医学图像分割中可靠不确定性的平均校准损失
Average Calibration Losses for Reliable Uncertainty in Medical Image Segmentation
AI总结：
本文提出基于mL1-ACE的可微校准损失，通过硬/软分箱方法提升像素校准，实验显示其能有效降低校准误差并保持高Dice相似系数，同时引入数据集可靠性直方图分析校准与真实准确性的对齐。
摘要：
医学图像分割的深度神经网络常表现出过度自信，影响可靠性和临床应用。本文提出可微的边际L1平均校准误差（mL1-ACE）作为辅助损失，可在单张图像基础上计算。我们比较了硬分箱和软分箱方法，直接改进像素校准。在四个数据集（ACDC、AMOS、KiTS、BraTS）上的实验表明，结合mL1-ACE显著降低了校准误差，特别是平均校准误差（ACE）和最大校准误差（MCE），同时保持高Dice相似系数（DSC）。我们发现软分箱变体在DSC加交叉熵损失基线上的校准改进最大，但常牺牲分割性能，而硬分箱mL1-ACE保持分割性能，尽管校准改进较弱。为深入理解校准性能及其在影像数据集中的变化，我们引入数据集可靠性直方图，即对单张图像可靠性图的汇总。所得分析突显了预测置信度与真实准确性的对齐改善。总体而言，我们的方法为从业者提供了对校准-准确率权衡的明确控制，使深度学习方法更可靠地融入临床工作流程。我们在此分享代码：https://github.com/cai4cai/Average-Calibration-Losses
英文摘要：
Deep neural networks for medical image segmentation are often overconfident, compromising both reliability and clinical utility. In this work, we propose differentiable formulations of marginal L1 Average Calibration Error (mL1-ACE) as an auxiliary loss that can be computed on a per-image basis. We compare both hard- and soft-binning approaches to directly improve pixel-wise calibration. Our experiments on four datasets (ACDC, AMOS, KiTS, BraTS) demonstrate that incorporating mL1-ACE significantly reduces calibration errors, particularly Average Calibration Error (ACE) and Maximum Calibration Error (MCE), while largely maintaining high Dice Similarity Coefficients (DSCs). We find that the soft-binned variant yields the greatest improvements in calibration over the DSC plus cross-entropy loss baseline but often compromises segmentation performance, with hard-binned mL1-ACE maintaining segmentation performance, albeit with weaker calibration improvement. To gain further insight into calibration performance and its variability across an imaging dataset, we introduce dataset reliability histograms, an aggregation of per-image reliability diagrams. The resulting analysis highlights improved alignment between predicted confidences and true accuracies. Overall, our approach provides practitioners with explicit control over the calibration-accuracy trade-off, enabling more reliable integration of deep learning methods into clinical workflows. We share our code here: https://github.com/cai4cai/Average-Calibration-Losses
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
