Spatio-Temporal Conditional Diffusion Models for Forecasting Future Multiple Sclerosis Lesion Masks Conditioned on Treatments

TL;DR

This paper introduces a novel treatment-aware spatio-temporal diffusion model that predicts future lesion masks in Multiple Sclerosis patients using multi-modal data, enabling improved prognosis and treatment assessment.

Contribution

It presents the first spatio-temporal diffusion model conditioned on treatments for MS lesion forecasting, integrating multi-modal data for accurate future lesion prediction.

Findings

Accurately predicts future lesion masks across multiple treatments.

Demonstrates potential for clinical applications like lesion counting and activity classification.

Generates counterfactual lesion masks for different treatment efficacies.

Abstract

Image-based personalized medicine has the potential to transform healthcare, particularly for diseases that exhibit heterogeneous progression such as Multiple Sclerosis (MS). In this work, we introduce the first treatment-aware spatio-temporal diffusion model that is able to generate future masks demonstrating lesion evolution in MS. Our voxel-space approach incorporates multi-modal patient data, including MRI and treatment information, to forecast new and enlarging T2 (NET2) lesion masks at a future time point. Extensive experiments on a multi-centre dataset of 2131 patient 3D MRIs from randomized clinical trials for relapsing-remitting MS demonstrate that our generative model is able to accurately predict NET2 lesion masks for patients across six different treatments. Moreover, we demonstrate our model has the potential for real-world clinical applications through downstream tasks such as future lesion count and location estimation, binary lesion activity classification, and generating counterfactual future NET2 masks for several treatments with different efficacies. This work highlights the potential of causal, image-based generative models as powerful tools for advancing data-driven prognostics in MS.