Efficiently quantifying predictive uncertainty in medical images remains a challenge. While Bayesian neural networks (BNN) offer predictive uncertainty, they require substantial computational resources to train. Although Bayesian approximations such as ensembles have shown promise, they still suffer from high training and inference costs. Existing approaches mainly address the costs of BNN inference post-training, with little focus on improving training efficiency and reducing parameter complexity. This study introduces a training procedure for a sparse (partial) Bayesian network. Our method selectively assigns a subset of parameters as Bayesian by assessing their deterministic saliency through gradient sensitivity analysis. The resulting network combines deterministic and Bayesian parameters, exploiting the advantages of both representations to achieve high task-specific performance and minimize predictive uncertainty. Demonstrated on multi-label ChestMNIST for classification and ISIC, LIDC-IDRI for segmentation, our approach achieves competitive performance and predictive uncertainty estimation by reducing Bayesian parameters by over 95\%, significantly reducing computational expenses compared to fully Bayesian and ensemble methods.

通过选择性地通过梯度敏感性分析评估确定性显著性，本研究引入了对稀疏（部分）贝叶斯网络的训练过程。通过将确定性参数与贝叶斯参数相结合，充分利用两种表示的优点，实现了高效的特定任务性能和最小化的预测不确定性。在多标签ChestMNIST分类和ISIC、LIDC-IDRI分割任务上表现出了有竞争力的性能和预测不确定性估计，相比完全贝叶斯化和集合方法，能够显著减少95%以上贝叶斯参数，从而大大降低计算开销。

稀疏贝叶斯网络：医学图像分析中高效的不确定性量化