Fu Jingru, Dalca Adrian V, Fischl Bruce, Moreno Rodrigo, Hoffmann Malte
Division of Biomedical Imaging, KTH Royal Institute of Technology, Huddinge, Sweden.
Athinoula A. Martinos Center for Biomedical Imaging, Charlestown, USA.
Proc IEEE Int Symp Biomed Imaging. 2025 Apr;2025. doi: 10.1109/isbi60581.2025.10980859. Epub 2025 May 12.
Rigid registration aims to determine the translations and rotations necessary to align features in a pair of images. While recent machine learning methods have become state-of-the-art for linear and deformable registration across subjects, they have demonstrated limitations when applied to longitudinal (within-subject) registration, where achieving precise alignment is critical. Building on an existing framework for anatomy-aware, acquisition-agnostic affine registration, we propose a model optimized for longitudinal, rigid brain registration. By training the model with synthetic within-subject pairs augmented with rigid and subtle nonlinear transforms, the model estimates more accurate rigid transforms than previous cross-subject networks and performs robustly on longitudinal registration pairs within and across magnetic resonance imaging (MRI) contrasts.
刚性配准旨在确定一对图像中对齐特征所需的平移和旋转。虽然最近的机器学习方法已成为跨对象线性和可变形配准的最新技术，但在应用于纵向（对象内）配准时，它们已显示出局限性，而在纵向配准中实现精确对齐至关重要。基于现有的解剖学感知、采集无关仿射配准框架，我们提出了一种针对纵向刚性脑配准进行优化的模型。通过使用添加了刚性和细微非线性变换的合成对象内图像对训练该模型，该模型比以前的跨对象网络估计出更准确的刚性变换，并且在磁共振成像（MRI）对比度内和跨对比度的纵向配准对上表现稳健。
