Regensburg 2022 – scientific programme
Parts | Days | Selection | Search | Updates | Downloads | Help
BP: Fachverband Biologische Physik
BP 7: Poster 1
BP 7.26: Poster
Monday, September 5, 2022, 18:00–20:00, P1
Machine Learning based parametrization of tumor simulation — •Julian Herold1, Eric Behle2, and Alexander Schug2 — 1Karlsruhe Institute of Technology (KIT), Kaiserstraße 12, 76131 Karlsruhe, Germany — 2JSC, Jülich Research Centre, Wilhelm- Johnen-Straße, 52428 Jülich, Germany
Despite decades of substantial research, cancer remains a ubiquitous scourge in the industrialized world. Effective treatments require a thorough understanding of macroscopic cancerous tumor growth out of individual cells in the tissue and microenvironment context.
Here, we aim to introduce the critical scale-bridging link between clinical imaging and quantitative experiments focusing on small clusters of cancerous cells by applying machine learning to drive model building between them. We deploy Cells in Silico (CiS), a high performance framework for large-scale tissue modeling developed by us. Based on both a cellular potts model and an agent-based layer, CiS is capable of accurately representing many physical and biological properties, such as individual cell shapes, cell division, cell motility etc.
The strong representational capacity of our model comes with the need to adjust a large number of parameters according to experimental findings. We present a generalized approach to optimize these parameters which allows the use of different sources of experimental data.
One major hurdle to achieve this goal is finding appropriate objective functions. To overcome this we implemented a variation of the Particle Swarm Optimization algorithm which learns the objective function during the optimization process.