Index

Large Language Models for Modified Frenchay Dysarthria Assessment Reports from Parkinson’s Speech: Model Choice and Prompting Effects

Advanced nnU-Net Ensemble Techniques for Lung Nodule Segmentation

This thesis outlines a comprehensive research program aimed at advancing medical
image segmentation through enhanced nnU-Net ensemble methodologies. Building upon
substantial experimental results that demonstrate significant improvement over existing
approaches, the proposed research addresses critical gaps in current medical imaging AI
capabilities. The research aims to establish new performance standards for automated lung
nodule detection with current achievements of 0.84 dice coefficient representing a 29.2%
improvement over SAM baseline and approaching clinical utility thresholds. Future work will
focus on Vision Transformer integration with nnU-Net architectures, generalization validation
across additional lung imaging datasets, and clinical deployment optimization. The expected
outcomes include significant academic contributions through peer-reviewed publications,
practical clinical applications with potential for real-world healthcare impact, and establishment
of open-source implementations for research community adoption.

Development of a Local LLM Agent System for Clinical Expert Support and Automation in MRI Planning for Radiation Therapy

20250904_MastersThesis_MRI_LLM_Agent_Project

If you are interested, please contact fabian.wagner@fau.de

Cold Diffusion for CT Field-of-View Extension

Adaptive Biophysical Modelling for Thermal Ablation

Reinforcement Learning for Adaptive Protection in Power Grids

This thesis explores the use of reinforcement learning to improve protection strategies in power grids with high penetration of renewable energy. Conventional relay schemes often fail under changing fault conditions caused by inverter-based DERs. This thesis investigates how adaptive, data-driven control can overcome these challenges. A simulated environment based on DIgSILENT PowerFactory enables comparison between traditional protection and learning-based approaches.

Reproducible Reinforcement Learning on a Real-World Power Grid Control Problem

This is a project only (10 ECTS) focused on reproducible reinforcement learning and paper-driven implementation.
You will re-implement an IEEE-published RL method [1] and evaluate it on a realistic, safety-critical control problem.

The application domain is power grids, used purely as a real-world benchmark for reinforcement learning.
No prior power-systems background is required.

Implement a Q-learning-based control method from a research paper (state/action design, reward shaping, constraints).
Validate the implementation on a benchmark setup (reproducibility, metrics, sanity checks).
Apply the method to real data from a 20 kV distribution grid.
Optional: extend the same RL framework towards distance protection (concept + first prototype, time permitting).

Who should apply

Computer science or related background.
Good Python skills (NumPy/Pandas, Git).
Basic knowledge of machine learning or reinforcement learning.
Interest in implementing and evaluating methods from scientific papers.
Able to attend the weekly in-person meeting in Erlangen (Mondays, 14:00).

Apply

Send one PDF to julian.oelhaf@fau.de with the subject:

"Application | Project (10 ECTS) | Reproducible RL on Power Grids | <Your Full Name>"

Email body (max. 200 words): Short motivation and your earliest state date.

Attach as one PDF: CV, transcript (dated), optional code links.

📌 Incomplete applications will not be considered.

References

[1] H. C. Kılıçkıran, B. Kekezoglu, and N. G. Paterakis, Reinforcement Learning for Optimal Protection Coordination, IEEE SEST, 2018. DOI
[2] D. Wu, X. Zheng, D. Kalathil, and L. Xie, Nested Reinforcement Learning-Based Control for Protective Relays in Power Distribution Systems, IEEE CDC, 2019. DOI
[3] D. Wu, D. Kalathil, M. M. Begovic, K. Q. Ding, and L. Xie, Deep Reinforcement Learning-Based Robust Protection in DER-Rich Distribution Grids, IEEE Open Access Journal of Power and Energy, 2022. DOI

Device Detection for Improved Guidance in Minimally Invasive Interventions

Evolving Universal Datasets: Cross-Architecture Generalization via Evolutionary Distillation

The proliferation of large-scale datasets has been central to the success of modern deep learning, yet it presents significant challenges in terms of computational cost, training time, and data privacy. These issues are particularly acute in applications like Neural Architecture Search (NAS), where repeated training is time consuming. Dataset distillation offers a compelling solution by synthesizing small, information-rich datasets that act as efficient, privacy-preserving proxies for the originals. However, the practical utility of current distillation methods is severely hampered by a critical flaw: poor cross-architecture generalization. Datasets distilled for one network architecture often fail when used to train a different one, limiting their use as universal training assets.

This thesis aim to directly confront this generalization challenge by proposing a novel distillation framework based on an Evolutionary Algorithm (EA). We posit that conventional gradient-based optimization methods are prone to finding solutions overfitted to a single model’s inductive biases. In contrast, an EA can perform a more global search for a truly architecture-agnostic dataset. The core contribution of this work is a new fitness function that explicitly rewards generalization. By evaluating a candidate dataset’s performance across a diverse portfolio of architectures, our evolutionary search is driven to discover a compact dataset that captures universal features. This objective is further refined by incorporating gradient matching principles and full training epoch evaluations, ensuring the resulting dataset is not only generalizable but also effective for training robust models.