10 March 2017 Statistical aspects of radiogenomics: can radiogenomics models be used to aid prediction of outcomes in cancer patients?
Author Affiliations +
Abstract
Radiogenomics is a new direction in cancer research that aims at identifying the relationship between tumor genomics and its appearance in imaging (i.e. its radiophenotype). Recent years brought multiple radiogenomic discoveries in brain, breast, lung, and other cancers. With development of this new field we believe that it important to investigate in which setting radiogenomics could be useful to better direct research effort. One of the general applications of radiogenomics is to generate imaging-based models for prediction of outcomes and doing so through modeling the relationship between imaging and genomics and the relationship between genomics and outcomes. We believe that this is an important potential application of radiogenomic as it could advance imaging-based precision medicine. We show a preliminary simulation study evaluation whether such approach results in improved models. We investigate different setting in terms of the strengths of the radiogenomic relationship, prognostic power of the imaging and genomic descriptors, and availability and quality of data. Our experiments indicated that the following parameters have impact on usefulness of the radiogenomic approach: predictive power of genomic features and imaging features, strength of the radiogenomic relationship as well as number and follow up time for the genomic data. Overall, we found that there are some situations in which radiogenomics approach is beneficial but only when the radiogenomic relationship is strong and low number of imaging cases with outcomes data are available.
© (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Boya Ren, Maciej A. Mazurowski, "Statistical aspects of radiogenomics: can radiogenomics models be used to aid prediction of outcomes in cancer patients?", Proc. SPIE 10136, Medical Imaging 2017: Image Perception, Observer Performance, and Technology Assessment, 101361O (10 March 2017); doi: 10.1117/12.2255898; https://doi.org/10.1117/12.2255898
PROCEEDINGS
6 PAGES


SHARE
Back to Top