Journal
IEEE TRANSACTIONS ON MEDICAL IMAGING
Volume 40, Issue 1, Pages 444-454Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TMI.2020.3029205
Keywords
Three-dimensional displays; Motion estimation; Image reconstruction; Two dimensional displays; Biomedical imaging; Image registration; Optimization; Motion estimation; deep learning; motion-compensated reconstruction; coronary magnetic resonance angiography
Categories
Funding
- Engineering and Physical Sciences Research Council (EPSRC) [EP/P032311/1, EP/P001009/1, EP/P007619/1]
- British Heart Foundation (BHF) [PG/18/59/33955, RG/20/1/34802]
- King's BHF Centre of Research Excellence [RE/18/2/34213]
- Wellcome EPSRC Centre for Medical Engineering [NS/A000049/1]
- Department of Health via the National Institute for Health Research (NIHR) Cardiovascular Health Technology Cooperative (HTC) and Comprehensive Biomedical Research Centre
- King's College London
- King's College Hospital NHS Foundation Trust
- EPSRC [EP/P032311/1, EP/P001009/1, EP/P007619/1] Funding Source: UKRI
Ask authors/readers for more resources
A novel unsupervised deep learning-based strategy, RespME-net, is proposed for fast estimation of inter-bin 3D non-rigid respiratory motion fields in free-breathing 3D coronary magnetic resonance angiography. The network can predict 3D non-rigid motion fields with subpixel accuracy within approximately 10 seconds, being about 20 times faster than a GPU-implemented state-of-the-art non-rigid registration method.
Non-rigid motion-corrected reconstruction has been proposed to account for the complex motion of the heart in free-breathing 3D coronary magnetic resonance angiography (CMRA). This reconstruction framework requires efficient and accurate estimation of non-rigid motion fields from undersampled images at different respiratory positions (or bins). However, state-of-the-art registration methods can be time-consuming. This article presents a novel unsupervised deep learning-based strategy for fast estimation of inter-bin 3D non-rigid respiratory motion fields for motion-corrected free-breathing CMRA. The proposed 3D respiratory motion estimation network (RespME-net) is trained as a deep encoder-decoder network, taking pairs of 3D image patches extracted from CMRA volumes as input and outputting the motion field between image patches. Using image warping by the estimated motion field, a loss function that imposes image similarity and motion smoothness is adopted to enable training without ground truth motion field. RespME-net is trained patch-wise to circumvent the challenges of training a 3D network volume-wise which requires large amounts of GPU memory and 3D datasets. We perform 5-fold cross-validation with 45 CMRA datasets and demonstrate that RespME-net can predict 3D non-rigid motion fields with subpixel accuracy (0.44 +/- 0.38 mm) within similar to 10 seconds, being similar to 20 times faster than a GPU-implemented state-of-the-art non-rigid registration method. Moreover, we perform non-rigid motion-compensated CMRA reconstruction for 9 additional patients. The proposed RespME-net has achieved similar motion-corrected CMRA image quality to the conventional registration method regarding coronary artery length and sharpness.
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