantages of learning-based approaches is their general applicability: tailoring to a particular problem is performed by providing suitable training data, while the core of the algorithm remains unchanged. To bring these methods to members of the life science community without computer vision expertise, we have developed a toolkit for interactive learning and segmentation (ilastik).

While the algorithms in ilastik generalise to provide user-friendly solutions to a wide array of image analysis problems, the most challenging bioimage datasets require a tailored approach. Our group is particularly interested in solving challenging segmentation problems for light or electron microscopy (LM or EM), in 3D and at large scale. Most recently, we have developed methods and tools to segment all cells and nuclei in a juvenile worm of the species Platynereis dumerilii (EM, Vergara et al., bioRxiv 2020), as well as in various plant organs and tissues (LM, Wolny, Cerrone et al., eLife 2020).

Future projects and goals

All machine learning algorithms require user guidance at the training stage, but deep learning – the driver of the current computer vision revolution – is even more annotation hungry. This problem is especially acute in biological imaging, where annotation of ground-truth data cannot easily be outsourced to non-experts, and changes in experimental conditions can require retraining. Besides the annotation burden, the training process itself depends upon non-trivial expertise in the choice and tuning of hyperparameters. Our group is currently working on methods and training strategies that would reduce the requirements on the amount of training data, which we hope to incorporate into ilastik. We are also interested in creative combinations of deep learning and microscopy (Wagner, Beuttenmuelluer et al., bioRxiv 2020) and learning-based analysis of morphology.