# Adapting the Mean Teacher for keypoint-based lung registration under geometric domain shifts

arXiv: https://arxiv.org/abs/2207.00371 · HTML: https://mlsanity.com/paper/2207.00371/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 27 references that are in the map.
- First posted on arXiv 1 Jul 2022.

## Builds on (most cited first, 17 of 17)

- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Adversarial Discriminative Domain Adaptation](https://mlsanity.com/paper/1702.05464/) (2017)
- [Maximum Classifier Discrepancy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1712.02560/) (2017)
- [Deep Visual Domain Adaptation: A Survey](https://mlsanity.com/paper/1802.03601/) (2018)
- [Learning to Adapt Structured Output Space for Semantic Segmentation](https://mlsanity.com/paper/1802.10349/) (2018)
- [Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results](https://mlsanity.com/paper/1703.01780/) (2017)
- [Uncertainty-aware Self-ensembling Model for Semi-supervised 3D Left Atrium Segmentation](https://mlsanity.com/paper/1907.07034/) (2019)
- [Domain Adaptation for Medical Image Analysis: A Survey](https://mlsanity.com/paper/2102.09508/) (2021)
- [Domain Separation Networks](https://mlsanity.com/paper/1608.06019/) (2016)
- [Deep Learning in Medical Image Registration: A Survey](https://mlsanity.com/paper/1903.02026/) (2019)
- [Unsupervised domain adaptation for medical imaging segmentation with self-ensembling](https://mlsanity.com/paper/1811.06042/) (2018)
- [3D Human Pose Estimation in the Wild by Adversarial Learning](https://mlsanity.com/paper/1803.09722/) (2018)
- [Conditional Deformable Image Registration with Convolutional Neural Network](https://mlsanity.com/paper/2106.12673/) (2021)
- [Fast 3D registration with accurate optimisation and little learning for Learn2Reg 2021](https://mlsanity.com/paper/2112.03053/) (2021)
- [Voxelmorph++ Going beyond the cranial vault with keypoint supervision and multi-channel instance optimisation](https://mlsanity.com/paper/2203.00046/) (2022)
- [Deep learning based geometric registration for medical images: How accurate can we get without visual features?](https://mlsanity.com/paper/2103.00885/) (2021)
- [Unsupervised domain adaptation for clinician pose estimation and instance segmentation in the operating room](https://mlsanity.com/paper/2108.11801/) (2021)

## Built on by (most cited first, 5 of 5)

- [Anatomy-guided domain adaptation for 3D in-bed human pose estimation](https://mlsanity.com/paper/2211.12193/) (2022)
- [Unsupervised 3D registration through optimization-guided cyclical self-training](https://mlsanity.com/paper/2306.16997/) (2023)
- [Keypoint-Augmented Self-Supervised Learning for Medical Image Segmentation with Limited Annotation](https://mlsanity.com/paper/2310.01680/) (2023)
- [Deep Implicit Optimization enables Robust Learnable Features for Deformable Image Registration](https://mlsanity.com/paper/2406.07361/) (2024)
- [A denoised Mean Teacher for domain adaptive point cloud registration](https://mlsanity.com/paper/2306.14749/) (2023)

## Abstract (arXiv)

Recent deep learning-based methods for medical image registration achieve results that are competitive with conventional optimization algorithms at reduced run times. However, deep neural networks generally require plenty of labeled training data and are vulnerable to domain shifts between training and test data. While typical intensity shifts can be mitigated by keypoint-based registration, these methods still suffer from geometric domain shifts, for instance, due to different fields of view. As a remedy, in this work, we present a novel approach to geometric domain adaptation for image registration, adapting a model from a labeled source to an unlabeled target domain. We build on a keypoint-based registration model, combining graph convolutions for geometric feature learning with loopy belief optimization, and propose to reduce the domain shift through self-ensembling. To this end, we embed the model into the Mean Teacher paradigm. We extend the Mean Teacher to this context by 1) adapting the stochastic augmentation scheme and 2) combining learned feature extraction with differentiable optimization. This enables us to guide the learning process in the unlabeled target domain by enforcing consistent predictions of the learning student and the temporally averaged teacher model. We evaluate the method for exhale-to-inhale lung CT registration under two challenging adaptation scenarios (DIR-Lab 4D CT to COPD, COPD to Learn2Reg). Our method consistently improves on the baseline model by 50%/47% while even matching the accuracy of models trained on target data. Source code is available at https://github.com/multimodallearning/registration-da-mean-teacher.