Adaptive Clinical-Aware Latent Diffusion for Multimodal Brain Image Generation and Missing Modality Imputation
2026-03-10 • Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionArtificial Intelligence
AI summaryⓘ
The authors created ACADiff, a tool that fills in missing brain scans to help diagnose Alzheimer's disease. It uses a special technique that gradually cleans up the data and pays attention to any available brain images and patient information. Their method works well even when up to 80% of the imaging data is missing, doing better than other existing tools. They tested it on a real dataset and shared their code for others to use.
Alzheimer's diseasemultimodal neuroimagingbrain imaging modalitiesdiffusion modelssMRIFDG-PETAV45-PETclinical metadatadata synthesisdiagnostic performance
Authors
Rong Zhou, Houliang Zhou, Yao Su, Brian Y. Chen, Yu Zhang, Lifang He, Alzheimer's Disease Neuroimaging Initiative
Abstract
Multimodal neuroimaging provides complementary insights for Alzheimer's disease diagnosis, yet clinical datasets frequently suffer from missing modalities. We propose ACADiff, a framework that synthesizes missing brain imaging modalities through adaptive clinical-aware diffusion. ACADiff learns mappings between incomplete multimodal observations and target modalities by progressively denoising latent representations while attending to available imaging data and clinical metadata. The framework employs adaptive fusion that dynamically reconfigures based on input availability, coupled with semantic clinical guidance via GPT-4o-encoded prompts. Three specialized generators enable bidirectional synthesis among sMRI, FDG-PET, and AV45-PET. Evaluated on ADNI subjects, ACADiff achieves superior generation quality and maintains robust diagnostic performance even under extreme 80\% missing scenarios, outperforming all existing baselines. To promote reproducibility, code is available at https://github.com/rongzhou7/ACADiff