不确定性感知的逆一致微分同胚肺图像配准测试时自适应
Uncertainty-Aware Test-Time Adaptation for Inverse Consistent Diffeomorphic Lung Image Registration
AI总结：
提出一种不确定性感知的测试时自适应框架，利用MC dropout估计空间不确定性，在675名受试者数据上提升了吸气与呼气肺CT配准的逆一致性与DSC，显著优于VoxelMorph和TransMorph。
摘要：
微分同胚可变形图像配准确保吸气与呼气胸部CT扫描之间的平滑可逆变换。然而，在实际应用中，基于深度学习的微分同胚方法难以捕捉吸气与呼气体积间的大形变，因此缺乏逆一致性。现有方法也未能考虑模型不确定性，而这有助于提升性能。我们提出了一种用于逆一致微分同胚肺配准的不确定性感知测试时自适应框架。该方法使用蒙特卡洛（MC）dropout来估计空间不确定性，并以此提升模型性能。我们在来自COPDGene研究的675名受试者的大型队列上，训练并评估了吸气到呼气CT配准方法，实现了0.966的肺边界Dice相似系数（DSC），高于VoxelMorph（0.953）和TransMorph（0.953）。在逆向配准方向上，我们的方法也展现出一致的改进，总体DSC达到0.966，高于VoxelMorph（0.958）和TransMorph（0.956）。配对t检验表明改进具有统计学意义。
英文摘要：
Diffeomorphic deformable image registration ensures smooth invertible transformations across inspiratory and expiratory chest CT scans. Yet, in practice, deep learning-based diffeomorphic methods struggle to capture large deformations between inspiratory and expiratory volumes, and therefore lack inverse consistency. Existing methods also fail to account for model uncertainty, which can be useful for improving performance. We propose an uncertainty-aware test-time adaptation framework for inverse consistent diffeomorphic lung registration. Our method uses Monte Carlo (MC) dropout to estimate spatial uncertainty that is used to improve model performance. We train and evaluate our method for inspiratory-to-expiratory CT registration on a large cohort of 675 subjects from the COPDGene study, achieving a higher Dice similarity coefficient (DSC) between the lung boundaries (0.966) compared to both VoxelMorph (0.953) and TransMorph (0.953). Our method demonstrates consistent improvements in the inverse registration direction as well with an overall DSC of 0.966, higher than VoxelMorph (0.958) and TransMorph (0.956). Paired t-tests indicate statistically significant improvements.
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。
