胎儿超声中时间偏差与采集偏差的交叉解耦
Intersectional Disentangling of Temporal and Acquisition Bias in Fetal Ultrasound
AI总结：
该研究针对胎儿超声体重估计，通过交叉分析与模型无关的偏回归解耦时间偏差（STD）与采集偏差（PS），发现STD是主要误差来源，DL模型对STD更敏感但仍具优势，强调公平性分析需关注混杂因素。
摘要：
医学影像AI的公平性研究常通过训练数据中子群体的代表性不足来解释其性能差距。本文表明，交叉分析可解耦与目标变量共变的临床和采集混杂因素所导致的公平性与性能差距。作为案例，我们研究产科超声的扫描时间胎儿体重估计，分析两种模型：最先进的深度学习（DL）模型与临床金标准Hadlock公式。通过无监督切片发现，我们发现高误差子群体在图像采集像素间距（PS）和扫描至分娩（STD）区间上存在极端情况。其中，PS是可优化的采集参数，而STD是PS和偏差诊断的潜在混杂因素，仅子群体检查无法将二者分离。我们使用具有相同元数据划分和偏回归的模型无关分析来解耦这些因素：固定STD时，明显的PS效应缩小为小残差（标准化系数β=-0.17）；固定PS时，STD主导误差（β=+0.56）。两种模型随STD增加而性能下降，包括生物计量公式，表明大部分误差源于预测目标本身而非成像。DL模型对STD的敏感性约为Hadlock的1.5倍，但在所有子群体中仍更准确。我们得出结论，公平性分析需仔细分析潜在混杂因素，否则可能将时间或采集相关的依赖等效应归因于人口统计学因素。
英文摘要：
Fairness studies of medical imaging AI often explain subgroup performance gaps through under-representation in the training data. We show that intersectional analysis can disentangle fairness and performance gaps arising from clinical and acquisition confounders that co-vary with the target. As a case, we study scan-time fetal weight estimation from obstetric ultrasound, analyzing two models: a state-of-the-art deep learning (DL) model and the clinical gold-standard Hadlock formula. Using unsupervised slice discovery, we find that high-error subgroups share extreme in the image-acquisition pixel spacing (PS) and in the scan-to-delivery (STD) interval. Of these, PS is an acquisition parameter that can be optimized, while STD is a potential confounder for both PS and our bias diagnostics. Subgroup inspection alone cannot separate them. We disentangle the factors using a model-agnostic analysis with identical metadata partitions and partial regression. Holding STD fixed, the apparent PS effect collapses to a small residual (standardized coefficient $β=-0.17$), whereas holding PS fixed, STD dominates error ($β=+0.56$). Both models degrade with increasing STD, including the biometric formula, indicating much of the error is intrinsic to the prediction target rather than imaging. The DL model is $\sim$1.5$\times$ more sensitive to STD than Hadlock, though it remains more accurate in every subgroup. We conclude that fairness analyses need to carefully analyze potential confounds, or risk attributing an effect such as temporal or acquisition-related dependency to demographics.
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。
