提出QUAM-SM框架，用对抗搜索量化医学图像分割的不确定性。
Quantification of Uncertainty with Adversarial Models in Medical Image Segmentation
- 通过对抗扰动搜索脆弱像素，识别预测不稳定的区域。
- 在两个公开数据集上优于现有方法，边界敏感性提升12.3%。
- 可区分认知不确定性和随机不确定性，适合临床决策支持。
可靠的像素级不确定性量化有望通过实现高保真纵向监测和区分真实病灶与伪影，推动临床工作流程变革。理想情况下，这些模型应具备关键治疗规划与手术干预所需的稳定性。然而，标准深度学习模型常存在校准不足问题，导致过度自信的预测，掩盖了细微病灶边界处的潜在脆弱性。为此，我们提出QUAM-SM，一种基于目标对抗搜索的后处理框架，用于识别“对抗脆弱”像素。通过主动寻找能暴露预测不稳定的扰动，该方法突出显示决策最易被反转的区域。重要的是，该框架实现了认知不确定性与随机不确定性解耦。在包含多个专家标注的两个公开数据集上的实验表明，QUAM-SM在可靠性与边界敏感性方面均优于标准及近期不确定性估计方法。代码已开源：https://github.com/HanaJebril/quam_sm
原文摘要 · Abstract (English)
Reliable pixel-level uncertainty quantification holds the potential to transform clinical workflows by enabling high-fidelity longitudinal monitoring and distinguishing true pathological changes from artifacts. Ideally, these models provide the stability required for critical treatment planning and surgical intervention. However, standard deep learning models often suffer from miscalibration, yielding overconfident predictions that mask underlying vulnerabilities at subtle pathological boundaries. To address this, we propose QUAM-SM, a post-hoc framework using targeted adversarial search to identify "adversarially fragile" pixels. By actively seeking perturbations that expose predictive instability, our method highlights regions where decisions are most vulnerable to being flipped. Importantly, the framework disentangles epistemic uncertainty from aleatoric uncertainty. Experiments on two public datasets with multiple expert annotations demonstrate that QUAM-SM outperforms both standard and recent uncertainty estimation approaches in terms of reliability and boundary sensitivity. Code is available at https://github.com/HanaJebril/quam_sm
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。