通过解耦影像动态与静态结构，实现多模态病程建模
Multimodal Disease Progression Modeling via Spatiotemporal Disentanglement and Multiscale Alignment
- 分离胸片中的解剖静态特征与病理动态变化
- 在MIMIC数据集上实现疾病进展识别与重症预测最优性能
- 适合做医学影像与电子病历联合分析的研究者
纵向多模态数据（如电子健康记录EHR和序列胸片CXRs）对疾病进展建模至关重要，但因两大挑战而未被充分使用：（1）连续胸片序列中静态解剖区域占据主导，掩盖了临床有意义的动态变化；（2）稀疏不规则的影像数据与连续的EHR数据存在时间错位。我们提出$ exttt{DiPro}$框架，通过区域感知解耦与多尺度对齐解决上述问题。首先，从序列胸片中解耦出静态（解剖）与动态（病理进展）特征，突出疾病相关变化；其次，通过局部（成对时间区间级）与全局（全序列）同步，将静态与动态胸片特征与异步的EHR数据分层对齐，以建模一致的进展路径。在MIMIC数据集上的大量实验表明，$ exttt{DiPro}$能有效提取时间性临床动态，并在疾病进展识别与一般ICU预测任务中达到当前最优表现。
原文摘要 · Abstract (English)
Longitudinal multimodal data, including electronic health records (EHR) and sequential chest X-rays (CXRs), is critical for modeling disease progression, yet remains underutilized due to two key challenges: (1) redundancy in consecutive CXR sequences, where static anatomical regions dominate over clinically-meaningful dynamics, and (2) temporal misalignment between sparse, irregular imaging and continuous EHR data. We introduce $\texttt{DiPro}$, a novel framework that addresses these challenges through region-aware disentanglement and multi-timescale alignment. First, we disentangle static (anatomy) and dynamic (pathology progression) features in sequential CXRs, prioritizing disease-relevant changes. Second, we hierarchically align these static and dynamic CXR features with asynchronous EHR data via local (pairwise interval-level) and global (full-sequence) synchronization to model coherent progression pathways. Extensive experiments on the MIMIC dataset demonstrate that $\texttt{DiPro}$ could effectively extract temporal clinical dynamics and achieve state-of-the-art performance on both disease progression identification and general ICU prediction tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。