Theory Meets Practice #5: Al for Precision Medicine: From Foundation Models to Tumor Tissue Profiling in Computational Pathology
We are excited to host a BLISS x dida workshop featuring Lukas Ruff (VP of Data Science @ Aignostics) together with his colleagues (Christina Embacher, Jonas Dippel, and Maaike Galama), who will guide us through an interactive session on AI for Precision Medicine.
Title: Al for Precision Medicine: From Foundation Models to Tumor Tissue Profiling in Computational Pathology
📅 Date: 24.06.2026
🕕 Time: 18:00
📍 Location: TU Berlin Marchstrasse 23 [Room 0.011]
The session will last around 2 hours, followed by a networking session with dida and fellow AI enthusiasts (and free pizza!🍕). Bring your laptop!
Abstract: Nearly every cancer diagnosis still begins with a pathologist examining a stained tissue slide under a microscope. Digital pathology turns those slides into gigapixel images — and with them, a uniquely demanding frontier for machine learning. But getting from raw pixels to clinically meaningful, quantitative insight about a tumor and its microenvironment is far from trivial.
In this workshop, Aignostics — a computational pathology company and Charité spin-off — walks you along the arc from core ML research to real-world application. We start with an overview of digital pathology and what makes it challenging for ML (gigapixel images, scarce labels, scanner and staining variability). We then look at how pathology foundation models are built and what separates a good one from a fragile one — not just accuracy, but robustness to non-biological artifacts — with a short hands-on segment. Finally, we put these models to work: with Atlas H&E-TME we profile the tumor microenvironment from routine H&E slides, and you'll get hands-on with OpenTME — an open dataset of TME profiles across five cancer types from TCGA — and TME Studio to run your own analyses.
What we'll cover:
● Digital pathology 101 — why tissue slides are hard for ML, and where AI is changing the field.
● Developing pathology foundation models — training at scale, evaluation across benchmarks, and why robustness (not just performance) decides clinical readiness.
● H&E tissue profiling in practice — from a stained slide to thousands of quantitative cell- and tissue-level readouts, and how to explore them for biomarker discovery and spatial biology (hands-on with OpenTME + TME Studio).
By the end, you'll understand how a modern pathology AI stack fits together — and you'll have explored first analyses on real tumor data yourself.
Who is this event for?
This session is targeted at anyone with basic ML knowledge. Experience with Python is very helpful. We will cover the most important aspects as part of the workshop.
We are BLISS e.V., Berlin’s AI community connecting like-minded individuals passionate about machine learning and data science. Our BLISS Workshops connect students and young professionals with industry partners, offering an inside look into how machine learning is applied in real-world settings - from research and development to deployment.
We are dida, scientific engineers who believe that reliable AI should not be a "black box". That is why we prioritize transparency, mathematics, and code over hype. By bridging the gap between theoretical research and production, we develop custom white-box AI solutions that are fully explainable, rigorously engineered, and free of "magic".
dida Website: https://dida.do
dida Youtube: https://www.youtube.com/@dida-do
BLISS Website: https://bliss.berlin
BLISS Youtube: https://www.youtube.com/@bliss.ev.berlin