SCNAT and its network are committed to a sustainable science and society. They support policy-making, administration and business with expert knowledge and actively participate in public discourse. They strengthen the exchange across scientific disciplines and promote early career academics.

Image: Sebastian, stock.adobe.com

Symposium of the Microscopy Imaging Center if the University of Bern

Time

09:30 - 17:00

Venue

Schanzeneckstrasse 1, 3012 Bern

Meeting place

University of Bern, UniS, lecture hall A003, Schanzeneckstrasse 1, 3012 Bern

Machine learning in imaging

Teaser image MIC symposium 2019

PROGRAM

09:30 Welcome coffee and registration

10:30 Welcome: Hans-Uwe Simon, Dean of the Medical Faculty David Spreng, Dean of the Vetsuisse Faculty Britta Engelhardt, President of the MIC

Session 1. Chairs: Inti Zlobec, Raphael Sznitman

10:35 Machine learning at the University of Bern An overview presented by the scientific committee

10:45 Jean-Philippe Thiran (EPFL, Lausanne, CH) Keynote Inverse problems in ultrasound imaging: Efficient modeling, sparse regularization and neural networks

11:30 Anna Kreshuk (EMBL, Heidelberg, DE) Image segmentation at scale

12:00 Michael Schell (Cenibra GmbH, DE) Teacher or student? How to teach AI to pick correct confocal microscopy images

12:15 Lunch and industry exhibition

Session 2. Chairs: Guillaume Witz, Mauricio Reyes

13:45 Inti Zlobec (University of Bern, CH) Digital pathology in translational research

14:15 Andrew Janowczyk (Lausanne Univ. Hospital, CH) Computational pathology: Towards precision medicine

14:45 Gergely Kovach (Sysmex Suisse AG, CH) High resolution whole tissue imaging for 3D analysis

15:00 Coffee and industry exhibition

Session 3. Chairs: Mauricio Reyes, Raphael Sznitman

15:30 David Pointu (GE Healthcare AG, CH) Advantages of IN Carta Phenoglyphs™ HCA machine learning module

15:45 Ender Konukoglu (ETH Zürich, CH) On Bayesian models with networks for reconstruction and detection

16:15 Christine Decaestecker (University of Brussel, BE) Segmentation of histopathological images: How to reduce the supervision needs for deep learning

16:45 Conclusions and farewell

REGISTRATION

http://www.mic.unibe.ch/ symposium_registration.php

Categories

Approved for 0.5 day credit for continued animal experimentation in the Canton of Bern
Languages: English