Diffusion with a Linguistic Compass: Steering the Generation of Clinically Plausible Future sMRI Representations for Early MCI Conversion Prediction

2025/06/05 by Zhihao Tang, Tang, Zhihao, Chaozhuo Li +5
Computer Science · Medicine · Neuroscience · #Artificial Intelligence (cs.AI) #Dementia and Cognitive Impairment Research #FOS: Computer and information sciences #Functional Brain Connectivity Studies #Machine Learning (cs.LG) #Machine Learning in Healthcare

paper · pdf · doi:10.48550/arxiv.2506.05428

openalex publication_date 2025/06/05 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Early prediction of Mild Cognitive Impairment (MCI) conversion is hampered by a trade-off between immediacy--making fast predictions from a single baseline sMRI--and accuracy--leveraging longitudinal scans to capture disease progression. We propose MCI-Diff, a diffusion-based framework that synthesizes clinically plausible future sMRI representations directly from baseline data, achieving both real-time risk assessment and high predictive performance. First, a multi-task sequence reconstruction strategy trains a shared denoising network on interpolation and extrapolation tasks to handle irregular follow-up sampling and learn robust latent trajectories. Second, an LLM-driven "linguistic compass" is introduced for clinical plausibility sampling: generated feature candidates are quantized, tokenized, and scored by a fine-tuned language model conditioned on expected structural biomarkers, guiding autoregressive generation toward realistic disease patterns. Experiments on ADNI and AIBL cohorts show that MCI-Diff outperforms state-of-the-art baselines, improving early conversion accuracy by 5-12%.

Citations

• VGG-TSwinformer: Transformer-based deep learning model for early Alzheimer’s disease prediction
• Diffusion Models in Vision: A Survey
• Deep learning for Alzheimer's disease diagnosis: A survey
• Generative Adversarial Networks
• Going deep into schizophrenia with artificial intelligence
• Dual Attention Multi-Instance Deep Learning for Alzheimer’s Disease Diagnosis With Structural MRI
• Denoising Diffusion Probabilistic Models
• Hierarchical Fully Convolutional Network for Joint Atrophy Localization and Alzheimer's Disease Diagnosis Using Structural MRI
• Attention Is All You Need
• Ladder Variational Autoencoders

Related

• Predicting conversion of mild cognitive impairment to Alzheimer's disease
• Pretraining Transformer-Based Models on Diffusion-Generated Synthetic Graphs for Alzheimer's Disease Prediction
• Diffusion Models for conditional MRI generation
• Simulation of virtual cohorts increases predictive accuracy of cognitive decline in MCI subjects
• Conditional Score-Based Diffusion Model for Cortical Thickness Trajectory Prediction