About me

I am a third-year PhD Candidate at ETH Zürich and the German Cancer Research Center (DKFZ). My work is dedicated to advancing scientific discovery through deep learning and explainable AI (XAI) applied to high-dimensional and multi-modal data. I contributed to multiple interdisciplinary discovery projects across the domains of 🩻 medical imaging, 🦠 microbiology, and 🧱 material sciences. My efforts extend to increasing the safety of AI systems through model uncertainty, XAI (meta-)evaluation and model failure detection with specific focus on Vision Language Models (VLMs).

🎓 Academic Education

Download full CV

📑 Publications

Explainable AI-based analysis of human pancreas sections detects traits of type 2 diabetes

Lukas Klein, Sebastian Ziegler, Yanni Morgenroth, Eyke Schoeniger, Michele Solimena, Felicia Gerst, Robert Wagner, Fabian Isensee, Klaus Maier-Hein, Paul F. Jaeger
Under review at Nature Metabolism

Navigating the Maze of Explainable AI: A Systematic Approach to Evaluating Methods and Metrics

Lukas Klein, Carsten Lueth, Udo Schlegel, Till Bungert, Mennatallah El-Assady, Paul F.Jaeger
Under review at NeurIPS 2024

Enhancing predictive imaging biomarker discovery through treatment effect analysis

Shuhan Xiao, Lukas Klein, Paul F. Jaeger, Jens Petersen, Klaus Maier-Hein
Under review at Nature Scientific Reports

Interactive Semantic Interventions for VLMs: A Human-in-the-Loop Approach to Interpretability

Lukas Klein, Kenza Amara, Carsten T. Lüth, Antonio Foncubierta-Rodríguez, Hendrik Strobelt, Mennatallah El-Assady, Paul F. Jaeger
Under review at NeurIPS 2024 Safe Generative AI Workshop

Explainable AI-based analysis of human pancreas sections detects traits of type 2 diabetes

Lukas Klein, Sebastian Ziegler, Yanni Morgenroth, Eyke Schoeniger, Michele Solimena, Felicia Gerst, Robert Wagner, Fabian Isensee, Klaus Maier-Hein, Paul F. Jaeger
Under review at NeurIPS 2024 IAI Workshop

Discovering Process Dynamic for Scalable Perovskite Solar Cell Manufacturing with Explainable AI

Lukas Klein, Sebastian Ziegler, Felix Laufer, Charlotte Debus, Markus Götz, Klaus Maier-Hein, Ulrich W. Paetzold, Fabian Isensee, Paul F. Jaeger
Advanced Materials (IF: 30). This work has been covered i.a. by The Independent.

Understanding Solar Cell Manufacturing with Explainable AI

Lukas Klein, Sebastian Ziegler, Felix Laufer, Charlotte Debus, Markus Götz, Klaus Maier-Hein, Ulrich W. Paetzold, Fabian Isensee, Paul F. Jaeger
NeurIPS 2023 XAIA Workshop (Oral, Top 4 Paper)

Semi-supervised automated Gleason Grading on WSI

Maximilian Fischer, Lars Krämer, Sebastian Ziegler, Lukas Klein, Paul F. Jaeger, Marco Molden, Peter Neher, Fabian Isensee, Klaus Maier-Hein
ECDP 2024 (Oral)

Navigating the Pitfalls of Active Learning Evaluation: A Systematic Framework for Meaningful Performance Assessment

Carsten T. Lüth, Till J. Bungert, Lukas Klein, Paul F. Jaeger
NeurIPS 2023

A Call to Reflect on Evaluation Practices for Failure Detection in Image Classification

Paul F. Jaeger, Carsten T. Lueth, Lukas Klein, Till J. Bungert
ICLR 2023 (Oral, Top 1% Paper)

From Correlation to Causation: Formalizing Interpretable Machine Learning as a Statistical Process

Lukas Klein, Mennatallah El-Assady, Paul F Jaeger
IJCAI 2022 Workshop on XAI

Improving Explainability of Disentangled Representations using Multipath-Attribution Mappings

Lukas Klein, João B. S. Carvalho, Mennatallah El-Assady, Paolo Penna, Joachim M. Buhmann, Paul F Jaeger
MIDL 2022

📨 Contact