用控制理论设计新模型，让医疗影像分割更公平
Distribution-aware Fairness Learning in Medical Image Segmentation From A Control-Theoretic Perspective
- 基于最优控制理论设计混合专家模型，动态适应不同人群分布
- 在两个2D和一个3D数据集上实现当前最好公平性表现
- 适合关注医疗AI公平性与跨群体泛化能力的研究者
由于人口统计学特征（如年龄、性别、种族）和临床因素（如病情严重程度）导致的临床数据采集不平衡，医疗图像分割中的公平性至关重要。为应对这一挑战，我们提出受最优控制理论启发的分布感知混合专家模型（dMoE），全面分析其内在机制，并阐明其在适应医学图像分割中异质分布方面的角色。我们将dMoE集成到多种网络架构中，证明其在多样医学图像分析任务中的广泛适用性。通过融合人口统计学与临床因素，dMoE在两个2D基准数据集和一个3D内部数据集上均达到领先性能。结果表明，dMoE能有效缓解不平衡分布带来的偏差，为控制理论与医疗图像分割中的公平学习提供了一条有前景的路径。源代码将在https://github.com/tvseg/dMoE公开。
原文摘要 · Abstract (English)
Ensuring fairness in medical image segmentation is critical due to biases in imbalanced clinical data acquisition caused by demographic attributes (e.g., age, sex, race) and clinical factors (e.g., disease severity). To address these challenges, we introduce Distribution-aware Mixture of Experts (dMoE), inspired by optimal control theory. We provide a comprehensive analysis of its underlying mechanisms and clarify dMoE's role in adapting to heterogeneous distributions in medical image segmentation. Furthermore, we integrate dMoE into multiple network architectures, demonstrating its broad applicability across diverse medical image analysis tasks. By incorporating demographic and clinical factors, dMoE achieves state-of-the-art performance on two 2D benchmark datasets and a 3D in-house dataset. Our results highlight the effectiveness of dMoE in mitigating biases from imbalanced distributions, offering a promising approach to bridging control theory and medical image segmentation within fairness learning paradigms. The source code will be made available. The source code is available at https://github.com/tvseg/dMoE.
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。