发表机构
Zhejiang University; The Hong Kong Polytechnic University; IROOTECH TECHNOLOGY; Wolf 1069 b Lab, Sany Group（浙江大学; 香港理工大学; IROOTECH技术; Wolf 1069 b实验室，三一集团）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对缓慢演变神经退行性疾病未来解剖结构预测难题，提出潜在漂移的渐进生成框架，在压缩语义表示中学习变化，结合有限标量量化抑制干扰波动，实验表明该方法在神经预测上优于基线。
AI 中文摘要
预测缓慢演变的神经退行性疾病的未来解剖结构可以实现更早、更有针对性的干预并改善临床试验设计，但由于纵向MRI中的真实进展信号很微弱，这仍然具有挑战性。在这种低信号状态下，直接转移现代生成序列模型是不可靠的：训练受稳定的基线解剖结构主导，并受到密集的、特定样本的干扰变化的影响。我们首先通过两种模式提供了一种理论分析来解释这些失败。当优化朝着再现当前解剖结构驱动时，就会发生身份崩溃，这会阻止模型学习微弱的时间变化。当标准平滑网络无法将局部生物漂移与普遍噪声分开时，就会出现连续插值陷阱，这会导致虚假变化在整个体积中扩散。为了解决这两个问题，我们提出了潜在漂移，这是一个渐进的生成框架，它在压缩的语义表示中学习变化，而不是合成全分辨率解剖结构。这种设计从预测目标中消除了像素级身份，并将模型能力集中在与进展相关的动态上。我们进一步将有限标量量化应用于学习到的变化表示，这抑制了小的高频干扰波动，同时保留了一致的结构漂移。对纵向3D脑MRI的实验表明，潜在漂移在生成保真度和临床相关评估指标方面比扩散和自回归变压器基线改进了患者特定的神经预测。项目页面：\href{ this https URL }{ this https URL }。
英文摘要
Forecasting the future anatomy of slow-evolving neurodegenerative diseases could enable earlier, more targeted intervention and improve clinical trial design, but it remains challenging because true progression signals are subtle in longitudinal MRI. In this low-signal regime, transferring modern generative sequence models directly is unreliable: training is dominated by stable baseline anatomy and confounded by dense, sample-specific nuisance variation. We first provide a theoretical analysis that explains these failures through two modes. Identity collapse occurs when optimization is driven toward reproducing the current anatomy, which prevents the model from learning faint temporal change. The continuous interpolation trap arises when standard smooth networks cannot separate localized biological drift from pervasive noise, which leads to spurious changes that diffuse across the volume. To address both issues, we propose Latent Drift, a progressive generative framework that learns change in a compressed semantic representation rather than synthesizing full-resolution anatomy. This design removes pixel-level identity from the prediction target and concentrates model capacity on progression-relevant dynamics. We further apply Finite Scalar Quantization to the learned change representation, which suppresses small, high-frequency nuisance fluctuations while preserving consistent structural drift. Experiments on longitudinal 3D brain MRI show that Latent Drift improves patient-specific neuro-forecasting over diffusion and autoregressive transformer baselines across generative fidelity and clinically relevant evaluation metrics. Project page: \href{https://cutepkq.github.io/latent-drift}{https://cutepkq.github.io/latent-drift}.
CommentsAccepted to ECCV 2026
