# LiftReg: Limited Angle 2D/3D Deformable Registration

arXiv: https://arxiv.org/abs/2203.05565 · HTML: https://mlsanity.com/paper/2203.05565/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 19 references that are in the map.
- First posted on arXiv 10 Mar 2022.

## Builds on (most cited first, 2 of 2)

- [Spatial Transformer Networks](https://mlsanity.com/paper/1506.02025/) (2015)
- [Fluid registration between lung CT and stationary chest tomosynthesis images](https://mlsanity.com/paper/2203.04958/) (2022)

## Built on by (most cited first, 4 of 4)

- [Hierarchical Uncertainty Estimation for Learning-based Registration in Neuroimaging](https://mlsanity.com/paper/2410.09299/) (2024)
- [Learning Expected Appearances for Intraoperative Registration during Neurosurgery](https://mlsanity.com/paper/2310.01735/) (2023)
- [PolyPose: Deformable 2D/3D Registration via Polyrigid Transformations](https://mlsanity.com/paper/2505.19256/) (2025)
- [GuidedRec: Guiding Ill-Posed Unsupervised Volumetric Recovery](https://mlsanity.com/paper/2405.11977/) (2024)

## Abstract (arXiv)

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.