提出像素级校准误差，让医学分割模型的置信度更可信。
We Care Each Pixel: Calibrating on Medical Segmentation Model
- 引入像素级期望校准误差（pECE），量化模型置信度可靠性。
- 设计符号距离校准损失（SDC），提升边界几何与置信度一致性。
- 适用于临床依赖高置信度的医学图像分割任务。
医学图像分割是辅助诊断的基础，能精准勾勒解剖结构与病灶区域。现有指标如准确率、DSC、IoU、HD主要衡量预测与真实标签的空间重合度，却无法评估模型置信度的校准质量，而校准对临床可靠性至关重要。为此，我们提出像素级期望校准误差（pECE），显式测量像素级别的校准偏差，确保空间精度与置信度可靠性并重。同时，提出形态学适配策略，在计算校准损失前对真实标签掩码进行形态学操作，尤其提升基于边界的损失函数（如Margin SVLS和NACL）的效果。进一步提出符号距离校准损失（SDC），通过惩罚预测与真实符号距离函数（SDF）之间的差异，使边界几何与校准目标对齐。大量实验表明，该方法不仅提升分割性能，还显著改善校准质量，生成更可信的置信度估计。代码已开源：https://github.com/EagleAdelaide/SDC-Loss。
原文摘要 · Abstract (English)
Medical image segmentation is fundamental for computer-aided diagnostics, providing accurate delineation of anatomical structures and pathological regions. While common metrics such as Accuracy, DSC, IoU, and HD primarily quantify spatial agreement between predictions and ground-truth labels, they do not assess the calibration quality of segmentation models, which is crucial for clinical reliability. To address this limitation, we propose pixel-wise Expected Calibration Error (pECE), a novel metric that explicitly measures miscalibration at the pixel level, thereby ensuring both spatial precision and confidence reliability. We further introduce a morphological adaptation strategy that applies morphological operations to ground-truth masks before computing calibration losses, particularly benefiting margin-based losses such as Margin SVLS and NACL. Additionally, we present the Signed Distance Calibration Loss (SDC), which aligns boundary geometry with calibration objectives by penalizing discrepancies between predicted and ground-truth signed distance functions (SDFs). Extensive experiments demonstrate that our method not only enhances segmentation performance but also improves calibration quality, yielding more trustworthy confidence estimates. Code is available at: https://github.com/EagleAdelaide/SDC-Loss.
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。