Prostate cancer radiotherapy requires meticulous planning prior to treatment, where the treatment plan is optimized with organ delineations on a pre-treatment scan of the patient. Follow-up analysis in cancer radiotherapy has been inconclusive in the past. In this project, we would like to investigate appropriate visual analytics solutions that could support follow-up studies (i.e., how a patient treatment “evolves” through time).

Note: please mind that there is another topic (link) on follow-up studies support that focuses more on visualization (more about image analysis and visualization, no machine learning).


Design appropriate visual analytics strategies to support the analysis of follow-up studies in cancer radiotherapy. This should be done in a retrospective (i.e., analysis of past patients) and in a prospective (i.e., predictive analysis of new patients) manner.


  • Interest and knowledge in biomedical visualization and visual analytics.
  • Interest and knowledge in machine learning.
  • Some experience with machine learning frameworks.
  • Good programming skills.
  • Creativity and enthusiasm.


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



[3] Mirzargar, Mahsa, Ross T. Whitaker, and Robert M. Kirby. "Curve boxplot: Generalization of boxplot for ensembles of curves." IEEE transactions on visualization and computer graphics 20, no. 12 (2014): 2654-2663.
[4] Ferstl, Florian, Mathias Kanzler, Marc Rautenhaus, and Rüdiger Westermann. "Time-hierarchical clustering and visualization of weather forecast ensembles." IEEE transactions on visualization and computer graphics 23, no. 1 (2016): 831-840.



For more information please contact Renata Raidou.



Master Thesis