考虑医学数据采集的随机不确定性，提升缺失模态下的多模态诊断精度。
Embracing Aleatoric Uncertainty in Medical Multimodal Learning with Missing Modalities
- 用多变量高斯分布显式建模单模态不确定性
- 在MIMIC-IV和eICU上分别提升2.26%和2.17%的AUC-ROC
- 适合处理临床中常见模态缺失问题的研究者
医学多模态学习常面临临床实践中模态缺失的问题。现有方法假设各模态贡献均等且缺失模式随机，忽略了医学数据采集固有的不确定性。为此，我们提出随机不确定性建模（AUM），显式量化单模态的随机不确定性以应对模态缺失。具体地，AUM将每个单模态表示建模为多元高斯分布，捕捉随机不确定性，并实现模态可靠性量化。通过在双部患者-模态图中设计基于不确定性的动态消息传递机制，自适应聚合信息。该过程自然容纳缺失模态，同时动态强化可靠模态的信息以指导表征生成。AUM在MIMIC-IV死亡预测任务上实现2.26%的AUC-ROC提升，在eICU上获得2.17%的性能增益，优于现有最先进方法。
原文摘要 · Abstract (English)
Medical multimodal learning faces significant challenges with missing modalities prevalent in clinical practice. Existing approaches assume equal contribution of modality and random missing patterns, neglecting inherent uncertainty in medical data acquisition. In this regard, we propose the Aleatoric Uncertainty Modeling (AUM) that explicitly quantifies unimodal aleatoric uncertainty to address missing modalities. Specifically, AUM models each unimodal representation as a multivariate Gaussian distribution to capture aleatoric uncertainty and enable principled modality reliability quantification. To adaptively aggregate captured information, we develop a dynamic message-passing mechanism within a bipartite patient-modality graph using uncertainty-aware aggregation mechanism. Through this process, missing modalities are naturally accommodated, while more reliable information from available modalities is dynamically emphasized to guide representation generation. Our AUM framework achieves an improvement of 2.26% AUC-ROC on MIMIC-IV mortality prediction and 2.17% gain on eICU, outperforming existing state-of-the-art approaches.
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。