Towards Saner Deep Image Registration
Towards Saner Deep Image Registration
复制标题
DOI：
10.1109/iccv51070.2023.01145
复制
发表时间：
2023-07
期刊：
影响因子：
--
通讯作者：
Bin Duan;Ming Zhong;Yan Yan-Yan
中科院分区：
文献类型：
--
作者：
Bin Duan;Ming Zhong;Yan Yan-Yan
随着计算硬件的最新进展和深度学习架构的激增，基于学习的深度图像配准方法在度量性能和推理时间方面已经超过了传统的配准方法。然而，这些方法专注于改善性能测量，如骰子，导致较少的关注模型的行为，同样需要配准，特别是医学成像。本文在健全检查显微镜下研究了流行的基于学习的深度注册的这些行为。我们发现，大多数现有的注册遭受低逆一致性和非歧视的相同对由于过度优化的图像相似性。为了纠正这些行为，我们提出了一种新的基于正则化的sanity-enforcer方法，该方法对深度模型进行了两次健全性检查，以减少其逆一致性错误，同时提高其区分能力。此外，我们得到了一组理论保证我们的健全检查图像配准方法，实验结果支持我们的理论研究结果和它们的有效性，在不牺牲任何性能的情况下，增加模型的健全。
With recent advances in computing hardware and surges of deep-learning architectures, learning-based deep image registration methods have surpassed their traditional counterparts, in terms of metric performance and inference time. However, these methods focus on improving performance measurements such as Dice, resulting in less attention given to model behaviors that are equally desirable for registrations, especially for medical imaging. This paper investigates these behaviors for popular learning-based deep registrations under a sanity-checking microscope. We find that most existing registrations suffer from low inverse consistency and nondiscrimination of identical pairs due to overly optimized image similarities. To rectify these behaviors, we propose a novel regularization-based sanity-enforcer method that imposes two sanity checks on the deep model to reduce its inverse consistency errors and increase its discriminative power simultaneously. Moreover, we derive a set of theoretical guarantees for our sanity-checked image registration method, with experimental results supporting our theoretical findings and their effectiveness in increasing the sanity of models without sacrificing any performance.