Diffusion with a Linguistic Compass: Steering the Generation of Clinically Plausible Future sMRI Representations for Early MCI Conversion Prediction
This work addresses early prediction of MCI conversion for clinical applications, offering a method that balances real-time assessment with high accuracy, though it is incremental as it builds on existing diffusion and language model techniques.
The paper tackles the trade-off between immediacy and accuracy in predicting Mild Cognitive Impairment (MCI) conversion by proposing MCI-Diff, a diffusion-based framework that synthesizes clinically plausible future sMRI representations from baseline data, achieving improved early conversion accuracy by 5-12% compared to state-of-the-art baselines.
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%.