MvBody：基于光学3D人体扫描的多视图混合Transformer用于可解释的剖宫产预测
MvBody: Multi-View-Based Hybrid Transformer Using Optical 3D Body Scan for Explainable Cesarean Section Prediction
AI总结：
本文提出MvBody，一种基于多视图Transformer的网络，仅利用自我报告医疗数据和孕晚期3D光学人体扫描预测剖宫产风险，并通过度量学习提升泛化能力，在独立测试集上取得84.62%准确率和0.724 AUC-ROC，同时利用积分梯度提供可解释性。
AI中文摘要：
准确评估剖宫产（CS）分娩风险至关重要，尤其是在医疗资源有限、获得医疗服务往往受限的环境中。早期且可靠的风险预测有助于做出更明智的产前护理决策，并可改善孕产妇和新生儿结局。然而，现有的大多数预测模型都是为分娩期间院内使用而设计的，并且依赖于在资源有限或居家环境中通常无法获得的参数。在本研究中，我们开展了一项试点调查，以检验使用3D体形进行CS风险评估的可行性，为未来使用更经济实惠的通用设备进行应用奠定基础。我们提出了一种新颖的基于多视图的Transformer网络MvBody，该网络仅使用自我报告的医疗数据以及在妊娠第31周至第38周之间获取的3D光学人体扫描来预测CS风险。为了提高数据稀缺环境下的训练效率和模型泛化能力，我们在网络中引入了度量学习损失。与广泛使用的机器学习模型以及最新的先进3D分析方法相比，我们的方法表现出更优越的性能，在独立测试集上达到了84.62%的准确率和0.724的受试者工作特征曲线下面积（AUC-ROC）。为了提高模型预测的透明度和可信度，我们应用了积分梯度（Integrated Gradients）算法，为模型的决策过程提供具有理论依据的解释。我们的结果表明，孕前体重、产妇年龄、产科病史、既往剖宫产史以及体形（尤其是头部和肩部周围的体形）是CS风险预测的关键贡献因素。
英文摘要：
Accurately assessing the risk of cesarean section (CS) delivery is critical, especially in settings with limited medical resources, where access to healthcare is often restricted. Early and reliable risk prediction allows better-informed prenatal care decisions and can improve maternal and neonatal outcomes. However, most existing predictive models are tailored for in-hospital use during labor and rely on parameters that are often unavailable in resource-limited or home-based settings. In this study, we conduct a pilot investigation to examine the feasibility of using 3D body shape for CS risk assessment for future applications with more affordable general devices. We propose a novel multi-view-based Transformer network, MvBody, which predicts CS risk using only self-reported medical data and 3D optical body scans obtained between the 31st and 38th weeks of gestation. To enhance training efficiency and model generalizability in data-scarce environments, we incorporate a metric learning loss into the network. Compared to widely used machine learning models and the latest advanced 3D analysis methods, our method demonstrates superior performance, achieving an accuracy of 84.62% and an Area Under the Receiver Operating Characteristic Curve (AUC-ROC) of 0.724 on the independent test set. To improve transparency and trust in the model's predictions, we apply the Integrated Gradients algorithm to provide theoretically grounded explanations of the model's decision-making process. Our results indicate that pre-pregnancy weight, maternal age, obstetric history, previous CS history, and body shape, particularly around the head and shoulders, are key contributors to CS risk prediction.
