Get Started
Home
Topics
Search
Library
Research questionHow can longitudinal MRI models forecast neurodegenerative progression without confusing stable anatomy or noise with disease change?Longitudinal scans contain extensive stable, patient-specific anatomy, while disease-related changes are subtle and mixed with sample-specific variation. A forecasting model must identify genuine progression without generating spurious changes across the brain volume.
AI
Computer Vision
Health
Image & Video Processing
Machine Learning
Research Paper
Latest papersRecent research connected to this question, newest first.Progression as Latent Drift: Generative Forecasting of Slow-Evolving PathologiesThe source studies generative neuro-forecasting for slow-evolving neurodegenerative disease using longitudinal 3D brain MRI. It proposes Latent Drift, which models progression in a compressed change representation and applies finite scalar quantization; experiments compare it with diffusion and autoregressive transformer baselines using generative-fidelity and clinically relevant metrics. The source does not specify the disease cohort, scan interval, or deployment setting.research paper · Sep 2, 2026
Related questions
How can automated brain-MRI reporting compare longitudinal studies to describe subtle, distributed interval changes?How can MRI-based cortical surface analysis localize nonuniform differences between clinical groups?How can vision-language models reliably report clinically meaningful changes between serial CT scans?How can 3D brain MRI inpainting reconstruct healthy tissue in pathological regions without changing observed anatomy?