SimBioSys TumorScope: Spatio-temporal modeling of the tumor microenvironment to predict chemotherapeutic response.

Background: One of the most important sources of variability affecting each patient’s response to neoadjuvant chemotherapy (NACT) is drug and nutrient perfusion, The SimBioSys TumorScope is a computational decision-support system that is designed to predict the flow of drugs and nutrients throughout the tumor microenvironment, and the subsequent response of the tumor to treatment. By enabling healthcare providers to simulate a range of different standard-of-care treatment regimens in a realistic 3D model of each patient’s tumor, providers can predict which treatments are most effective, and provide the best possible care for their patients.

Methods: SimBioSys TumorScope implements a multi-scale simulation technology that couples several biophysical and biochemical models in order to predict how individual patients’ tumors respond to NACT. The simulations explicitly track the 3D morphology of the tumor and surrounding tissues (based on MRI images), as well as the concentrations of key nutrients and drugs as they change over time. At each location within the 3D model, these concentrations are used to predict cell growth and death rates. As different regions of the tumor grow or die, its macroscopic shape changes.

Results: SimBioSys TumorScope was retrospectively applied to over 300 breast cancer patients that received NACT. Simulations were initialized with pre-treatment MRI data, and run through the entirety of each patient’s specified treatment regimen. Predicted changes in tumor volume and longest dimension were then compared against measured values at several time-points after initiation of therapy, yielding Pearson correlations of over 0.93 for both. Work is underway to extend the technology to lung tumors; early results show very different metabolic behaviors from those of breast tumors, and significantly less response to treatment overall.

Conclusions: Through accurate spatio-temporal modeling of drug and nutrient perfusion, metabolic behavior, and the physico-chemical interactions that arise between tissues, the SimBioSys TumorScope for Breast Cancer can accurately predict the response of patients treated with NACT.

View the full publication and poster here.