通过视觉基础模型探究医学图像分割中的偶然不确定性
Delving Aleatoric Uncertainty in Medical Image Segmentation via Vision Foundation Models
利用视觉基础模型解码特征的奇异值能量定义语义感知尺度来量化偶然不确定性，可迁移到其他密集预测任务中做样本筛选和损失加权。
原文依据 we analyze the feature diversity of the model's decoded representations and quantify their singular value energy to define the semantic perception scale for each class
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论医学图像分割通过精确描绘解剖结构和病变来支持临床工作流程。然而，医学图像数据集受到采集噪声和标注歧义的影响，导致普遍存在的数据不确定性，严重削弱了模型的鲁棒性。现有研究主要关注模型架构改进和预测可靠性估计，而对内在数据不确定性的系统探索仍不充分。为弥补这一空白，本文提出利用视觉基础模型的通用表示能力来估计内在数据不确定性。具体而言，我们分析模型解码表示的特征多样性，并量化其奇异值能量以定义每个类别的语义感知尺度，从而衡量样本难度和偶然不确定性。在此基础上，我们设计了两种不确定性驱动的应用策略：（1）偶然不确定性感知的数据筛选机制，以消除潜在噪声样本并提升模型学习质量；（2）动态不确定性感知的优化策略，在训练过程中根据语义感知尺度自适应调整类别特定的损失权重，并结合标签去噪机制以提高训练稳定性。在涵盖CT和MRI模态、涉及多器官和肿瘤分割任务的五个公开数据集上的实验结果表明，我们的方法在各种主流网络架构上均取得了显著且稳健的性能提升，揭示了偶然不确定性在医学图像理解和分割任务中的广泛应用潜力。代码已公开。
英文原文摘要 1780 字符
Medical image segmentation supports clinical workflows by precisely delineating anatomical structures and lesions. However, medical image datasets medical image datasets suffer from acquisition noise and annotation ambiguity, causing pervasive data uncertainty that substantially undermines model robustness. Existing research focuses primarily on model architectural improvements and predictive reliability estimation, while systematic exploration of the intrinsic data uncertainty remains insufficient. To address this gap, this work proposes leveraging the universal representation capabilities of visual foundation models to estimate inherent data uncertainty. Specifically, we analyze the feature diversity of the model's decoded representations and quantify their singular value energy to define the semantic perception scale for each class, thereby measuring sample difficulty and aleatoric uncertainty. Based on this foundation, we design two uncertainty-driven application strategies: (1) the aleatoric uncertainty-aware data filtering mechanism to eliminate potentially noisy samples and enhance model learning quality; (2) the dynamic uncertainty-aware optimization strategy that adaptively adjusts class-specific loss weights during training based on the semantic perception scale, combined with a label denoising mechanism to improve training stability. Experimental results on five public datasets encompassing CT and MRI modalities and involving multi-organ and tumor segmentation tasks demonstrate that our method achieves significant and robust performance improvements across various mainstream network architectures, revealing the broad application potential of aleatoric uncertainty in medical image understanding and segmentation tasks. The code is available.