DeepTag: An Unsupervised Deep Learning Method for Motion Tracking on Cardiac Tagging Magnetic Resonance Images
This addresses the challenge of regional myocardium deformation analysis for cardiac diagnosis, offering a more efficient and accurate solution, though it appears incremental as it builds on existing deep learning and registration techniques.
The authors tackled the problem of motion tracking on cardiac tagging MRI images, which is difficult and limits clinical use, by proposing an unsupervised deep learning method that estimates motion fields between frames; their method outperformed conventional approaches in landmark tracking accuracy and inference efficiency on a clinical dataset.
Cardiac tagging magnetic resonance imaging (t-MRI) is the gold standard for regional myocardium deformation and cardiac strain estimation. However, this technique has not been widely used in clinical diagnosis, as a result of the difficulty of motion tracking encountered with t-MRI images. In this paper, we propose a novel deep learning-based fully unsupervised method for in vivo motion tracking on t-MRI images. We first estimate the motion field (INF) between any two consecutive t-MRI frames by a bi-directional generative diffeomorphic registration neural network. Using this result, we then estimate the Lagrangian motion field between the reference frame and any other frame through a differentiable composition layer. By utilizing temporal information to perform reasonable estimations on spatio-temporal motion fields, this novel method provides a useful solution for motion tracking and image registration in dynamic medical imaging. Our method has been validated on a representative clinical t-MRI dataset; the experimental results show that our method is superior to conventional motion tracking methods in terms of landmark tracking accuracy and inference efficiency.