TumorTwin: A python framework for patient-specific digital twins in oncology
🤖 AI Summary
Current cancer digital twins lack generality and reusability. Method: We propose the first modular, patient-specific digital twin framework for oncology, featuring a novel cross-disease–compatible standardized patient data structure enabling dynamic modeling of image-guided tumor growth and radiotherapy response; a loosely coupled modular architecture that seamlessly integrates heterogeneous clinical data, multiscale biophysical models, diverse numerical solvers, and optimization algorithms; and CPU/GPU-coaccelerated forward simulation and gradient computation. The framework innovatively incorporates uncertainty quantification and online model recalibration to support clinical decision-making. Contribution/Results: Validated on a high-grade glioma radiotherapy simulation dataset, the framework significantly improves prototyping efficiency of digital twins and enables systematic evaluation and deployment across multiple cancer types, models, and therapies.
Application Category
📝 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.
Problem
Research questions and friction points this paper is trying to address.
Develops a Python framework for patient-specific cancer digital twins
Enables dynamic model re-calibration and treatment optimization
Supports modular testing of oncology models and algorithms
Innovation
Methods, ideas, or system contributions that make the work stand out.
Modular Python framework for oncology digital twins
Adaptable patient-data structure for various diseases
CPU/GPU-parallelized model solves and gradients
🔎 Similar Papers
2024-09-19arXiv.orgCitations: 1
