Working Group Artificial Intelligence in Radiation Oncology | Radiation Oncology TUM University Hospital Munich
Radiotherapy
Artificial Intelligence in radiation oncology research group
Use of AI in radiation oncology: Our research group develops AI models for prognosis, therapy prediction and segmentation in cancer.
artificial-intelligence-research-group
Working Group Artificial Intelligence in Radiation Oncology
The application of artificial intelligence (AI) methods opens up new possibilities in clinical medicine. In our interdisciplinary research group, we utilize state-of-the-art AI models to address clinically relevant questions in (radio)oncology. We develop methods to enhance the accuracy and safety of large language models (LLMs) in clinical applications. We analyze LLMs for clinical decision support, for the support of the daily clinical workloads and for health education for cancer patients. Furthermore, we evaluate the potential of multimodal AI models that can process various types of data. Another focus of our work lies in the analysis of medical imaging data (CT, MRI, and PET) for the non-invasive characterization of biological tissues. Our models aim to improve prognostic predictions for patients, assess therapy response, and determine non-invasive molecular-pathological properties. Additionally, we develop innovative agentic AI approaches for medical therapy planning within the ERC-funded project AI-PIONEER.
Prof. Jan Peeken, MD PhD MHBA Head of Research Group
Research Focus:
Agentic AI for interactive medical treatment planning (AI-PIONEER ERC-funded project)
Application of large language models as an information source and decision-support system (AIDvice project)
Multimodal foundation models for gastrointestinal cancers (BZKF Lighthouse)
AI-based analysis for patients with brain metastases (AURORA Multicenter Study of the AG Stereotaxy of DEGRO)
AI-based analysis of patients with anal carcinoma (DKTK Multicenter Study)
AI-based analysis of patients with soft tissue sarcomas
AI-based analysis of patients with prostate carcinoma (Co-IMPACT consortium)
Development and improvement of neural networks for tumor and risk organ segmentation
Prediction of side effects of radiation therapy (DFG SPP 2177)
Current team members:
Josef Buchner (Physician Scientist)
Dr. med. Julia Fabian (Physician Scientist)
Dr. med. Dr. rer. Nat. Kim Kraus (Physician Scientist)
Linus Marx (Physician Scientist)
Dr. med. Mai Nguyen (Physician Scientist)
Dr. med. Samuel Vorbach (Physician Scientist)
Dr. med. Lucas Zander (Physician Scientist)
Can Erdur (MSc; PhD-student)
Stefan Fischer (MSc; PhD-student)
Ahmed El Gohary Yasser Mohamed (MSc; PhD-student)
Johannes Kiechle (MSc; PhD-student)
Lukas Atzelsberger (Medical Doctoral Thesis)
Lena-Maria Paula Irmgard Baumann (Medical Doctoral Thesis)
Reuter LM, Kraus KM, Fischer SM, …, Peeken, JC (2026). Prediction of Symptomatic Radiation Pneumonitis in Lung Cancer Patients: A Radiomics and Dosiomics Machine Learning Approach Using the Prospective Multicenter RTOG 0617 and REQUITE Trials. International journal of radiation oncology, biology, physics, S0360-3016(26)00365-2. https://doi.org/10.1016/j.ijrobp.2026.01.031.
Peeken JC*, Etzel L*, Tomov T et al. Development and benchmarking of a Deep Learning-based MRI-guided gross tumor segmentation algorithm for Radiomics analyses in extremity soft tissue sarcomas. Radiother Oncol. 2024 Aug;197:110338. doi: https://doi.org/10.1016/j.radonc.2024.110338. *shared authorship.
Buchner JA, Kofler F, Mayinger M, ... , Peeken JC. Radiomics-based prediction of local control in patients with brain metastases following postoperative stereotactic radiotherapy. Neuro Oncol. 2024 Sep 5;26(9):1638-1650. https://doi.org/10.1093/neuonc/noae098.
Kraus KM, Oreshko M, Schnabel JA, ..., Peeken JC. Dosiomics and radiomics-based prediction of pneumonitis after radiotherapy and immune checkpoint inhibition: The relevance of fractionation. Lung Cancer. 2024 Mar;189:107507. doi: https://doi.org/10.1016/j.lungcan.2024.107507.
Zamboglou C*, Peeken JC*, Janbain A, et al. Development and Validation of a Multi-institutional Nomogram of Outcomes for PSMA-PET-Based Salvage Radiotherapy for Recurrent Prostate Cancer. JAMA Netw Open [Internet]. 2023; 6: e2314748. https://jamanetwork.com/journals/jamanetworkopen/fullarticle/2805173, * shared authorship.
Spohn SKB, Schmidt-Hegemann N-S, Ruf J, ..., Peeken JC. Development of PSMA-PET-guided CT-based radiomic signature to predict biochemical recurrence after salvage radiotherapy. Eur J Nucl Med Mol Imaging. 2023; Available at: https://doi.org/10.1007/s00259-023-06195-3.
Buchner JA, Kofler F, Etzel L, ..., Peeken JC. Development and external validation of an MRI-based neural network for brain metastasis segmentation in the AURORA multicenter study. Radiother Oncol. 2023; 178: 109425. available at: https://doi.org/10.1016/j.radonc.2022.11.014
Spohn SKB, Farolfi A, Schandeler S, ..., Peeken JC. The maximum standardized uptake value in patients with recurrent or persistent prostate cancer after radical prostatectomy and PSMA-PET-guided salvage radiotherapy-a multicenter retrospective analysis. Eur J Nucl Med Mol Imaging. 2022 Dec;50(1):218-227. doi: https://doi.org/10.1007/s00259-022-05931-5.
Peeken JC, Asadpour R, Specht K, et al. MRI-based Delta-Radiomics predicts pathologic complete response in high-grade soft-tissue sarcoma patients treated with neoadjuvant therapy. Radiother Oncol. 2021 Nov;164:73-82. https://doi.org/10.1016/j.radonc.2021.08.023.
Peeken JC, Shouman MA, Kroenke M et al. A CT-based radiomics model to detect prostate cancer lymph node metastases in PSMA radioguided surgery patients. Eur J Nucl Med Mol Imaging. 2020;47(13):2968-2977. https://doi.org/10.1007/s00259-020-04864-1.