Description

To evaluate the robustness of a treatment, cohort studies are often employed in clinical practice for cancer patients. This means that a large number of patients is followed through the treatment and the effects of the therapeutic strategies are modeled on the basis of imaging information and clinical data. In chemotherapy, mathematical models (ODEs) that describe the tumor response to chemotherapy are an additional source of information that provides significant insights for therapy optimization and outcome.

Tasks

The goal of this project is to provide a visual analytics strategy that supports clinical experts working on the optimization of chemotherapy for breast cancer patients by bridging insights from medical images to clinical data and to mathematical models of tumor response. The developed approach should enable the user to analyze the existing cohort of patients, explore their characteristics with regard to treatment and clinical outcomes, and relate these findings to insights from established mathematical models for tumor response (e.g., for model improvement or for model confirmation).

Requirements

  • Interest and knowledge in biomedical visualization and in visual analytics.
  • Knowledge and experience with machine learning.
  • Prior knowledge of differential equations.
  • Good programming skills.
  • Creativity and enthusiasm.

Environment

To be discussed (depending on the background of the student).

References

[1] https://doi.org/10.1109/tvcg.2021.3114810

[2] https://doi.org/10.1016/j.cag.2021.04.010

[3] https://www.frontiersin.org/articles/10.3389/fphys.2019.00616/full

[4] https://www.sciencedirect.com/science/article/pii/S240589632030923X

Responsible

For more information please contact Renata Raidou.

Details

Type

Bachelor Thesis
Master Thesis

Persons

1