Feedback attention to enhance unsupervised deep learning image registration in 3D echocardiography
File(s)
Accepted version
Author(s)
Hasan, Md Kamrul
Luo, Yihao
Yang, Guang
Yap, Choon Hwai
Type
Journal Article
Abstract
Cardiac motion estimation is important for assessing the contractile health of the heart, and performing this in 3D can provide advantages due to the complex 3D geometry and motions of the heart. Deep learning image registration (DLIR) is a robust way to achieve cardiac motion estimation in echocardiography, providing speed and precision benefits, but DLIR in 3D echo remains challenging. Successful unsupervised 2D DLIR strategies are often not effective in 3D, and there have been few 3D echo DLIR implementations. Here, we propose a new spatial feedback attention (FBA) module to enhance unsupervised 3D DLIR and enable it. The module uses the results of initial registration to generate a co-attention map that describes remaining registration errors spatially and feeds this back to the DLIR to minimize such errors and improve self-supervision. We show that FBA improves a range of promising 3D DLIR designs, including networks with and without transformer enhancements, and that it can be applied to both fetal and adult 3D echo, suggesting that it can be widely and flexibly applied. We further find that the optimal 3D DLIR configuration is when FBA is combined with a spatial transformer and a DLIR backbone modified with spatial and channel attention, which outperforms existing 3D DLIR approaches. FBA’s good performance suggests that spatial attention is a good way to enable scaling up from 2D DLIR to 3D and that a focus on the quality of the image after registration warping is a good way to enhance DLIR performance. Codes and data are available at: https://github.com/kamruleee51/Feedback_DLIR.
Date Issued
2025-05-01
Date Acceptance
2025-01-06
Citation
IEEE Transactions on Medical Imaging, 2025, 44 (5), pp.2230-2243
ISSN
0278-0062
Publisher
Institute of Electrical and Electronics Engineers
Start Page
2230
End Page
2243
Journal / Book Title
IEEE Transactions on Medical Imaging
Volume
44
Issue
5
Copyright Statement
Copyright © 2025 IEEE This is the author’s accepted manuscript made available under a CC-BY licence in accordance with Imperial’s Research Publications Open Access policy (www.imperial.ac.uk/oa-policy)
License URL
Identifier
https://www.ncbi.nlm.nih.gov/pubmed/40030923
Subjects
4D echocardiography
Accuracy
and image registration
cardiac motion estimation
Computer Science
Computer Science, Interdisciplinary Applications
deep learning
Deformation
Echocardiography
Engineering
Engineering, Biomedical
Engineering, Electrical & Electronic
Feature extraction
feedback attention
Image registration
Imaging Science & Photographic Technology
Life Sciences & Biomedicine
Magnetic resonance imaging
MOTION
Radiology, Nuclear Medicine & Medical Imaging
Science & Technology
Speckle
SPECKLE-TRACKING ECHOCARDIOGRAPHY
Strain
STRAIN
Technology
Three-dimensional displays
Transformers
Publication Status
Published
Coverage Spatial
United States
Date Publish Online
2025-01-16