ESTRO 2024 - Abstract Book

S4668

Physics - Optimisation, algorithms and applications for ion beam treatment planning

ESTR0 2024

Fig2: Cell survival for a 230 MeV proton SOBP; orange experimental data from [10], blue ML predictions

Conclusion:

In the 'standard' configuration, CELL allows the prediction of cell survival based on theoretical models, if the specific cellular parameters are available. For both of the implemented models, these parameters are currently only available for the V79 cell line. Nevertheless, users have the flexibility to manually input parameters when available, or they can choose to use an alternative theoretical model.

The introduction of ML partially addresses this limitation by expanding the range of cell types for which survival predictions can be computed.

CELL is a user-friendly graphical interface designed for cell survival estimation. This program offers versatility, ease of use, and a comprehensive set of tools within a single package, accelerating the learning curves of new users.

Keywords: Cell Survival, Machine Learning, Monte Carlo

References:

1) McMahon, S. J. (2018). The linear quadratic model: usage, interpretation and challenges. Physics in Medicine & Biology, 64(1):01TR01.

2) Chatzipapas, K. P., Papadimitroulas, P., Emfietzoglou, D., Kalospyros, S. A., Hada, M., Georgakilas, A. G., and Kagadis, G. C. (2020). Ionizing radiation and complex dna damage: quantifying the radiobiological damage using monte carlo simulations. Cancers, 12(4):799.

3) Semenenko, V. and Stewart, R. (2006). Fast monte carlo simulation of dna damage formed by electrons and light ions. Physics in Medicine & Biology, 51(7):1693.