Georg Schramm

prof_pic.jpg

I am an Assistant Professor in Molecular Image Reconstruction and Analysis at KU Leuven, Belgium, emphasizing improved diagnostic image quality through advanced modeling, cutting-edge reconstruction algorithms, and sustainable machine learning techniques.

Born in 1987 in Görlitz, Germany, I spent my childhood engrossed in football and playing saxophone and clarinet in the local music school’s big band. In 2005, I moved to Dresden to study physics at TU Dresden, later completing an Erasmus semester at the University of Sheffield in 2009. I earned my Master’s in physics in 2011, ranking among the top five graduates in TU Dresden’s School of Science.

In 2015, I obtained a PhD (Dr. rer. medic) in medical imaging with the highest distinction (summa cum laude) from TU Dresden / Helmholz-Zentrum Dresden-Rossendorf. Following seven years as a Postdoc at KU Leuven, Belgium, focusing on advanced image reconstruction techniques for molecular imaging, I spent a year as a visiting instructor at Stanford University, CA, working on sodium MR image reconstruction.

In my free time, I enjoy hiking, photography, cycling, as well as supporting the San Francisco 49ers.

news

Feb 01, 2026 I really enjoyed giving my invited talk about “ML in Positron Emission Tomography” at the AI in the Wild West workshop in Rennes, France. Pdf version available here.
Jan 29, 2026 Our publication on object-independent scatter normalization in PET was published in Physics in Medicine and Biology. Arxiv version available here.
Nov 20, 2025 Together with Seyed Amir Zaman Pour and Charles Carron, our team was ranked as runner up in the 2025 Ultra low dose PET denoising challenge.
Oct 06, 2025 I will give an invited talk entitled “Expected Enhancement in PET Technology & Novel Methods Enabled by High Sensitivity PET Systems” at the Ultra low dose PET workshop at the IEEE MIC/NSS 2025 conference in Yokohama, Japan.
Oct 06, 2025 Max Keppens has joint our lab as a PhD student and will work on improving PET reconstruction on data from the NeuroExplorer. Welcome Max!

selected publications

  1. pls.png
    Evaluation of parallel level sets and Bowsher’s method as segmentation-free anatomical priors for time-of-flight PET reconstruction
    Georg Schramm, Martin Holler, Ahmadreza Rezaei, and 5 more authors
    IEEE transactions on medical imaging, 2017
  2. roadmap_2020.png
    Quantitative PET in the 2020s: a roadmap
    Steven R Meikle, Vesna Sossi, Emilie Roncali, and 29 more authors
    Physics in Medicine & Biology, 2021
  3. bow_cnn.png
    Approximating anatomically-guided PET reconstruction in image space using a convolutional neural network
    Georg Schramm, David Rigie, Thomas Vahle, and 5 more authors
    Neuroimage, 2021
  4. tof_perspective.png
    Time of flight in perspective: instrumental and computational aspects of time resolution in positron emission tomography
    Dennis R Schaart, Georg Schramm, Johan Nuyts, and 1 more author
    IEEE transactions on radiation and plasma medical sciences, 2021
  5. fast_memory_eff.png
    Fast and memory-efficient reconstruction of sparse Poisson data in listmode with non-smooth priors with application to time-of-flight PET
    Georg Schramm and Martin Holler
    Physics in Medicine & Biology, 2022
  6. parallelproj.png
    PARALLELPROJ—an open-source framework for fast calculation of projections in tomography
    Georg Schramm and Kris Thielemans
    Frontiers in Nuclear Medicine, 2024
  7. fast_precond.png
    Fast PET reconstruction with variance reduction and prior-aware preconditioning
    Matthias J. Ehrhardt, Zeljko Kereta, and Georg Schramm
    Frontiers in Nuclear Medicine, 2025