A Structural Causal Model for MR Images of Multiple Sclerosis

TL;DR

This paper develops a structural causal model to generate counterfactual MR images of the brain in multiple sclerosis patients, enabling better understanding of disease progression and treatment effects.

Contribution

It introduces a novel SCM that links demographic, disease, and imaging data to produce counterfactual brain images for MS patients.

Findings

Generated counterfactual MR images show plausible changes with covariate modifications.

The model aids in understanding disease progression and treatment response.

Counterfactual images can improve image processing and causal inference in medical imaging.

Abstract

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