以语言罗盘引导的扩散：为早期 MCI 转化预测生成临床合理的未来 sMRI 表征
Diffusion with a Linguistic Compass: Steering the Generation of Clinically Plausible Future sMRI Representations for Early MCI Conversion Prediction
把扩散模型的潜空间轨迹外推与 LLM 打分引导结合，用单次基线扫描合成未来 sMRI 表征；这套「潜变量外推 + 语言模型合理性筛选」的采样策略可迁移到任何需要从单帧预测时序演变的医学或视频表征任务。
原文依据 synthesizes clinically plausible future sMRI representations directly from baseline data
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论轻度认知障碍（MCI）转化的早期预测受制于即时性与准确性之间的权衡：即时性指仅凭单次基线 sMRI 做出快速预测，准确性则指利用纵向扫描捕捉疾病进展。我们提出 MCI-Diff，一个基于扩散的框架，可直接从基线数据合成临床合理的未来 sMRI 表征，从而同时实现实时风险评估与高预测性能。首先，多任务序列重建策略在插值与外推任务上训练共享去噪网络，以应对不规则的随访采样并学习稳健的潜变量轨迹。其次，引入由大语言模型驱动的「语言罗盘」进行临床合理性采样：生成的特征候选被量化、词元化，并由一个以预期结构生物标志物为条件的微调语言模型打分，从而引导自回归生成朝向真实的疾病模式。在 ADNI 与 AIBL 队列上的实验表明，MCI-Diff 优于最优基线，将早期转化准确率提升 5-12%。
英文原文摘要 1108 字符
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%.