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

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Tang, Zhihao, Li, Chaozhuo, Zhang, Litian, Zhang, Xi
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912415968395264
author Tang, Zhihao
Li, Chaozhuo
Zhang, Litian
Zhang, Xi
author_facet Tang, Zhihao
Li, Chaozhuo
Zhang, Litian
Zhang, Xi
contents 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%.
format Preprint
id arxiv_https___arxiv_org_abs_2506_05428
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Diffusion with a Linguistic Compass: Steering the Generation of Clinically Plausible Future sMRI Representations for Early MCI Conversion Prediction
Tang, Zhihao
Li, Chaozhuo
Zhang, Litian
Zhang, Xi
Machine Learning
Artificial Intelligence
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%.
title Diffusion with a Linguistic Compass: Steering the Generation of Clinically Plausible Future sMRI Representations for Early MCI Conversion Prediction
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2506.05428