Medical University of Vienna · Radiation Oncology
AI and medical physics
for radiation oncology.
We develop computational methods to make radiotherapy planning more efficient, evaluate clinical workflows, and understand patients’ experiences of treatment.
Medical University of Vienna · Vienna, Austria
Research
From computational methods to clinical practice
AI-based treatment planning
We develop dose prediction, deliverable plan generation, and differentiable dose calculation methods for automated and adaptive radiotherapy research.
Auto-segmentation
We investigate AI-based contouring and the clinical implementation and evaluation of segmentation tools across treatment sites.
Patient-reported outcomes
We use electronic patient-reported outcome measures to study symptoms during and after radiotherapy and evaluate treatment in clinical practice.
Clinical workflows and safety
We develop data-driven tools for workflow monitoring, incident reporting, and quality assurance to support efficient and transparent radiotherapy practice.
Selected publications
Full publication listPyDoseRT: A physics-informed, plug-and-play dose engine for gradient-based radiotherapy treatment planning
Medical Imaging with Deep Learning · Short Paper Track · July 2026 · Related preprint ↗
A probabilistic framework for risk-bounded patient-specific quality assurance in volumetric modulated arc therapy based on measured and calculated gamma pass rates
Zeitschrift für Medizinische Physik · Published online May 2026
Prospective evaluation of acute side effects profiles in moderately hypofractionated whole-pelvic radiotherapy for prostate cancer
Clinical and Translational Radiation Oncology 59, 101169
Prospective monitoring of the clinical implementation of ultrahypofractionated whole-breast radiotherapy using electronic patient-reported outcome measures
Clinical and Translational Radiation Oncology 58, 101148
Earlier selected publications · 2025–2021
Optical Coherence Tomography Angiography (OCTA) Captures Early Micro-Vascular Remodeling in Non-Melanoma Skin Cancer During Superficial Radiotherapy: A Proof-of-Concept Study
An open-source irradiation and data-handling framework for pre-clinical ion-beam research
Enhancing clinical safety in radiation oncology: A data-driven approach to risk management
Ultra-fast, one-click radiotherapy treatment planning outside a treatment planning system
Automation of ePROMs in radiation oncology and its impact on patient response and bias
Generating deliverable DICOM RT treatment plans for prostate VMAT by predicting MLC motion sequences with an encoder-decoder network
Increasing Quality and Efficiency of the Radiotherapy Treatment Planning Process by Constructing and Implementing a Workflow-Monitoring Application
Clinical Implementation and Evaluation of Auto-Segmentation Tools for Multi-Site Contouring in Radiotherapy
On the sensitivity of PROMs during breast radiotherapy
Can Generative Adversarial Networks help to overcome the limited data problem in segmentation?
Technical Note: Dose prediction for radiation therapy using feature-based losses and One Cycle Learning
Recent preprints
Not peer reviewedSimkó A, Zimmermann L, Fuchs H, Heilemann G · September 2026 · arXiv:2609.01085
Zimmermann L, Fuchs H, Simkó A, Heilemann G · September 2026 · arXiv:2609.01018
Team
Medical physics, clinical research, and data science
Gerd Heilemann
Principal Investigator
Researcher profile ↗Simon Glatzer
PhD Student
Matthias Kronsteiner
PhD Student
Get in touch
For research collaborations or enquiries about working with the group, contact Gerd Heilemann.
Department of Radiation Oncology
Medical University of Vienna
Währinger Gürtel 18–20, 1090 Vienna, Austria