CNN-based lung CT registration with multiple anatomical constraints.
CNN-based lung CT registration with multiple anatomical constraints.
复制标题
基于CNN的多解剖约束肺部CT配准。
DOI：
10.1016/j.media.2021.102139
复制
发表时间：
2021-08
影响因子：
10.9
通讯作者：
van Ginneken, Bram
中科院分区：
文献类型：
--
作者：
Hering, Alessa;Haeger, Stephanie;Moltz, Jan;Lessmann, Nikolas;Heldmann, Stefan;van Ginneken, Bram
基于深度学习的配准方法成为传统配准方法的快速替代方案。然而，这些方法通常仍然不能实现与常规配准方法相同的性能，因为它们要么限于小变形，要么它们不能处理大变形和小变形的叠加而不产生内部具有折叠的难以置信的变形场。在本文中，我们确定了用于肺部配准的传统配准方法的重要策略，并成功开发了深度学习对应方法。我们采用了一个基于高斯金字塔的多级框架，可以解决图像配准优化在一个由粗到精的方式。此外，我们防止折叠的变形场和限制的雅可比行列式的生理意义的值相结合的体积变化的惩罚与曲率正则化的损失函数。关键点对应被集成以专注于较小结构的对齐。我们进行了广泛的评估，以评估的准确性，鲁棒性，估计变形场的可扩展性，和我们的注册方法的可转移性。我们表明，它实现了国家的最先进的结果COPDGene数据集相比，传统的注册方法具有更短的执行时间。在我们对DIRLab呼气到吸气肺配准的实验中，我们证明了比其他深度学习方法的实质性改进（TRE低于1.2 mm）。我们的算法可在https://grand-challenge.org/algorithms/deep-learning-based-ct-lung-registration/上公开获得。
Deep-learning-based registration methods emerged as a fast alternative to conventional registration methods. However, these methods often still cannot achieve the same performance as conventional registration methods because they are either limited to small deformation or they fail to handle a superposition of large and small deformations without producing implausible deformation fields with foldings inside. In this paper, we identify important strategies of conventional registration methods for lung registration and successfully developed the deep-learning counterpart. We employ a Gaussian-pyramid-based multilevel framework that can solve the image registration optimization in a coarse-to-fine fashion. Furthermore, we prevent foldings of the deformation field and restrict the determinant of the Jacobian to physiologically meaningful values by combining a volume change penalty with a curvature regularizer in the loss function. Keypoint correspondences are integrated to focus on the alignment of smaller structures. We perform an extensive evaluation to assess the accuracy, the robustness, the plausibility of the estimated deformation fields, and the transferability of our registration approach. We show that it achieves state-of-the-art results on the COPDGene dataset compared to conventional registration method with much shorter execution time. In our experiments on the DIRLab exhale to inhale lung registration, we demonstrate substantial improvements (TRE below 1.2 mm) over other deep learning methods. Our algorithm is publicly available at https://grand-challenge.org/algorithms/deep-learning-based-ct-lung-registration/.
登录
查看更多内容
影响因子：
10.9
作者：
de Vos, Bob D.;Berendsen, Floris F.;Isgum, Ivana
通讯作者：
Isgum, Ivana
DOI：
10.1016/s0734-189x(89)80014-3
发表时间：
1989-04-01
期刊：
COMPUTER VISION GRAPHICS AND IMAGE PROCESSING
影响因子：
--
作者：
BAJCSY, R;KOVACIC, S
通讯作者：
KOVACIC, S
影响因子：
3.5
作者：
Castillo, Richard;Castillo, Edward;Guerrero, Thomas
通讯作者：
Guerrero, Thomas
DOI：
10.1007/s11548-019-02068-z
发表时间：
2019-11-01
影响因子：
3
作者：
Hering, Alessa;Kuckertz, Sven;Heinrich, Mattias P.
通讯作者：
Heinrich, Mattias P.
影响因子：
3.8
作者：
Fu, Yabo;Lei, Yang;Yang, Xiaofeng
通讯作者：
Yang, Xiaofeng