M.Sc. Laura Hellwege

Institut für Medizintechnik
Universität zu Lübeck
Ratzeburger Allee 160
23562 Lübeck
Gebäude 64, Raum 063

Email:	l.hellwege(at)uni-luebeck.de
Phone:	+49 451 3101 5471

Roles

Research Assistant

Research

Research Interests

Computed Tomography
Inverse Problems
Medical Image Processing
Neural Networks

Involved Projects

Tomedex

Curriculum Vitae

LAURA HELLWEGE was born in Stade, Germany in 1997. She received her Master of Science in Mathematics in Medicine and Life Sciences in 2020 from the Universität zu Lübeck, Germany. During her study she was mainly interested in numerical methods and inverse problems in medical image processing. In 2020 she wrote her master thesis at the Institute for Medical Engineering about the usage of Neural Networks for preprocessing in Computed Tomography. Since 09/2020 she is a Research Assistant at the Institute of Medical Engineering where she works in the field of computer tomographic reconstruction.

Publications

[ 2026 ]
[ 2025 ]
[ 2023 ]
[ 2021 ]

2026[ to top ]

Hellwege, L., Engster, J. C., Schaar, M., Buzug, T. M. and Stille, M.: Reversible Image Augmentations for Unsupervised Deep Learning in Computed Tomography, 156–161, 2026, DOI: 10.1007/978-3-658-51100-5_33.
- [ BibTeX ]
@inproceedings{Hellwege2026Augmentations, abstract = {We propose a physically consistent, reversible image augmentation approach for an unsupervised computed tomography (CT) reconstruction deep learning framework. The framework has the unique property of calculating the loss in the projection domain, so no image-domain ground truth is required. Even though previous evaluation proved feasibility of unsupervised deep learning for inverse problems like CT reconstruction, it also showed frail behavior after data alterations. To increase training diversity without violating projection-image fidelity, we apply reversible image augmentations that preserve non-zero image pixels, record the sampled parameters, and invert the transforms on the U-Net++ output. We describe implementation details, parameter sampling schemes and practical constraints for CT data, and discuss how the approach permits richer, physically consistent augmentation for improving performance in unsupervised reconstruction.}, address = {Wiesbaden}, author = {Hellwege, Laura and Engster, Johann C. and Schaar, Moritz and Buzug, Thorsten M. and Stille, Maik}, booktitle = {Bildverarbeitung für die Medizin}, editor = {Handels, Heinz and Breininger, Katharina and Deserno, Thomas M. and Maier, Andreas and Maier-Hein, Klaus H. and Palm, Christoph and Tolxdorff, Thomas}, keywords = {hellwegelaura}, pages = {156-161}, publisher = {Springer Fachmedien Wiesbaden}, title = {Reversible Image Augmentations for Unsupervised Deep Learning in Computed Tomography}, year = 2026 }

2025[ to top ]

Hellwege, L., Claus, C. G., Schaar, M., Buzug, T. M. and Stille, M.: Generation of realistic multi-energetic cone-beam CT datasets based on medical software phantoms, Current Directions in Biomedical Engineering, 11(1), 559–562, 2025, DOI: 10.1515/cdbme-2025-0242.
- [ BibTeX ]
@article{Hellwege2025Simulation, author = {Hellwege, Laura and Claus, Carla Gensana and Schaar, Moritz and Buzug, Thorsten M and Stille, Maik}, journal = {Current Directions in Biomedical Engineering}, keywords = {buzugthorsten}, month = {09}, number = 1, pages = {559–562}, publisher = {Walter de Gruyter GmbH}, title = {Generation of realistic multi-energetic cone-beam {CT} datasets based on medical software phantoms}, volume = 11, year = 2025 }
Hellwege, L., Engster, J. C., Schaar, M., Buzug, T. M. and Stille, M.: Unsupervised Deep Learning for Inverse Problems in Computed Tomography, 2025, DOI: 10.48550/arXiv.2508.05321.
- [ BibTeX ]
@misc{Hellwege2025Unsupervised, author = {Hellwege, Laura and Engster, Johann Christopher and Schaar, Moritz and Buzug, Thorsten M and Stille, Maik}, keywords = {hellwegelaura}, note = {Preprint}, title = {Unsupervised Deep Learning for Inverse Problems in Computed Tomography}, year = 2025 }

2023[ to top ]

Hellwege, L., Schaar, M., Buzug, T. and Stille, M.: Enhancing virtual monoenergetic images for non-congruent dual-energy CT projection data, Current Directions in Biomedical Engineering, 9, 674–677, 2023, DOI: 10.1515/cdbme-2023-1169.
- [ BibTeX ]
@article{article, author = {Hellwege, Laura and Schaar, Moritz and Buzug, Thorsten and Stille, Maik}, journal = {Current Directions in Biomedical Engineering}, keywords = {buzugthorsten}, month = {09}, pages = {674-677}, title = {Enhancing virtual monoenergetic images for non-congruent dual-energy CT projection data}, volume = 9, year = 2023 }
Hellwege, L., Schaar, M., Buzug, T. M. and Stille, M.: Advanced Empirical Dual-Energy Calibration, 2023.
- [ BibTeX ]
@inproceedings{hellwege2023advanced, author = {Hellwege, Laura and Schaar, Moritz and Buzug, Thorsten M. and Stille, Maik}, booktitle = {Proceedings of IEEE MIC 2023}, keywords = {buzugthorsten}, publisher = {IEEE Xplore}, title = {Advanced Empirical Dual-Energy Calibration}, year = 2023 }

2021[ to top ]

Hellwege, L., Blum, N., Buzug, T. M. and Stille, M.: Partial Convolution Network for Metal Artifact Reduction in CT Preprocessing: Preliminary Results, 2021.
- [ BibTeX ]
- [ URL ]
@inproceedings{Hellwege2021PartialCN, author = {Hellwege, Laura and Blum, Nele and Buzug, Thorsten M. and Stille, Maik}, booktitle = {Medical Imaging and Deep Learning 2021}, keywords = {buzugthorsten}, month = {07}, title = {Partial Convolution Network for Metal Artifact Reduction in CT Preprocessing: Preliminary Results}, year = 2021 }