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

07/01/2022
by   Alexander Bigalke, et al.
0

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 while even matching the accuracy of models trained on target data. Source code is available at https://github.com/multimodallearning/registration-da-mean-teacher.

READ FULL TEXT
research
06/26/2023

A denoised Mean Teacher for domain adaptive point cloud registration

Point cloud-based medical registration promises increased computational ...
research
07/04/2022

Counterbalancing Teacher: Regularizing Batch Normalized Models for Robustness

Batch normalization (BN) is a ubiquitous technique for training deep neu...
research
06/29/2023

Unsupervised 3D registration through optimization-guided cyclical self-training

State-of-the-art deep learning-based registration methods employ three d...
research
11/22/2022

Anatomy-guided domain adaptation for 3D in-bed human pose estimation

3D human pose estimation is a key component of clinical monitoring syste...
research
06/23/2020

Rethinking Distributional Matching Based Domain Adaptation

Domain adaptation (DA) is a technique that transfers predictive models t...
research
02/09/2023

MAPS: A Noise-Robust Progressive Learning Approach for Source-Free Domain Adaptive Keypoint Detection

Existing cross-domain keypoint detection methods always require accessin...
research
03/10/2021

Regressive Domain Adaptation for Unsupervised Keypoint Detection

Domain adaptation (DA) aims at transferring knowledge from a labeled sou...

Please sign up or login with your details

Forgot password? Click here to reset