Treatment-Conditioned Diffusion for Forecasting Neurodegenerative Disease Progression
It addresses the need for high-fidelity longitudinal neuroimaging prediction for Parkinson's disease patients, enabling personalized therapeutic intervention.
The paper introduces a treatment-conditioned diffusion framework for forecasting neurodegenerative disease progression, achieving 14.0% lower MSE, 7.2% lower MAE, and 4.9% higher SSIM compared to baselines.
Forecasting the progression of neurodegenerative diseases, such as Parkinson's disease, is essential for effective long-term planning and personalized therapeutic intervention. Existing systems typically produce scalar clinical scores that ignore the rich structure of longitudinal neuroimaging, while traditional generative approaches suffer from a loss of anatomical details and blurring subtle progression patterns. To address this, we introduce a novel treatment-conditioned diffusion framework that predicts high-fidelity future brain states by conditioning the generative process on patients' screening DaTscan images and levodopa equivalent daily dose over one year. The pipeline uses a Transformer-based encoder to represent non-linear, time-dependent pharmacological dynamics and optimizes generation through a multi-weight region-of-interest mask that focuses on biologically critical areas. Experimental evaluation shows that our framework maintains sharp anatomical boundaries and significantly improves clinical fidelity relative to the baseline, achieving 14.0% lower MSE, 7.2% lower MAE, and 4.9% higher SSIM.