Statistical shape modeling (SSM) enables population-based quantitative analysis of anatomical shapes, informing clinical diagnosis. Deep learning approaches predict correspondence-based SSM directly from unsegmented 3D images but require calibrated uncertainty quantification, motivating Bayesian formulations. Variational information bottleneck DeepSSM (VIB-DeepSSM) is an effective, principled framework for predicting probabilistic shapes of anatomy from images with aleatoric uncertainty quantification. However, VIB is only half-Bayesian and lacks epistemic uncertainty inference. We derive a fully Bayesian VIB formulation and demonstrate the efficacy of two scalable implementation approaches: concrete dropout and batch ensemble. Additionally, we introduce a novel combination of the two that further enhances uncertainty calibration via multimodal marginalization. Experiments on synthetic shapes and left atrium data demonstrate that the fully Bayesian VIB network predicts SSM from images with improved uncertainty reasoning without sacrificing accuracy.

翻译：统计形状建模（SSM）能够实现解剖形状的群体定量分析，为临床诊断提供依据。深度学习方法可直接从未分割的三维图像中预测基于对应关系的SSM，但需要校准的不确定性量化，这推动了贝叶斯公式的发展。变分信息瓶颈DeepSSM（VIB-DeepSSM）是一种有效且规范化的框架，可基于图像预测具有偶然不确定性量化的概率解剖形状。然而，VIB仅为半贝叶斯方法，缺乏认知不确定性推断。我们推导出完全贝叶斯VIB公式，并展示了两种可扩展实现方法的有效性：具体丢弃法和批次集成法。此外，我们提出两者的创新性组合，通过多模态边际化进一步增强了不确定性校准。在合成形状和左心房数据上的实验表明，完全贝叶斯VIB网络能在不牺牲准确性的前提下，从图像中预测出具有改进不确定性推理能力的SSM。