A Structural Causal Model for MR Images of Multiple Sclerosis

Precision medicine involves answering counterfactual questions such as “Would this patient respond better to treatment A or B?” These types of are causal in nature and require the tools inference be answered, e.g., with a structural model (SCM). In work, we develop an SCM that models interaction between demographic information, disease covariates, magnetic resonance (MR) images brain for people multiple sclerosis. Inference generates show what MR image would look like if covariates changed. can used modeling progression downstream processing tasks where controlling confounders is necessary.