Visual Analytics to Support Correlative Exploration and Sensemaking in Radiogenomics Analysis (DAAV)

Radiogenomics refers to the combined study of imaging-derived features, called radiomics, with gene mutation data, called genomics. Radiomic features are extracted from medical imaging data that show tumor characteristics as indicators of metabolic activity or metastasis. Genomic data decode functional information of Deoxyribonucleic Acid (DNA) or Ribonucleic acid (RNA) sequences. The analysis of radiogenomics with respect to clinical data, such as the age or Body Mass Index (BMI) of patients, is currently being investigated as a potential enabler of prostate cancer risk stratification. In this process, each patient is assigned a particular risk status that supports a better understanding of the tumor aggressiveness and the indication of a better treatment process. However, the size, heterogeneity, and complexity of radiogenomic data make the analysis of the available information space tedious for domain experts and hinder the exploration and sensemaking of patient information. Visual analytics combines analytical reasoning with interactive visual interfaces that allow the user to gain insight into complex data and make effective decisions. In the context of radiogenomics analysis with regard to clinical data, visual analytics approaches are not popular yet, but they offer promising directions. We aspire to provide visual analytics strategies that support the correlative exploration and analysis of radiogenomic data in a large cohort of prostate cancer patients. Guiding the user through the exploratory process of the data is anticipated to further support data sensemaking.