Imaging ONEWORLD - 'DeepLearning in Microscopy' - Professor Udo Birk
19 July 2021
This week will feature Professor Udo Birk, University of Applied Sciences of the Grisons
Scientific Organisers: Stefanie Reichelt, Alex Sossick, Nick Barry, Alessandro Esposito and Kirti Prakash
The meeting will begin at 1pm BST.
As part of the 'Imaging ONEWORLD' series, the focus of these lectures is on microscopy and image analysis methods and how to apply these to your research. Almost all aspects of imaging such as sample preparation, labelling strategies, experimental workflows, ‘how-to’ image and analyse, as well as facilitating collaborations and inspiring new scientific ideas will be covered. Speakers will be available for questions and answers. The organisers, CRUK CI core facility staff, Gurdon Institute, MRC-LMB, MRC Cancer Unit and NPL will be able to continue the discussion and provide advice on your imaging projects.
Professor Udo Birk
Udo Birk is Head of Advanced Training Technics and Professor at the University of Applied Sciences of the Grisons in Chur, Switzerland. The focus of his work is on image processing and machine vision.
Before his current position, Udo Birk has also been deputy group leader of the super-resolution light microscopy lab with Prof. Christoph Cremer, a guest researcher at the University of Heidelberg, visiting research fellow at the Foundation of Research of Technology Hellas and also at the King’s College London. He has been a consultant for German small and medium-sized enterprises and research organizations participating in European research collaborations within the EUROSTARS funding programme.
His research is focused on the set-up, improvement and application of both machine vision and novel imaging techniques, and comprises hardware as well as software implementation. Current projects make use of advanced 3D image sensors. Other foci are teaching of Image Processing, Signal Processing, Deep Learning, and Microscopy. Example applications are:
- Use of Machine Vision for automation, e.g. in automated detection and analysis of fluorescent signals in biochemical assays, in human-machine interface devices, and lab automation.
- Nano-scale Imaging e.g., chromatin remodelling and the functional architecture of the cell nucleus, sub-cellular transport.
- Meso-scale imaging using 3D optical tomography and photoacoustics e.g., imaging of live model organisms (e.g. C. elegans, Parhyale hawaiensis), detection of blood vessels during laser surgery.
Recent advancements in microscopic image analysis have made use of the tremendous progress that artificial intelligence has seen in the evaluation of digital images. The application of deep learning techniques to microscopic image analysis ranges from image restoration and denoising to automated cellular and subcellular profiling to generation of augmented reconstructed image data, encompassing e.g. super-resolution images from single molecule localization microscopy data, virtual refocussing, content aware neuronal reconstructions and many more. However, deep learning methods are generally based on the availability of large amounts of reliable ground truth data. In the talk I will highlight some of the recent advances in deep learning applied to microscopic data with a focus on applications for super-resolution microscopy.