University of Bordeaux, IMB, UMR CNRS 5251, INRIA Project team Monc, F-33405 Talence Cedex, France.
INRIA Bordeaux Sud Ouest, 200 Av. de la Tour, Talence 33405, France.
Phys Med Biol. 2024 Aug 8;69(16). doi: 10.1088/1361-6560/ad6952.
In medical imaging, it is often crucial to accurately assess and correct movement during image-guided therapy. Deformable image registration (DIR) consists in estimating the required spatial transformation to align a moving image with a fixed one. However, it is acknowledged that for DIR methods, boundary conditions applied to the solution are critical in preventing mis-registration. This poses an issue particularly when areas of interest are located near the image border. Despite the extensive research on registration techniques, relatively few have addressed the issue of boundary conditions in the context of medical DIR. Our aim is a step towards customizing boundary conditions to suit the diverse registration tasks at hand.We analyze the behavior of two typical global boundary conditions: homogeneous Dirichlet and homogeneous Neumann. We propose a generic, locally adaptive, Robin-type condition enabling to balance between Dirichlet and Neumann boundary conditions, depending on incoming/outgoing flow fields on the image boundaries. The proposed framework is entirely automatized through the determination of a reduced set of hyperparameters optimized via energy minimization.The proposed approach was tested on a mono-modal computed tomography (CT) thorax registration task and an abdominal CT-to-MRI registration task. For the first task, we observed a relative improvement in terms of target registration error of up to 12% (mean 4%), compared to homogeneous Dirichlet and homogeneous Neumann. For the second task, the automatic framework provides results close to the best achievable.This study underscores the importance of tailoring the registration problem at the image boundaries. In this research, we introduce a novel method to adapt the boundary conditions on a voxel-by-voxel basis, yielding optimized results in two distinct tasks: mono-modal CT thorax registration and abdominal CT-to-MRI registration. The proposed framework enables optimized boundary conditions in image registration without prior assumptions regarding the images or the motion.
在医学成像中，准确评估和纠正图像引导治疗过程中的运动至关重要。变形图像配准（Deformable Image Registration，DIR）旨在估计所需的空间变换，以将移动图像与固定图像对齐。然而，众所周知，对于 DIR 方法，施加于解的边界条件对于防止配准错误至关重要。当感兴趣区域位于图像边界附近时，这尤其成问题。尽管已经对配准技术进行了广泛的研究，但相对较少的研究涉及医学 DIR 中边界条件的问题。我们的目标是朝着定制边界条件以适应手头各种配准任务的方向迈出一步。
均匀 Dirichlet 和均匀 Neumann。我们提出了一种通用的、局部自适应的 Robin 型条件，能够根据图像边界上的流入/流出流场，在 Dirichlet 和 Neumann 边界条件之间取得平衡。通过能量最小化优化确定一组简化超参数，从而完全自动化了所提出的框架。
所提出的方法在单模态计算机断层扫描（CT）胸部配准任务和腹部 CT 到 MRI 配准任务上进行了测试。对于第一个任务，与均匀 Dirichlet 和均匀 Neumann 相比，我们观察到目标配准误差方面的相对改善，最高可达 12%（平均 4%）。对于第二个任务，自动框架提供的结果接近最佳可实现的结果。
这项研究强调了根据图像边界定制配准问题的重要性。在这项研究中，我们介绍了一种新的方法，可在体素基础上自适应边界条件，在两个不同的任务中产生优化的结果：单模态 CT 胸部配准和腹部 CT 到 MRI 配准。所提出的框架能够在不预先假设图像或运动的情况下，在图像配准中实现优化的边界条件。
