41st Deep Learning Meetup in Vienna (virtual edition)

Dear Deep Learning community,

It is our pleasure to present you another online meetup in our Deep Learning meetup series!

This time we will look into different deep learning architectures and their application in the medical sciences, with a talk by two researchers of the St. Anna Children’s Cancer research institute and the Software Competence Center Hagenberg!

Our Agenda for this meetup:

18:30 - 18:40 Welcome & Announcements

18:40 - 19:30
Deep Tissue Analysis - A Step Towards Multiscale Tumor Sample Exploration
Florian Kromp, St. Anna Children’s Cancer research institute
Lukas Fischer, Software Competence Center Hagenberg

19:30 - 20:00 Networking: individual discussions in breakout rooms

After the talk we'll have time for networking amongst the community in breakout groups. Have your snacks & drinks ready ;-)

We would be glad to welcome you at this meetup!

See you soon!
René, Jan, Alex, Tom

---------------------------------------------------------------------

Talk abstract:

Deep Tissue Analysis - A Step Towards Multiscale Tumor Sample Exploration

Biomedical analysts and application specialists developing diagnostic strategies for patients suffering from cancer are faced with an ever-increasing size of data, based on multimodal and multiscale analyses of tissue samples. Resulting large-scale while complex biological data challenge the design of automated diagnostic pipelines, but at the same time set the stage for applying deep learning based methods. These can support the generation of high-quality annotations prior to data interpretation by experts while decreasing the resources needed. Based on a project aiming at multiOMICs data exploration of patients suffering from Neuroblastoma tumors, we introduce and discuss deep neural network architectures in bioimage and genomics data analysis.

Florian Kromp is working as PostDoc in the tumor biology group at the St. Anna Children’s Cancer research institute (CCRI). During his bachelor studies in medical informatics at the TU Wien he started his research career in the immunological diagnostics group at CCRI. While working on machine-learning based assessment of Akute Lymphoblastic Leukemia (ALL) data, he discovered his interest in automated image processing and later joined the Tumour Biology group. Working on quantitative microscopy imaging data, he received his MSc and PhD degrees for performing research on the automated segmentation of cellular nuclei in fluorescence microscopy images. His main interest is to use deep learning approaches for data analysis with the overall aim to combine multi-modal datasets including imaging and multiOMICs data for comprehensive visualization and tailored analysis of patients suffering from cancer.

Lukas Fischer is Research Manager for Data Science at the Software Competence Center Hagenberg (SCCH). He did his MSc in Medical Informatics at the TU Wien with a focus on medical image segmentation, statistical shape models, image registration, bio-inspired optimization algorithms and machine learning. He continued his PhD studies and research in the domain of medical imaging/medical physics as a research assistant at the Computational Imaging Research Lab (CIR) at the Medical University of Vienna (MUW). His research focus was on the computer vision based quantification of trabecular microarchitecture in patients suffering from severe osteoporosis after lung transplantation. His current main research interests are in Machine Learning, with special focus on Deep Learning, Generative Models (e.g. GANs, VAEs, AEs), Vision Transformers, Computer Vision, especially on medical data (e.g. segmentation, registration, classification, and tracking), as well as Transfer Learning and Privacy Preserving Learning aspects.