Go to symposium website → www.slas.org/HighContentAnalysis
Back To Schedule
Monday, October 21 • 11:30am - 11:50pm
Enabling Technologies- Deep Learning Techniques for 3D Tissue and Organoid Manipulation and Segmentation

Sign up or log in to save this to your schedule, view media, leave feedback and see who's attending!

Deep Learning Techniques for 3D Tissue and Organoid Manipulation and Segmentation
In this talk I will give an overview of the techniques developed to convert our high content screening pipeline from 2D to organoids. First, I will present classical image processing algorithms and novel deep learning approaches for single cell-based analysis. I will discuss the challenges, opportunities and difficulties in converting these methods to 3 dimensions. A tool will be presented for annotating volumetric data to generate training image database. Our goal is to develop a deep learning architecture for 3D instance segmentation which will be used for processing image stacks of spheroids acquired on light sheet microscopy. Furthermore, I will present our 3D pipeline from spheroid generation to imaging. We are developing the Spheroid Picker robot that is capable of automatically selecting spheroids based on their morphological properties and transfer them from growing plates to high content plates. This low-cost device is a stereo microscope equipped with a pipette manipulator and a pressure controller system. The clearing method applied on the sample to allow high resolution deep imaging with light sheet fluorescence microscopy will be introduced. Finally, I will describe our label free automatic patch clamp system that performs electrophysiological measurements on living neurons in 3D brain tissue slices. The system is validated on hundreds of rodent and human cells.

avatar for Krisztián Koós

Krisztián Koós

Ph.D. Candidate, Biological Research Centre of the Hungarian Academy of Sciences
Krisztian Koos is currently a Ph.D. candidate in the laboratory of Peter Horvath, Biological Research Centre of the Hungarian Academy of Sciences. He graduated as a computer scientist at the University of Szeged where he worked on computer tomography algorithms. His research interests... Read More →

avatar for Hazel Screen, Ph.D., MRes, BEng

Hazel Screen, Ph.D., MRes, BEng

Professor of Biomedical Engineering, Queen Mary University of London
Hazel Screen is Professor of Biomedical Engineering and Chair of Bioengineering at Queen Mary University of London.Her research group focuses on multi-scale structure-function behaviour and mechanobiology in tissues. She has particular interest in in vitro models to explore health... Read More →

Monday October 21, 2019 11:30am - 11:50pm BST
Wellcome Auditorium