LiftReg: Limited Angle 2D/3D Deformable Registration
This addresses medical image registration challenges for limited angle imaging, though it appears incremental as it builds on existing learning-based methods.
The authors tackled 2D/3D deformable registration for limited angle acquisitions by proposing LiftReg, a deep learning framework trained on simulated DRR-CT pairs, which outperformed an existing learning-based approach on the DirLab lung dataset.
We propose LiftReg, a 2D/3D deformable registration approach. LiftReg is a deep registration framework which is trained using sets of digitally reconstructed radiographs (DRR) and computed tomography (CT) image pairs. By using simulated training data, LiftReg can use a high-quality CT-CT image similarity measure, which helps the network to learn a high-quality deformation space. To further improve registration quality and to address the inherent depth ambiguities of very limited angle acquisitions, we propose to use features extracted from the backprojected 2D images and a statistical deformation model. We test our approach on the DirLab lung registration dataset and show that it outperforms an existing learning-based pairwise registration approach.