DIKU Bits: Automatic analysis of microscope images

On 7 June the Image Analysis, Computational Modelling, and Geometry Section at Department of Computer Science, University of Copenhagen, will give a DIKU Bits lecture.

Speaker

Jon Sporring, Professor in the Image Analysis, Computational Modelling, and Geometry Section

Title

Automatic analysis of microscope images

Abstract

Analysis of the shapes and structures in biological material needs computer scientists to turn pictures into knowledge: I will show examples of research we have been doing over the last 10 years together with biologists and statisticians on developing new methods for exploring images at the nanoscale (1e-9 meter) and how we are linking what we find to the well-being of humans and other animals. During my talk, I will discuss techniques for aligning stacks of 2-dimensional images into a 3-dimensional block of data, how we use deep learning to segment images, and how we statistics to characterize shapes and their relations to answer questions such as: Can we see the changes in a brain due to stress?

Bio

Which courses do you teach?

Programmering og probemløsning (BSc datalogi, BSc Machine learning og datavidenskab, BSc Datalogi og Økonomi)

Signal and Image processing (MSc Programme in Computer Science, MSc Programme in Physics)

Biological Imaging (MSc biological area)

Big Data in Biotechnology (MSc Programme in Biotechnology, MSc Programme in Biotechnology with a minor subject, MSc Programme in Environmental Science)

Which technology/research/projects/startup are you excited to see the evolution of?

Microscope imaging, MAXIV (https://www.maxiv.lu.se/), Europeans Spallation Source (https://europeanspallationsource.se)

What is your favorite sketch from the DIKUrevy? I like the old sketch, where Knud Henriksen obscured the cos^2(x)+sin^(x)=1 equation