# Tackling the Problem of Large Deformations in Deep Learning Based Medical Image Registration Using Displacement Embeddings

arXiv: https://arxiv.org/abs/2005.13338 · HTML: https://mlsanity.com/paper/2005.13338/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 May 2020.

## Built on by (most cited first, 3 of 3)

- [Accurate Point Cloud Registration with Robust Optimal Transport](https://mlsanity.com/paper/2111.00648/) (2021)
- [QUIZ: An Arbitrary Volumetric Point Matching Method for Medical Image Registration](https://mlsanity.com/paper/2310.00296/) (2023)
- [Spot the Difference: Detection of Topological Changes via Geometric Alignment](https://mlsanity.com/paper/2106.08233/) (2021)

## Abstract (arXiv)

Though, deep learning based medical image registration is currently starting to show promising advances, often, it still fells behind conventional frameworks in terms of registration accuracy. This is especially true for applications where large deformations exist, such as registration of interpatient abdominal MRI or inhale-to-exhale CT lung registration. Most current works use U-Net-like architectures to predict dense displacement fields from the input images in different supervised and unsupervised settings. We believe that the U-Net architecture itself to some level limits the ability to predict large deformations (even when using multilevel strategies) and therefore propose a novel approach, where the input images are mapped into a displacement space and final registrations are reconstructed from this embedding. Experiments on inhale-to-exhale CT lung registration demonstrate the ability of our architecture to predict large deformations in a single forward path through our network (leading to errors below 2 mm).