Spatio-Temporal Conditional Diffusion Models for Forecasting Future Multiple Sclerosis Lesion Masks Conditioned on Treatments
This work addresses personalized medicine for Multiple Sclerosis patients by enabling treatment-aware lesion forecasting, though it appears incremental as it builds on existing diffusion model techniques for a specific medical application.
The authors tackled the problem of forecasting future Multiple Sclerosis lesion masks conditioned on treatments by introducing a spatio-temporal diffusion model that incorporates multi-modal patient data, achieving accurate predictions of new and enlarging T2 lesion masks across six different treatments on a dataset of 2131 patient 3D MRIs.
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.