临床域偏移下多器官CT分割的边界感知器官级召回率风险控制
Bound-Aware Per-Organ Recall Risk Control for Multi-Organ CT Segmentation under Clinical Domain Shift
浏览论文内容
中文总结 AI 辅助
针对临床域偏移下多器官CT分割的召回率保证问题,该研究为AMOS训练的nnU-Net校准器官级阈值,对比多种风险控制方法,提出WSR投注界可高效重新认证Tier-1器官,为多器官分割的风险控制提供了新方案。
中文摘要 AI 辅助
无分布风险控制为冻结的分割模型提供器官特定的召回率保证。我们为经AMOS数据集训练的nnU-Net校准器官级阈值,审计其向RAOS数据集的迁移性能,并利用病例级体素假阴性率(FNR)估计局部重新认证成本。AMOS数据集上的控制通过了验证,但迁移后有7/12个器官超出α=0.10的阈值;较小的校准集可能因保守或空洞阈值掩盖超出情况。风险控制预测集(RCPS)对总体平均风险提供高概率控制,而保形风险控制(CRC)提供较弱的期望控制,两者均要求数据可交换性;固定全局阈值无法提供器官级保证。WSR(Waudby-Smith–Ramdas)投注界用25个本地病例重新认证了6个Tier-1器官,而Hoeffding–Bentkus(HB)则需要30–40个病例;CRC仅需10–15个病例,但具有较重的单病例尾部。使用25个病例时,无Tier-2器官满足我们示例的精度标准。
英文摘要
Distribution-free risk control adds organ-specific recall guarantees to frozen segmentation. We calibrate per-organ thresholds for an AMOS-trained nnU-Net, audit transfer to RAOS, and estimate local re-certification cost using case-level voxel false-negative rate (FNR). The AMOS control passes, but $7/12$ organs exceed $α{=}0.10$ after transfer; smaller calibration sets can mask exceedances with conservative or vacuous thresholds. Risk-Controlling Prediction Sets (RCPS) give high-probability control of population-mean risk, whereas Conformal Risk Control (CRC) gives weaker expectation control. Both require exchangeability; fixed and global thresholds give no per-organ guarantee. The Waudby--Smith--Ramdas (WSR) betting bound re-certifies six Tier-1 organs with 25 local cases, versus 30--40 for Hoeffding--Bentkus (HB). CRC needs 10--15 but has a heavier individual-case tail. No Tier-2 organ meets our illustrative precision criterion with 25 cases.
发表机构
- Jade Hochschule Wilhelmshaven(威廉港雅德应用科学大学)
机构由 AI 辅助整理,请以论文原文为准。