Journal
STATISTICAL ATLASES AND COMPUTATIONAL MODELS OF THE HEART: REGULAR AND CMRXMOTION CHALLENGE PAPERS, STACOM 2022
Volume 13593, Issue -, Pages 168-178Publisher
SPRINGER INTERNATIONAL PUBLISHING AG
DOI: 10.1007/978-3-031-23443-9_16
Keywords
Unsupervised registration; MLP; Transformer; Echocardiography
Categories
Funding
- French government through the National Research Agency (ANR) Investments in the Future with 3IA Cote d'Azur [ANR-19-P3IA-0002]
- Inria
Ask authors/readers for more resources
Image registration is a crucial and challenging task in medical image computing. Traditional approaches are time-consuming, while CNN and attention-based models such as Transformer have shown good performance. This study introduces patch-based MLP/Transformer models for image registration and demonstrates their effectiveness in unsupervised echocardiography registration, outperforming popular CNN models in terms of registration performance.
Image registration is an essential but challenging task in medical image computing, especially for echocardiography, where the anatomical structures are relatively noisy compared to other imaging modalities. Traditional (non-learning) registration approaches rely on the iterative optimization of a similarity metric which is usually costly in time complexity. In recent years, convolutional neural network (CNN) based image registration methods have shown good effectiveness. In the meantime, recent studies show that the attention-based model (e.g., Transformer) can bring superior performance in pattern recognition tasks. In contrast, whether the superior performance of the Transformer comes from the long-winded architecture or is attributed to the use of patches for dividing the inputs is unclear yet. This work introduces three patchbased frameworks for image registration using MLPs and transformers. We provide experiments on 2D-echocardiography registration to answer the former question partially and provide a benchmark solution. Our results on a large public 2D-echocardiography dataset show that the patch-based MLP/Transformer model can be effectively used for unsupervised echocardiography registration. They demonstrate comparable and even better registration performance than a popular CNN registration model. In particular, patch-based models better preserve volume changes in terms of Jacobian determinants, thus generating robust registration fields with less unrealistic deformation. Our results demonstrate that patch-based learning methods, whether with attention or not, can perform high-performance unsupervised registration tasks with adequate time and space complexity.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available