On Tuesday September 27^th, 2022, Dr. Florian Jug (Head of the Image Analysis Facility, Human Technopole) will visit Politecnico for the first event of the "HT days" series.

Dr. Jug will give a seminar entitled "Microscopy Image Restoration and Downstream Analysis - recent improvements and hopes for the future" at 10 am in the Schiavoni Seminar Room (Building 20), then would be glad to meet collegues and (MD/PhD) students who are willing to talk for possibly establishing scientific collaborations in dedicated meetings from 11.30 to 12.30 or from 13.45 to 15. People interested in attending these meetings may write to Prof. Francesca Ieva (francesca.ieva@polimi.it) by September 23^th.

Abstract

The necessity to analyze scientific images is as old as the ability to acquire such data. While this analysis did initially happen by observation only, modern microscopy techniques now enable us to image at unprecedented spatial and temporal resolutions, through the 'eyes' of many and very diverse imaging modalities.

The unfathomable amounts of data acquired in the context of biomedical research cannot any longer be analyzed by manual observation alone. Instead, algorithmic solutions are helping researchers to study and quantify large image data.

In the past years, our abilities to use artificial neural networks (ANNs) for the automated analysis of scientific image data gained significant traction, and many important analysis problems have now much improved solutions based on ANNs. At the same time, we start being aware of limitations that come with this new set of machine learning approaches.

In his talk, Dr. Jug will give a few updates on some of the latest algorithmic developments from his and other labs. More specifically, he will talk about improved but easy to use image restoration and segmentation methods and the efforts of his community to store, share, and run ANN based methods via the BioImage Model Zoo - a Horizon Europe funded infrastructure he and his team are currently establishing. Finally, he will carefully attempt to look into the future and share his predictions about how artificial intelligence will help us make valuable scientific discoveries at elevated pace.

Short Bio

Dr. Florian Jug holds a PhD in Computational Neuroscience from the Institute of Theoretical Computer Science at ETH Zurich, but later moved into image and data analysis at the Max-Planck Institute CBG in Dresden. He has recently moved to the Fondazione Human Technopole, where his team is pushing the boundary of what AI and machine learning can do to better analyze and quantify biological data. Dr. Jug’s team covers the full breadth of bio-image computing, from research on novel methods in computer vision and machine learning, all the way to offering bio-image analysis as a service.

Florian Jug is a strong proponent of open access science, open AI and ML methods, and open source software. His team is a core contributor to Fiji (~100,000 active users) and collaboratively develops open methods such as CARE, Noise2Void, PN2V, DivNoising, etc. He organizes scientific conferences (e.g the I2K conference), workshops (e.g. the BIC workshops at top-tier computer vision conferences) and various practical courses on machine learning for bio-image analysis (e.g. DL@MBL in Woods Hole) or microscopy (e.g. Quantitative Imaging at Cold Spring Harbor).