Document Open Access Logo

Inverse Biophysical Modeling and Machine Learning in Personalized Oncology (Dagstuhl Seminar 23022)

Authors George Biros, Andreas Mang, Björn H. Menze, Miriam Schulte and all authors of the abstracts in this report

Thumbnail PDF


  • Filesize: 8.17 MB
  • 32 pages

Document Identifiers

Author Details

George Biros
  • University of Texas at Austin, US
Andreas Mang
  • University of Houston, US
Björn H. Menze
  • Universität Zürich, CH
Miriam Schulte
  • Universität Stuttgart, DE
and all authors of the abstracts in this report

Cite AsGet BibTex

George Biros, Andreas Mang, Björn H. Menze, and Miriam Schulte. Inverse Biophysical Modeling and Machine Learning in Personalized Oncology (Dagstuhl Seminar 23022). In Dagstuhl Reports, Volume 13, Issue 1, pp. 36-67, Schloss Dagstuhl - Leibniz-Zentrum für Informatik (2023)


This report documents the program and the outcomes of Dagstuhl Seminar 23022 "Inverse Biophysical Modeling and Machine Learning in Personalized Oncology". This seminar brought together leading experts in mathematical, computational, and medical imaging sciences with research interests in data science, scientific machine learning, modeling and numerical simulation, optimization, and statistical and deterministic inversion, and image analysis with applications in medical imaging, and, in particular, oncology. A central theme of the seminar was the integration of data-driven methods with model-driven approaches for predictive modeling. The seminar had several main thrusts including design and analysis of novel mathematical models, recent developments in medical imaging, machine learning in the context data analytics and data-driven model prediction, predictive computational modeling through (statistical) inversion, integration of machine learning with model-based priors and use of these methods to aid decision-making. We discussed these topics through the lens of foundational algorithmic complications and mathematical and computational challenges. The participants explored how advances in the applied sciences (e.g., data analytics, medical imaging, or radiomics) can aid us to tackle challenges in the application domain. We also discussed the significant challenges associated with the validation of the proposed methodology, and a lack of reproducibility due to the absence of standard protocols for validation of data- and model-driven methods by translational research groups.

Subject Classification

ACM Subject Classification
  • Applied computing → Imaging
  • Applied computing → Life and medical sciences
  • Computing methodologies → Machine learning algorithms
  • Computing methodologies → Machine learning approaches
  • Mathematics of computing → Mathematical optimization
  • Mathematics of computing → Mathematical software performance
  • Mathematics of computing → Numerical analysis
  • Mathematics of computing → Solvers
  • Bayesian inverse problems
  • image segmentation
  • inverse problems
  • machine learning
  • medical image analysis
  • parallel computing
  • tumor growth simulation and modeling


  • Access Statistics
  • Total Accesses (updated on a weekly basis)
    PDF Downloads
Questions / Remarks / Feedback

Feedback for Dagstuhl Publishing

Thanks for your feedback!

Feedback submitted

Could not send message

Please try again later or send an E-mail