AUTHOR=Ghosh Debashis , Mastej Emily , Jain Rajan , Choi Yoon Seong TITLE=Causal Inference in Radiomics: Framework, Mechanisms, and Algorithms JOURNAL=Frontiers in Neuroscience VOLUME=16 YEAR=2022 URL=https://www.frontiersin.org/journals/neuroscience/articles/10.3389/fnins.2022.884708 DOI=10.3389/fnins.2022.884708 ISSN=1662-453X ABSTRACT=

The widespread use of machine learning algorithms in radiomics has led to a proliferation of flexible prognostic models for clinical outcomes. However, a limitation of these techniques is their black-box nature, which prevents the ability for increased mechanistic phenomenological understanding. In this article, we develop an inferential framework for estimating causal effects with radiomics data. A new challenge is that the exposure of interest is latent so that new estimation procedures are needed. We leverage a multivariate version of partial least squares for causal effect estimation. The methodology is illustrated with applications to two radiomics datasets, one in osteosarcoma and one in glioblastoma.