Open-source image-based digital twins for oncology

Development of open source, Python-based, digital twin codebase for image-based modeling. https://github.com/OncologyModelingGroup/TumorTwin/

Digital twins for virtual clinical trials

Clinical trials are inefficient and costly. This project builds models of virtual patient populations to rapidly test countless intervention strategies in silico, aiming to fundamentally improve the design, efficiency, and success of future trials.

Image-based models of response to radiotherapy

The goal of this project is the development of image-based models to enable patient-specific digital twins. These digital twins are then applied to a range of disease settings including: head and neck cancer, sarcomas, and high and low grade gliomas.

Forecasting response of high-grade glioma patients to radiation therapy

The focus of this project is to translate our efforts at the pre-clinical level to the clinical setting. The longterm vision is to improve patient outcomes through the use of accurate predictive models personalized for each patient

Image-driven models of tumor growth in the pre-clinical setting

While not perfect, the pre-clinical setting is a great area to explore optimal ways to incorporate different imaging (MRI, PET, microscopy, etc) with mathematical models of tumor growth and response.

Repeatable & reproducible cancer imaging methods

Repeatable and reproducible approaches for acquiring and analyzing images is crucial for clinical decision making and for inclusion in mathematical models.