Lessons Learnt from Developing Visual Analytics Applications for Adaptive Prostate Cancer Radiotherapy

Renata Raidou, Katarína Furmanová, Nicolas Grossmann, Oscar Casares-Magaz, Vitali Moiseenko, John P. Einck, Meister Eduard Gröller, Ludvig Paul Muren
Lessons Learnt from Developing Visual Analytics Applications for Adaptive Prostate Cancer Radiotherapy
In The Gap between Visualization Research and Visualization Software (VisGap) (2020), pages 1-8. May 2020.

Information

Abstract

In radiotherapy (RT), changes in patient anatomy throughout the treatment period might lead to deviations between planned and delivered dose, resulting in inadequate tumor coverage and/or overradiation of healthy tissues. Adapting the treatment to account for anatomical changes is anticipated to enable higher precision and less toxicity to healthy tissues. Corresponding tools for the in-depth exploration and analysis of available clinical cohort data were not available before our work. In this paper, we discuss our on-going process of introducing visual analytics to the domain of adaptive RT for prostate cancer. This has been done through the design of three visual analytics applications, built for clinical researchers working on the deployment of robust RT treatment strategies. We focus on describing our iterative design process, and we discuss the lessons learnt from our fruitful collaboration with clinical domain experts and industry, interested in integrating our prototypes into their workflow.

Additional Files and Images

Weblinks

No further information available.

BibTeX

@inproceedings{raidou_visgap2020,
  title =      "Lessons Learnt from Developing Visual Analytics Applications
               for Adaptive Prostate Cancer Radiotherapy",
  author =     "Renata Raidou and Katar\'{i}na  Furmanov\'{a} and Nicolas
               Grossmann and Oscar Casares-Magaz and Vitali Moiseenko and
               John P. Einck and Meister Eduard Gr\"{o}ller and Ludvig Paul
               Muren",
  year =       "2020",
  abstract =   "In radiotherapy (RT), changes in patient anatomy throughout
               the treatment period might lead to deviations between
               planned and delivered dose, resulting in inadequate tumor
               coverage and/or overradiation of healthy tissues. Adapting
               the treatment to account for anatomical changes is
               anticipated to enable higher precision and less toxicity to
               healthy tissues. Corresponding tools for the in-depth
               exploration and analysis of available clinical cohort data
               were not available before our work. In this paper, we
               discuss our on-going process of introducing visual analytics
               to the domain of adaptive RT for prostate cancer. This has
               been done through the design of three visual analytics
               applications, built for clinical researchers working on the
               deployment of robust RT treatment strategies. We focus on
               describing our iterative design process, and we discuss the
               lessons learnt from our fruitful collaboration with clinical
               domain experts and industry, interested in integrating our
               prototypes into their workflow.",
  month =      may,
  booktitle =  "The Gap between Visualization Research and Visualization
               Software (VisGap) (2020)",
  event =      "EGEV2020 - VisGap Workshop",
  pages =      "1--8",
  keywords =   "Visual Analytics, Life and Medical Sciences",
  URL =        "https://www.cg.tuwien.ac.at/research/publications/2020/raidou_visgap2020/",
}