Journal article
Michael G. Kapteyn, Anirban Chaudhuri, Ernesto A. B. F. Lima, G. Pash, Rafael Bravo, Karen Willcox, Thomas E. Yankeelov, D. Hormuth
arXiv.org, 2025
arXiv.org, 2025
Semantic Scholar
ArXiv
DBLP
DOI
PubMed
Cite
Cite
APA
Click to copy
Kapteyn, M. G., Chaudhuri, A., Lima, E. A. B. F., Pash, G., Bravo, R., Willcox, K., … Hormuth, D. (2025). TumorTwin: A python framework for patient-specific digital twins in oncology. ArXiv.org.
Chicago/Turabian
Click to copy
Kapteyn, Michael G., Anirban Chaudhuri, Ernesto A. B. F. Lima, G. Pash, Rafael Bravo, Karen Willcox, Thomas E. Yankeelov, and D. Hormuth. “TumorTwin: A Python Framework for Patient-Specific Digital Twins in Oncology.” arXiv.org (2025).
MLA
Click to copy
Kapteyn, Michael G., et al. “TumorTwin: A Python Framework for Patient-Specific Digital Twins in Oncology.” ArXiv.org, 2025.
BibTeX Click to copy
@article{michael2025a,
title = {TumorTwin: A python framework for patient-specific digital twins in oncology},
year = {2025},
journal = {arXiv.org},
author = {Kapteyn, Michael G. and Chaudhuri, Anirban and Lima, Ernesto A. B. F. and Pash, G. and Bravo, Rafael and Willcox, Karen and Yankeelov, Thomas E. and Hormuth, D.}
}
Abstract
BACKGROUND Advances in the theory and methods of computational oncology have enabled accurate characterization and prediction of tumor growth and treatment response on a patient-specific basis. This capability can be integrated into a digital twin framework in which bi-directional data-flow between the physical tumor and the digital tumor facilitate dynamic model re-calibration, uncertainty quantification, and clinical decision-support via recommendation of optimal therapeutic interventions. However, many digital twin frameworks rely on bespoke implementations tailored to each disease site, modeling choice, and algorithmic implementation.
FINDINGS We present TumorTwin, a modular software framework for initializing, updating, and leveraging patient-specific cancer tumor digital twins. TumorTwin is publicly available as a Python package, with associated documentation, datasets, and tutorials. Novel contributions include the development of a patient-data structure adaptable to different disease sites, a modular architecture to enable the composition of different data, model, solver, and optimization objects, and CPU- or GPU-parallelized implementations of forward model solves and gradient computations. We demonstrate the functionality of TumorTwin via an in silico dataset of high-grade glioma growth and response to radiation therapy.
CONCLUSIONS The TumorTwin framework enables rapid prototyping and testing of image-guided oncology digital twins. This allows researchers to systematically investigate different models, algorithms, disease sites, or treatment decisions while leveraging robust numerical and computational infrastructure.