Georg Schramm

The Molecular Image Reconstruction Group at KU Leuven, within the Department of Imaging & Pathology, offers a fully funded PhD position in advanced brain PET image reconstruction. Led by Professor Georg Schramm, the group is renowned for its research at the intersection of medical image reconstruction, positron emission tomography (PET), and machine learning. The group collaborates closely with UZ Leuven, one of Europe's leading academic hospitals, providing direct access to state-of-the-art clinical PET infrastructure and expertise in nuclear medicine and neurology. This PhD position is part of the PEARL project (PET Enhancement via Advanced Reconstruction using variational methods and machine Learning), a tri-national Weave project funded by FWO (Belgium), FWF (Austria), and DFG (Germany). The project involves collaboration with the University of Graz (Prof. Martin Holler) and TU Munich (Prof. Reinhard Heckel), aiming to advance static and dynamic brain PET image reconstruction through open benchmarking infrastructure, novel machine learning methods, and memory-efficient variational algorithms operating directly on raw PET data. As a PhD researcher, you will contribute to several key tasks: Data curation: Retrospective collection, quality control, and preprocessing of approximately 500 static and dynamic brain PET/MR datasets acquired at UZ Leuven over the past decade. Open data infrastructure: Pseudonymisation and conversion of raw listmode data into open, standardized formats. GPU software development: Design and optimization of high-performance, open-source time-of-flight (TOF) listmode forward and back-projectors for integration into machine learning frameworks such as PyTorch, building on the parallelproj library. Method evaluation: Critical assessment of reconstruction algorithms developed across partner institutions, in close collaboration with clinical and kinetic modelling experts at UZ Leuven. Challenge organisation: Planning and execution of an open international brain PET reconstruction challenge, including data sharing agreements, automatic evaluation pipelines, and platform setup. Dissemination: Presentation of results at international conferences and publication in peer-reviewed journals. Applicants must have a Master's degree (or equivalent) in Engineering, Physics, Computer Science, Mathematics, or a closely related field, obtained before the start date. Essential skills include solid programming abilities in Python (or other high-level languages), experience with scientific computing libraries (e.g., NumPy, PyTorch), a strong mathematical background in linear algebra, optimization, and probability/statistics, and excellent written and spoken English. Enthusiasm for interdisciplinary research at the interface of medical imaging and machine learning, as well as high intrinsic motivation, are expected. Optional but advantageous qualifications include prior experience with medical image reconstruction or emission tomography, efficient handling of large research datasets, knowledge of variational methods, convex optimization, or iterative algorithms for inverse problems, experience with open-source software development and version control (Git), and exposure to deep learning methods. The position offers a fully funded 4-year PhD contract within a stimulating, internationally connected research environment. Benefits include direct access to clinical PET infrastructure and experts at UZ Leuven, high-performance GPU computing resources, participation in international conferences and project workshops (Leuven, Munich, Graz), short-term research exchanges at partner institutions in Graz and Munich, and immersion in a vibrant, international academic community in Leuven—a historic university city in the heart of Europe. KU Leuven is committed to equal opportunity and diversity, fostering an inclusive, respectful, and socially safe environment. For further information or questions about accessibility or support, contact Prof. Georg Schramm at [email protected]. Application deadline: 10 May 2026. Apply online via the KU Leuven job portal.