Latent Diffusion Model Forecasts Brain MRI Progression in Alzheimer's Patients
Start here
A multimodal-conditioned latent diffusion model, MC-LDM, generates patient-specific spatiotemporal brain MRI forecasts, predicting how brain anatomy will change over time. Conditioned on MRI, tau-PET, CDR scores and APOE4 status during training, it needs only baseline MRI, APOE4 and patient metadata at inference. Trained on 1,355 visits from 852 subjects in ADNI, it reduced average regional volumetric error by 18% against the second-best baseline on an independent test set of 664 visits. The approach could support disease progression modeling and treatment monitoring in Alzheimer's disease, though clinical validation beyond ADNI data is still open.
Written by a model from the reports · updated 4 hours ago
Coverage timeline
Follow the coverage to see the different angles.
- arxiv.orgMultimodal-Conditioned Latent Diffusion Models for Spatiotemporal Brain MRI Forecasting
MC-LDM performs patient-specific spatiotemporal brain MRI forecasting, reducing average regional volumetric MAE by 18% versus the second-best baseline on an independent test set of 664 visits. The latent diffusion model is trained with MRI, tau-PET, CDR and APOE4, but at inference uses only baseline MRI, APOE4 and patient metadata. It was trained on 1,355 visits from 852 subjects in ADNI.
Coverage and heat for this story
Reports so far 1·Heat now 9·Peak heat 10 (Oct 20 20:00)·Reports, 24h +1
Two panels, same clock (pointer stays in sync): top is cumulative editorial reports — only rises; last point = All reports; slope = new reports that hour. Bottom is Live-board heatIndex — 7-day participants with a 24-hour half-life, so it can fall when talk cools.