CAR-Net: Unsupervised Co-Attention Guided Registration Network for Joint Registration and Structure Learning
This addresses the need for more accurate and efficient image registration in medical imaging, though it appears incremental as it builds on existing unsupervised methods with a novel co-attention mechanism.
The paper tackled the problem of improving image registration accuracy in medical image analysis by proposing CAR-Net, an unsupervised deep learning network that uses co-attention to learn representations, resulting in higher accuracy and smoother deformation fields compared to state-of-the-art methods on cardiac MRI data.
Image registration is a fundamental building block for various applications in medical image analysis. To better explore the correlation between the fixed and moving images and improve registration performance, we propose a novel deep learning network, Co-Attention guided Registration Network (CAR-Net). CAR-Net employs a co-attention block to learn a new representation of the inputs, which drives the registration of the fixed and moving images. Experiments on UK Biobank cardiac cine-magnetic resonance image data demonstrate that CAR-Net obtains higher registration accuracy and smoother deformation fields than state-of-the-art unsupervised registration methods, while achieving comparable or better registration performance than corresponding weakly-supervised variants. In addition, our approach can provide critical structural information of the input fixed and moving images simultaneously in a completely unsupervised manner.